مرکز دیتای نیکراد

{
    "id": "llmtr/gemma-4",
    "object": "model",
    "created": 1776880304,
    "owned_by": "llmtr",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Gemma 4",
    "description": "Türkiye'de barindirilan Gemma 4; 128K baglam, gorsel girdi ve arac cagrisi.",
    "context_length": 131072,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000002",
        "completion": "0.000005",
        "input_cache_read": "0.0000005"
    },
    "top_provider": {
        "context_length": 131072,
        "max_completion_tokens": 131072,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": []
    }
}

{
    "id": "llmtr/qwen3-6-35b",
    "object": "model",
    "created": 1776880304,
    "owned_by": "llmtr",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen 3.6 35B-A3B",
    "description": "Türkiye'de barindirilan kod ve mantik agirlikli isler icin yerli Qwen modeli.",
    "context_length": 262144,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000005",
        "completion": "0.000005"
    },
    "top_provider": {
        "context_length": 262144,
        "max_completion_tokens": 65536,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": []
    }
}

{
    "id": "llmtr/qwen3-8-27b",
    "object": "model",
    "created": 1791267994,
    "owned_by": "llmtr",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen 3.8 27B",
    "description": "Verilerin Türkiye'de işlenmesi gereken ajan, kod ve uzun belge işleri için 262K bağlamlı, araç çağırabilen Qwen 3.8 27B.",
    "context_length": 262144,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000005",
        "completion": "0.000007",
        "input_cache_read": "0.00000125"
    },
    "top_provider": {
        "context_length": 262144,
        "max_completion_tokens": 262144,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": []
    }
}

{
    "id": "llmtr/trendyol-asure-12b",
    "object": "model",
    "created": 1786690403,
    "owned_by": "llmtr",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Trendyol Asure 12B",
    "description": "Turkce sohbet, RAG chatbot ve e-ticaret metin isleri icin Turkiye'de barindirilan, gorsel okuyabilen 12B model.",
    "context_length": 40960,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000001",
        "completion": "0.0000005",
        "input_cache_read": "0.000000025"
    },
    "top_provider": {
        "context_length": 40960,
        "max_completion_tokens": 40960,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "temperature",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "llmtr/magibu-11b-v8",
    "object": "model",
    "created": 1780689763,
    "owned_by": "llmtr",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Magibu 11B v8",
    "description": "Turkce sohbet ve yardimci akislar icin Magibu ekibi tarafindan gelistirilmis 11B LLMTR modeli.",
    "context_length": 8192,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000001",
        "completion": "0.0000005"
    },
    "top_provider": {
        "context_length": 8192,
        "max_completion_tokens": 8192,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "temperature",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "llmtr/muse-glimmer-30b-tr",
    "object": "model",
    "created": 1786702265,
    "owned_by": "llmtr",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Muse Glimmer 30B (Türkiye)",
    "description": "Verilerin Türkiye'de işlenmesi gereken ajan ve akıl yürütme işleri için 128K bağlamlı, görsel okuyabilen 30B model.",
    "context_length": 131072,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000002",
        "completion": "0.000005",
        "input_cache_read": "0.0000005"
    },
    "top_provider": {
        "context_length": 131072,
        "max_completion_tokens": 131072,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "llmtr/leyla",
    "object": "model",
    "created": 1790679228,
    "owned_by": "llmtr",
    "supported_operations": [
        "SYSTEM_ONE"
    ],
    "supported_endpoints": [
        "/v1/systemone"
    ],
    "name": "Leyla",
    "description": "Türkiye'de barındırılan ilk System One modeli: Türkçe metinleri yönlendirme ve sınıflandırma için olasılıklı kararlara çevirir.",
    "context_length": 1024,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000003",
        "completion": "0"
    },
    "top_provider": {
        "context_length": 1024,
        "max_completion_tokens": 1024,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "llmtr/embeddingmagibu-200m",
    "object": "model",
    "created": 1792040573,
    "owned_by": "llmtr",
    "supported_operations": [
        "EMBEDDINGS"
    ],
    "supported_endpoints": [
        "/v1/embeddings"
    ],
    "name": "EmbeddingMagibu 200M",
    "description": "Türkçe arama, RAG ve benzerlik için Türkiye'de barındırılan embedding modeli.",
    "context_length": 8192,
    "architecture": {
        "modality": "text->embedding",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "embedding"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000001"
    },
    "top_provider": {
        "context_length": 8192,
        "max_completion_tokens": 8192,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "llmtr/qwen3-5-4b",
    "object": "model",
    "created": 1783962981,
    "owned_by": "llmtr",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen 3.5 4B",
    "description": "Türkçe sohbet, RAG ve araç çağırma akışları için Türkiye'de barındırılan 128K bağlamlı 4B model.",
    "context_length": 131072,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000001",
        "completion": "0.000003",
        "input_cache_read": "0.00000025"
    },
    "top_provider": {
        "context_length": 131072,
        "max_completion_tokens": 65536,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "openai/gpt-6-astra",
    "object": "model",
    "created": 1788586945,
    "owned_by": "openai",
    "supported_operations": [
        "RESPONSES"
    ],
    "supported_endpoints": [
        "/v1/responses"
    ],
    "name": "GPT-6 Astra",
    "description": "Uçtan uca zor işler, ajan akışları ve bilgisayar kullanımı için OpenAI'nin en yetenekli modeli.",
    "context_length": 1050000,
    "architecture": {
        "modality": "text+image+file->text",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00001",
        "completion": "0.00005",
        "input_cache_read": "0.000001",
        "input_cache_write": "0.0000125"
    },
    "top_provider": {
        "context_length": 1050000,
        "max_completion_tokens": 1050000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "tool_choice",
        "tools"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": [
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ]
    }
}

{
    "id": "openai/gpt-6.1-sol",
    "object": "model",
    "created": 1790747189,
    "owned_by": "openai",
    "supported_operations": [
        "RESPONSES"
    ],
    "supported_endpoints": [
        "/v1/responses"
    ],
    "name": "GPT-6.1 Sol",
    "description": "Ajan tabanlı kodlama, bilgisayar kullanımı ve belge ağırlıklı profesyonel işler için geliştirilmiş Sol modeli.",
    "context_length": 1050000,
    "architecture": {
        "modality": "text+image+file->text",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000002",
        "completion": "0.00001",
        "input_cache_read": "0.0000001",
        "input_cache_write": "0.0000025"
    },
    "top_provider": {
        "context_length": 1050000,
        "max_completion_tokens": 1050000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "tool_choice",
        "tools"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": [
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ]
    }
}

{
    "id": "openai/gpt-6-sol",
    "object": "model",
    "created": 1790159267,
    "owned_by": "openai",
    "supported_operations": [
        "RESPONSES"
    ],
    "supported_endpoints": [
        "/v1/responses"
    ],
    "name": "GPT-6 Sol",
    "description": "Zor akıl yürütme, kod ve ajan işleri için GPT-6 Astra'nın güçlü yönlerini daha düşük maliyetle sunan model.",
    "context_length": 1050000,
    "architecture": {
        "modality": "text+image+file->text",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000002",
        "completion": "0.00001",
        "input_cache_read": "0.0000002",
        "input_cache_write": "0.0000025"
    },
    "top_provider": {
        "context_length": 1050000,
        "max_completion_tokens": 1050000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "tool_choice",
        "tools"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": [
            "none",
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ]
    }
}

{
    "id": "openai/gpt-6-luna",
    "object": "model",
    "created": 1790159267,
    "owned_by": "openai",
    "supported_operations": [
        "RESPONSES"
    ],
    "supported_endpoints": [
        "/v1/responses"
    ],
    "name": "GPT-6 Luna",
    "description": "Hızlı yanıt ve yüksek hacimli, maliyet hassas işler için GPT-6 modeli.",
    "context_length": 1050000,
    "architecture": {
        "modality": "text+image+file->text",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000001",
        "completion": "0.0000005",
        "input_cache_read": "0.00000001",
        "input_cache_write": "0.000000125"
    },
    "top_provider": {
        "context_length": 1050000,
        "max_completion_tokens": 1050000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "tool_choice",
        "tools"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": [
            "none",
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ]
    }
}

{
    "id": "openai/gpt-5.6-sol",
    "object": "model",
    "created": 1783622629,
    "owned_by": "openai",
    "supported_operations": [
        "RESPONSES"
    ],
    "supported_endpoints": [
        "/v1/responses"
    ],
    "name": "GPT-5.6 Sol",
    "description": "GPT-5.6 Sol: zor reasoning, kod ve ajan akışları için OpenAI GPT-5.6 preview modeli.",
    "context_length": 1050000,
    "architecture": {
        "modality": "text+image+file->text",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000004",
        "completion": "0.00002",
        "input_cache_read": "0.0000004"
    },
    "top_provider": {
        "context_length": 1050000,
        "max_completion_tokens": 1050000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "tool_choice",
        "tools"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": [
            "none",
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ]
    }
}

{
    "id": "openai/gpt-5.6-sol-pro",
    "object": "model",
    "created": 1783622629,
    "owned_by": "openai",
    "supported_operations": [
        "RESPONSES"
    ],
    "supported_endpoints": [
        "/v1/responses"
    ],
    "name": "GPT-5.6 Sol Pro",
    "description": "GPT-5.6 Sol Pro: pro modda zor reasoning, kod ve ajan akışları için OpenAI GPT-5.6 preview modeli.",
    "context_length": 1050000,
    "architecture": {
        "modality": "text+image+file->text",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000004",
        "completion": "0.00002",
        "input_cache_read": "0.0000004"
    },
    "top_provider": {
        "context_length": 1050000,
        "max_completion_tokens": 1050000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "tool_choice",
        "tools"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": [
            "none",
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ]
    }
}

{
    "id": "openai/gpt-5.6-terra",
    "object": "model",
    "created": 1783622629,
    "owned_by": "openai",
    "supported_operations": [
        "RESPONSES"
    ],
    "supported_endpoints": [
        "/v1/responses"
    ],
    "name": "GPT-5.6 Terra",
    "description": "GPT-5.6 Terra: zeka ve maliyet dengesi isteyen üretim işleri için OpenAI GPT-5.6 preview modeli.",
    "context_length": 1050000,
    "architecture": {
        "modality": "text+image+file->text",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000002",
        "completion": "0.000012",
        "input_cache_read": "0.0000002"
    },
    "top_provider": {
        "context_length": 1050000,
        "max_completion_tokens": 1050000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "tool_choice",
        "tools"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": [
            "none",
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ]
    }
}

{
    "id": "openai/gpt-5.6-terra-pro",
    "object": "model",
    "created": 1783622629,
    "owned_by": "openai",
    "supported_operations": [
        "RESPONSES"
    ],
    "supported_endpoints": [
        "/v1/responses"
    ],
    "name": "GPT-5.6 Terra Pro",
    "description": "GPT-5.6 Terra Pro: pro modda zeka-maliyet dengesi isteyen işler için OpenAI GPT-5.6 preview modeli.",
    "context_length": 1050000,
    "architecture": {
        "modality": "text+image+file->text",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000002",
        "completion": "0.000012",
        "input_cache_read": "0.0000002"
    },
    "top_provider": {
        "context_length": 1050000,
        "max_completion_tokens": 1050000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "tool_choice",
        "tools"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": [
            "none",
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ]
    }
}

{
    "id": "openai/gpt-5.6-luna",
    "object": "model",
    "created": 1783622629,
    "owned_by": "openai",
    "supported_operations": [
        "RESPONSES"
    ],
    "supported_endpoints": [
        "/v1/responses"
    ],
    "name": "GPT-5.6 Luna",
    "description": "GPT-5.6 Luna: maliyet hassas ve yüksek hacimli işler için OpenAI GPT-5.6 preview modeli.",
    "context_length": 1050000,
    "architecture": {
        "modality": "text+image+file->text",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000002",
        "completion": "0.0000012",
        "input_cache_read": "0.00000002"
    },
    "top_provider": {
        "context_length": 1050000,
        "max_completion_tokens": 1050000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "tool_choice",
        "tools"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": [
            "none",
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ]
    }
}

{
    "id": "openai/gpt-5.6-luna-pro",
    "object": "model",
    "created": 1783622629,
    "owned_by": "openai",
    "supported_operations": [
        "RESPONSES"
    ],
    "supported_endpoints": [
        "/v1/responses"
    ],
    "name": "GPT-5.6 Luna Pro",
    "description": "GPT-5.6 Luna Pro: pro modda maliyet hassas yüksek hacimli işler için OpenAI GPT-5.6 preview modeli.",
    "context_length": 1050000,
    "architecture": {
        "modality": "text+image+file->text",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000002",
        "completion": "0.0000012",
        "input_cache_read": "0.00000002"
    },
    "top_provider": {
        "context_length": 1050000,
        "max_completion_tokens": 1050000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "tool_choice",
        "tools"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": [
            "none",
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ]
    }
}

{
    "id": "openai/gpt-5.5",
    "object": "model",
    "created": 1777134642,
    "owned_by": "openai",
    "supported_operations": [
        "RESPONSES"
    ],
    "supported_endpoints": [
        "/v1/responses"
    ],
    "name": "GPT-5.5",
    "description": "Kod, derin analiz ve ajan orkestrasyonu için olgun OpenAI frontier modeli.",
    "context_length": 1050000,
    "architecture": {
        "modality": "text+image+file->text",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000005",
        "completion": "0.00003",
        "input_cache_read": "0.0000005"
    },
    "top_provider": {
        "context_length": 1050000,
        "max_completion_tokens": 1050000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "tool_choice",
        "tools"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": [
            "none",
            "low",
            "medium",
            "high",
            "xhigh"
        ]
    }
}

{
    "id": "openai/gpt-5.5-pro",
    "object": "model",
    "created": 1781584660,
    "owned_by": "openai",
    "supported_operations": [
        "RESPONSES"
    ],
    "supported_endpoints": [
        "/v1/responses"
    ],
    "name": "GPT-5.5 Pro",
    "description": "En zor reasoning, kod ve uzun bağlamlı analiz için GPT-5.5 Pro.",
    "context_length": 1050000,
    "architecture": {
        "modality": "text+image+file->text",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00003",
        "completion": "0.00018"
    },
    "top_provider": {
        "context_length": 1050000,
        "max_completion_tokens": 1050000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "tool_choice",
        "tools"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": [
            "none",
            "low",
            "medium",
            "high",
            "xhigh"
        ]
    }
}

{
    "id": "openai/gpt-5.4",
    "object": "model",
    "created": 1776880298,
    "owned_by": "openai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GPT-5.4",
    "description": "Zor muhakeme ve üretim ajanları için olgun ve dengeli OpenAI modeli.",
    "context_length": 272000,
    "architecture": {
        "modality": "text+image+file+audio->text",
        "input_modalities": [
            "text",
            "image",
            "file",
            "audio"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000025",
        "completion": "0.000015"
    },
    "top_provider": {
        "context_length": 272000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "openai/gpt-5.4-mini",
    "object": "model",
    "created": 1776880298,
    "owned_by": "openai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GPT-5.4 mini",
    "description": "Kod yardımcıları ve alt ajan akışları için en dengeli GPT-5.4 mini modeli.",
    "context_length": 128000,
    "architecture": {
        "modality": "text+image+file+audio->text",
        "input_modalities": [
            "text",
            "image",
            "file",
            "audio"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000075",
        "completion": "0.0000045"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "openai/gpt-5.2",
    "object": "model",
    "created": 1776880298,
    "owned_by": "openai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GPT-5.2",
    "description": "Kod üretimi ve çok adımlı ajan işleri için üst seviye GPT-5 modeli.",
    "context_length": 128000,
    "architecture": {
        "modality": "text+image+file+audio->text",
        "input_modalities": [
            "text",
            "image",
            "file",
            "audio"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000175",
        "completion": "0.000014"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "openai/o3",
    "object": "model",
    "created": 1776880299,
    "owned_by": "openai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "o3",
    "description": "Zor teknik analiz ve çok adımlı problem çözümü için güçlü reasoning modeli.",
    "context_length": 200000,
    "architecture": {
        "modality": "text+image+file->text",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000002",
        "completion": "0.000008"
    },
    "top_provider": {
        "context_length": 200000,
        "max_completion_tokens": 100003,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "tool_choice",
        "tools"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": [
            "low",
            "medium",
            "high"
        ]
    }
}

{
    "id": "openai/gpt-image-2",
    "object": "model",
    "created": 1777134643,
    "owned_by": "openai",
    "supported_operations": [
        "IMAGES_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/images/generations"
    ],
    "name": "GPT Image 2",
    "description": "Üretim kalitesinde görsel üretim için OpenAI görüntü modeli.",
    "context_length": 32000,
    "architecture": {
        "modality": "text+image->image",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "image"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000005"
    },
    "top_provider": {
        "context_length": 32000,
        "max_completion_tokens": 32000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "google/gemini-4-argon",
    "object": "model",
    "created": 1792049934,
    "owned_by": "google",
    "supported_operations": [
        "CHAT_COMPLETIONS",
        "RESPONSES"
    ],
    "supported_endpoints": [
        "/v1/chat/completions",
        "/v1/responses"
    ],
    "name": "Gemini 4 Argon",
    "description": "Zor yazılım, bilim ve çok adımlı ajan işleri için Google'ın amiral gemisi akıl yürütme modeli.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text+image+file+audio+video->text",
        "input_modalities": [
            "text",
            "image",
            "file",
            "audio",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000002",
        "completion": "0.00001",
        "input_cache_read": "0.0000001",
        "audio": "0.000002"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 1048576,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
            "low",
            "medium",
            "high"
        ]
    }
}

{
    "id": "google/gemini-3.8-flash",
    "object": "model",
    "created": 1788419901,
    "owned_by": "google",
    "supported_operations": [
        "CHAT_COMPLETIONS",
        "RESPONSES"
    ],
    "supported_endpoints": [
        "/v1/chat/completions",
        "/v1/responses"
    ],
    "name": "Gemini 3.8 Flash",
    "description": "Uzun soluklu kod işleri ve otonom ajanlar için Google'ın güncel Flash modeli.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text+image+file+audio+video->text",
        "input_modalities": [
            "text",
            "image",
            "file",
            "audio",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000075",
        "completion": "0.00000375",
        "input_cache_read": "0.000000075",
        "audio": "0.00000075"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 65536,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
            "low",
            "medium",
            "high"
        ]
    }
}

{
    "id": "google/gemini-3.7-flash",
    "object": "model",
    "created": 1786681642,
    "owned_by": "google",
    "supported_operations": [
        "CHAT_COMPLETIONS",
        "RESPONSES"
    ],
    "supported_endpoints": [
        "/v1/chat/completions",
        "/v1/responses"
    ],
    "name": "Gemini 3.7 Flash",
    "description": "Ajan ve kod işleri için Google'ın güncel Flash modeli.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text+image+file+audio+video->text",
        "input_modalities": [
            "text",
            "image",
            "file",
            "audio",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000075",
        "completion": "0.00000375",
        "input_cache_read": "0.000000075",
        "audio": "0.00000075"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 65536,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
            "low",
            "medium",
            "high"
        ]
    }
}

{
    "id": "google/gemini-2.5-flash-image",
    "object": "model",
    "created": 1776880300,
    "owned_by": "google",
    "supported_operations": [
        "IMAGES_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/images/generations"
    ],
    "name": "Gemini 2.5 Flash Image",
    "description": "Hızlı görsel üretim ve düzenleme için Gemini görüntü modeli.",
    "context_length": 0,
    "architecture": {
        "modality": "text+image->image",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "image"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000003",
        "completion": "0.0000025",
        "image_output": "0.039"
    },
    "top_provider": {
        "context_length": 0,
        "max_completion_tokens": 0,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "google/gemini-2.5-flash-native-audio-preview-12-2025",
    "object": "model",
    "created": 1776880300,
    "owned_by": "google",
    "supported_operations": [
        "REALTIME_SESSION"
    ],
    "supported_endpoints": [
        "/v1/realtime/sessions"
    ],
    "name": "Gemini 2.5 Flash Native Audio (Live API)",
    "description": "Gerçek zamanlı sesli diyalog için Gemini Live ses modeli.",
    "context_length": 128000,
    "architecture": {
        "modality": "text+audio+video->text",
        "input_modalities": [
            "text",
            "audio",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000005",
        "completion": "0.000002",
        "audio": "0.000003"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "google/gemini-2.5-flash-preview-tts",
    "object": "model",
    "created": 1776880300,
    "owned_by": "google",
    "supported_operations": [
        "AUDIO_SPEECH"
    ],
    "supported_endpoints": [
        "/v1/audio/speech"
    ],
    "name": "Gemini 2.5 Flash Preview TTS",
    "description": "Hızlı ve yönlendirilebilir konuşma üretimi için Gemini TTS modeli.",
    "context_length": 0,
    "architecture": {
        "modality": "text+audio->audio",
        "input_modalities": [
            "text",
            "audio"
        ],
        "output_modalities": [
            "audio"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000005"
    },
    "top_provider": {
        "context_length": 0,
        "max_completion_tokens": 0,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "google/gemini-2.5-pro-preview-tts",
    "object": "model",
    "created": 1776880300,
    "owned_by": "google",
    "supported_operations": [
        "AUDIO_SPEECH"
    ],
    "supported_endpoints": [
        "/v1/audio/speech"
    ],
    "name": "Gemini 2.5 Pro Preview TTS",
    "description": "Daha doğal ve güçlü ses çıkışı için Gemini Pro TTS modeli.",
    "context_length": 0,
    "architecture": {
        "modality": "text+audio->audio",
        "input_modalities": [
            "text",
            "audio"
        ],
        "output_modalities": [
            "audio"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000001"
    },
    "top_provider": {
        "context_length": 0,
        "max_completion_tokens": 0,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "google/gemini-3-flash-preview",
    "object": "model",
    "created": 1776880300,
    "owned_by": "google",
    "supported_operations": [
        "CHAT_COMPLETIONS",
        "RESPONSES"
    ],
    "supported_endpoints": [
        "/v1/chat/completions",
        "/v1/responses"
    ],
    "name": "Gemini 3 Flash Preview",
    "description": "Hızlı multimodal yardımcılar ve ajan deneyleri için Gemini 3 preview modeli.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text+image+file+audio+video->text",
        "input_modalities": [
            "text",
            "image",
            "file",
            "audio",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000005",
        "completion": "0.000003",
        "input_cache_write": "0.00000005",
        "audio": "0.000001"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 65536,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "google/gemini-3.1-flash-lite",
    "object": "model",
    "created": 1778648402,
    "owned_by": "google",
    "supported_operations": [
        "CHAT_COMPLETIONS",
        "RESPONSES"
    ],
    "supported_endpoints": [
        "/v1/chat/completions",
        "/v1/responses"
    ],
    "name": "Gemini 3.1 Flash-Lite",
    "description": "Yuksek hacimli hafif multimodal isler icin GA Gemini 3.1 secenegi.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text+image+file+audio+video->text",
        "input_modalities": [
            "text",
            "image",
            "file",
            "audio",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000025",
        "completion": "0.0000015",
        "input_cache_write": "0.000000025",
        "audio": "0.0000005"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 65536,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": []
    }
}

{
    "id": "google/gemini-3.1-pro-preview",
    "object": "model",
    "created": 1776880300,
    "owned_by": "google",
    "supported_operations": [
        "CHAT_COMPLETIONS",
        "RESPONSES"
    ],
    "supported_endpoints": [
        "/v1/chat/completions",
        "/v1/responses"
    ],
    "name": "Gemini 3.1 Pro Preview",
    "description": "Yazılım, araştırma ve grounded reasoning için üst seviye Gemini 3.1 preview modeli.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text+image+file+audio+video->text",
        "input_modalities": [
            "text",
            "image",
            "file",
            "audio",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000002",
        "completion": "0.000012"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 65536,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "google/gemini-3.1-pro-preview-customtools",
    "object": "model",
    "created": 1776880300,
    "owned_by": "google",
    "supported_operations": [
        "CHAT_COMPLETIONS",
        "RESPONSES"
    ],
    "supported_endpoints": [
        "/v1/chat/completions",
        "/v1/responses"
    ],
    "name": "Gemini 3.1 Pro Preview",
    "description": "Yazılım, araştırma ve grounded reasoning için üst seviye Gemini 3.1 preview modeli.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text+image+file+audio+video->text",
        "input_modalities": [
            "text",
            "image",
            "file",
            "audio",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000002",
        "completion": "0.000012"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 65536,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "google/gemini-3.5-flash",
    "object": "model",
    "created": 1779259201,
    "owned_by": "google",
    "supported_operations": [
        "CHAT_COMPLETIONS",
        "RESPONSES"
    ],
    "supported_endpoints": [
        "/v1/chat/completions",
        "/v1/responses"
    ],
    "name": "Gemini 3.5 Flash",
    "description": "Ajan, kod ve multimodal ürün akışları için kararlı Gemini Flash modeli.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text+image+file+audio+video->text",
        "input_modalities": [
            "text",
            "image",
            "file",
            "audio",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000015",
        "completion": "0.000009",
        "input_cache_read": "0.00000015",
        "audio": "0.0000015"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 65536,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": [
            "minimal",
            "low",
            "medium",
            "high"
        ]
    }
}

{
    "id": "google/gemini-3.5-flash-lite",
    "object": "model",
    "created": 1784702661,
    "owned_by": "google",
    "supported_operations": [
        "CHAT_COMPLETIONS",
        "RESPONSES"
    ],
    "supported_endpoints": [
        "/v1/chat/completions",
        "/v1/responses"
    ],
    "name": "Gemini 3.5 Flash-Lite",
    "description": "Yüksek hacimli ajan ve belge işleme için en uygun maliyetli Gemini modeli.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text+image+file+audio+video->text",
        "input_modalities": [
            "text",
            "image",
            "file",
            "audio",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000003",
        "completion": "0.0000025",
        "audio": "0.0000003"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 65536,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": [
            "minimal",
            "low",
            "medium",
            "high"
        ]
    }
}

{
    "id": "google/gemini-3.6-flash",
    "object": "model",
    "created": 1784702661,
    "owned_by": "google",
    "supported_operations": [
        "CHAT_COMPLETIONS",
        "RESPONSES"
    ],
    "supported_endpoints": [
        "/v1/chat/completions",
        "/v1/responses"
    ],
    "name": "Gemini 3.6 Flash",
    "description": "Ajan ve kod akışlarında daha az token harcayan kararlı Gemini Flash modeli.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text+image+file+audio+video->text",
        "input_modalities": [
            "text",
            "image",
            "file",
            "audio",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000015",
        "completion": "0.0000075",
        "input_cache_read": "0.00000015",
        "audio": "0.0000015"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 65536,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": [
            "minimal",
            "low",
            "medium",
            "high"
        ]
    }
}

{
    "id": "google/gemini-embedding-001",
    "object": "model",
    "created": 1776880300,
    "owned_by": "google",
    "supported_operations": [
        "EMBEDDINGS"
    ],
    "supported_endpoints": [
        "/v1/embeddings"
    ],
    "name": "Gemini Embedding",
    "description": "Metin tabanlı arama ve RAG için temel Gemini embedding modeli.",
    "context_length": 2048,
    "architecture": {
        "modality": "text->embedding",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "embedding"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000015"
    },
    "top_provider": {
        "context_length": 2048,
        "max_completion_tokens": 2048,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "google/gemini-embedding-2-preview",
    "object": "model",
    "created": 1776880300,
    "owned_by": "google",
    "supported_operations": [
        "EMBEDDINGS"
    ],
    "supported_endpoints": [
        "/v1/embeddings"
    ],
    "name": "Gemini Embedding 2 Preview",
    "description": "Metin, görsel ve belge araması için multimodal Gemini embedding modeli.",
    "context_length": 8192,
    "architecture": {
        "modality": "text+image+file+audio+video->embedding",
        "input_modalities": [
            "text",
            "image",
            "file",
            "audio",
            "video"
        ],
        "output_modalities": [
            "embedding"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000002",
        "completion": "0.000012",
        "image": "0.00012"
    },
    "top_provider": {
        "context_length": 8192,
        "max_completion_tokens": 8192,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "google/gemini-nano-banana-2.1",
    "object": "model",
    "created": 1791396533,
    "owned_by": "google",
    "supported_operations": [
        "IMAGES_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/images/generations"
    ],
    "name": "Gemini Nano Banana 2.1",
    "description": "Görsel üretimi ve düzenleme için Nano Banana 2'nin güncellenmiş Gemini modeli.",
    "context_length": 131072,
    "architecture": {
        "modality": "text+image+video->image",
        "input_modalities": [
            "text",
            "image",
            "video"
        ],
        "output_modalities": [
            "image"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000015",
        "completion": "0.0000075",
        "input_cache_read": "0.00000015",
        "image_output": "0.0336"
    },
    "top_provider": {
        "context_length": 131072,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "google/veo-3.1-fast-generate-001",
    "object": "model",
    "created": 1784312821,
    "owned_by": "google",
    "supported_operations": [
        "VIDEO_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/video/generations"
    ],
    "name": "Veo 3.1",
    "description": "Hız odaklı Veo 3.1 Fast video üretimi.",
    "context_length": 0,
    "architecture": {
        "modality": "text+image+video->video",
        "input_modalities": [
            "text",
            "image",
            "video"
        ],
        "output_modalities": [
            "video"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": [],
    "top_provider": {
        "context_length": 0,
        "max_completion_tokens": 0,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "google/veo-3.1-generate-001",
    "object": "model",
    "created": 1784312821,
    "owned_by": "google",
    "supported_operations": [
        "VIDEO_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/video/generations"
    ],
    "name": "Veo 3.1",
    "description": "En güncel Veo 3.1 ile yüksek kaliteli sesli video üretimi.",
    "context_length": 0,
    "architecture": {
        "modality": "text+image+video->video",
        "input_modalities": [
            "text",
            "image",
            "video"
        ],
        "output_modalities": [
            "video"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": [],
    "top_provider": {
        "context_length": 0,
        "max_completion_tokens": 0,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "google/veo-3.1-lite-generate-001",
    "object": "model",
    "created": 1784312821,
    "owned_by": "google",
    "supported_operations": [
        "VIDEO_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/video/generations"
    ],
    "name": "Veo 3.1",
    "description": "En ekonomik Veo katmanı: Veo 3.1 Lite.",
    "context_length": 0,
    "architecture": {
        "modality": "text+image+video->video",
        "input_modalities": [
            "text",
            "image",
            "video"
        ],
        "output_modalities": [
            "video"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": [],
    "top_provider": {
        "context_length": 0,
        "max_completion_tokens": 0,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "anthropic/claude-fable-5.1",
    "object": "model",
    "created": 1788325708,
    "owned_by": "anthropic",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Claude Fable 5.1",
    "description": "Anthropic'in en güçlü genel erişimli Claude modeli; Fable 5'in halefi.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text+image+file->text",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00001",
        "completion": "0.00005",
        "input_cache_read": "0.00000025",
        "input_cache_write": "0.0000125",
        "input_cache_write_1h": "0.00002"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning_effort",
        "tool_choice",
        "tools"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ]
    }
}

{
    "id": "anthropic/claude-opus-5.5",
    "object": "model",
    "created": 1790143054,
    "owned_by": "anthropic",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Claude Opus 5.5",
    "description": "Uzun soluklu ajan kodlaması ve bilgi işleri için güncel Opus; Opus 5'in halefi.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000004",
        "completion": "0.00002",
        "input_cache_read": "0.0000002",
        "input_cache_write": "0.000005",
        "input_cache_write_1h": "0.000008"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning_effort",
        "tool_choice",
        "tools"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": [
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ]
    }
}

{
    "id": "anthropic/claude-fable-5",
    "object": "model",
    "created": 1781032857,
    "owned_by": "anthropic",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Claude Fable 5",
    "description": "Fable serisinin önceki nesli; uzun soluklu ajan ve kod işleri için oturmuş seçenek.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text+image+file->text",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00001",
        "completion": "0.00005"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning_effort",
        "tool_choice",
        "tools"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": [
            "low",
            "medium",
            "high",
            "xhigh"
        ]
    }
}

{
    "id": "anthropic/claude-opus-5",
    "object": "model",
    "created": 1784917542,
    "owned_by": "anthropic",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Claude Opus 5",
    "description": "Opus serisinin önceki nesli; mevcut ajan ve kod entegrasyonları için oturmuş seçenek.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text+image+file->text",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000005",
        "completion": "0.000025",
        "input_cache_read": "0.0000005",
        "input_cache_write": "0.00000625",
        "input_cache_write_1h": "0.00001"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning_effort",
        "tool_choice",
        "tools"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ]
    }
}

{
    "id": "anthropic/claude-opus-4.8",
    "object": "model",
    "created": 1779990987,
    "owned_by": "anthropic",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Claude Opus 4.8",
    "description": "Zor reasoning, kod ve uzun soluklu ajan işleri için stabil Opus modeli.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text+image+file->text",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000005",
        "completion": "0.000025"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning_effort",
        "tool_choice",
        "tools"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": [
            "low",
            "medium",
            "high",
            "xhigh"
        ]
    }
}

{
    "id": "anthropic/claude-opus-4.7",
    "object": "model",
    "created": 1778841199,
    "owned_by": "anthropic",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Claude Opus 4.7",
    "description": "Zor kod, derin analiz ve uzun soluklu ajan işleri için önceki nesil Opus.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text+image+file->text",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000005",
        "completion": "0.000025"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning_effort",
        "tool_choice",
        "tools"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": [
            "low",
            "medium",
            "high",
            "xhigh"
        ]
    }
}

{
    "id": "anthropic/claude-opus-4.6",
    "object": "model",
    "created": 1776880299,
    "owned_by": "anthropic",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Claude Opus 4.6",
    "description": "Uzun soluklu ajanlar ve ağır kod işleri için önceki nesil Opus.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text+image+file->text",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000005",
        "completion": "0.000025"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "anthropic/claude-opus-4.5",
    "object": "model",
    "created": 1776880299,
    "owned_by": "anthropic",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Claude Opus 4.5",
    "description": "Derin analiz ve üst seviye kod kalitesi için premium Opus modeli.",
    "context_length": 200000,
    "architecture": {
        "modality": "text+image+file->text",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000005",
        "completion": "0.000025"
    },
    "top_provider": {
        "context_length": 200000,
        "max_completion_tokens": 64000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "anthropic/claude-sonnet-5.5",
    "object": "model",
    "created": 1790654019,
    "owned_by": "anthropic",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Claude Sonnet 5.5",
    "description": "Kod, ajan ve günlük üretim işleri için güncel Sonnet; Sonnet 5'in halefi.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000002",
        "completion": "0.00001",
        "input_cache_read": "0.0000001",
        "input_cache_write": "0.0000025",
        "input_cache_write_1h": "0.000004"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning_effort",
        "tool_choice",
        "tools"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
            "none",
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ]
    }
}

{
    "id": "anthropic/claude-sonnet-5",
    "object": "model",
    "created": 1782880538,
    "owned_by": "anthropic",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Claude Sonnet 5",
    "description": "Kod, ajan ve uzun bağlamlı işler için önceki nesil Sonnet.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text+image+file->text",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000002",
        "completion": "0.00001",
        "input_cache_read": "0.0000002",
        "input_cache_write": "0.0000025",
        "input_cache_write_1h": "0.000004"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning_effort",
        "tool_choice",
        "tools"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
            "low",
            "medium",
            "high",
            "xhigh"
        ]
    }
}

{
    "id": "anthropic/claude-sonnet-4.6",
    "object": "model",
    "created": 1776880299,
    "owned_by": "anthropic",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Claude Sonnet 4.6",
    "description": "Mevcut entegrasyonlar için güçlü, stabil Sonnet 4.6 seçeneği.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text+image+file->text",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000003",
        "completion": "0.000015"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "anthropic/claude-sonnet-4.5",
    "object": "model",
    "created": 1776880299,
    "owned_by": "anthropic",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Claude Sonnet 4.5",
    "description": "Kod yardımı ve günlük ajan işleri için güçlü önceki Sonnet modeli.",
    "context_length": 200000,
    "architecture": {
        "modality": "text+image+file->text",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000003",
        "completion": "0.000015"
    },
    "top_provider": {
        "context_length": 200000,
        "max_completion_tokens": 64000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "anthropic/claude-haiku-5.5",
    "object": "model",
    "created": 1791447418,
    "owned_by": "anthropic",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Claude Haiku 5.5",
    "description": "Sınıflandırma, yönlendirme ve alt ajan işleri için güncel Haiku; Haiku 4.5'in halefi.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000001",
        "completion": "0.0000005",
        "input_cache_read": "0.00000001",
        "input_cache_write": "0.000000125",
        "input_cache_write_1h": "0.0000002"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning_effort",
        "tool_choice",
        "tools"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
            "none",
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ]
    }
}

{
    "id": "anthropic/claude-haiku-4.5",
    "object": "model",
    "created": 1776880299,
    "owned_by": "anthropic",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Claude Haiku 4.5",
    "description": "Mevcut entegrasyonlar için hızlı, stabil Haiku 4.5 seçeneği.",
    "context_length": 200000,
    "architecture": {
        "modality": "text+image+file->text",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000001",
        "completion": "0.000005"
    },
    "top_provider": {
        "context_length": 200000,
        "max_completion_tokens": 64000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "qwen/qwen3.8-max",
    "object": "model",
    "created": 1785830140,
    "owned_by": "qwen",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen3.8-Max",
    "description": "Uzun soluklu ajan görevleri, görsel anlama ve kod üretimi için Qwen'in üst seviye modeli.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text+image+video->text",
        "input_modalities": [
            "text",
            "image",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000002",
        "completion": "0.000006",
        "input_cache_read": "0.00000025"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 131072,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p",
        "web_search_options"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "qwen/qwen3.7-max",
    "object": "model",
    "created": 1779380077,
    "owned_by": "qwen",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen3.7-Max",
    "description": "Zor ajan gorevleri ve kontrollu thinking icin Qwen'in en yeni Max modeli.",
    "context_length": 256000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000025",
        "completion": "0.0000075"
    },
    "top_provider": {
        "context_length": 256000,
        "max_completion_tokens": 131072,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "temperature",
        "tool_choice",
        "tools",
        "top_p",
        "web_search_options"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "qwen/qwen3.7-plus",
    "object": "model",
    "created": 1780503703,
    "owned_by": "qwen",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen3.7-Plus",
    "description": "Gorsel, video ve metin girdili ajan akislari icin dengeli Qwen3.7 modeli.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text+image+video->text",
        "input_modalities": [
            "text",
            "image",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000004",
        "completion": "0.0000016",
        "input_cache_read": "0.00000008"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 131072,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "temperature",
        "tool_choice",
        "tools",
        "top_p",
        "web_search_options"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "qwen/qwen3.8-flash",
    "object": "model",
    "created": 1787806692,
    "owned_by": "qwen",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen3.8-Flash",
    "description": "Uzun belgeler, görsel analiz ve araç kullanan uygulamalar için 1M bağlamlı Qwen Flash modeli.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text+image+video->text",
        "input_modalities": [
            "text",
            "image",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000015",
        "completion": "0.00000047",
        "input_cache_read": "0.000000016"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 131072,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "qwen/qwen3.6-flash",
    "object": "model",
    "created": 1781016211,
    "owned_by": "qwen",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen3.6-Flash",
    "description": "Gunluk metin isleri ve yardimci akislari icin genel Qwen modeli.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000025",
        "completion": "0.0000015"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 65536,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "temperature",
        "tool_choice",
        "tools",
        "top_p",
        "web_search_options"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "qwen/qwen-plus",
    "object": "model",
    "created": 1776880301,
    "owned_by": "qwen",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen-Plus",
    "description": "Uzun baglamli yardimcilar ve aracli urun akislari icin dengeli Qwen modeli.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000004",
        "completion": "0.0000012",
        "input_cache_read": "0.00000008"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p",
        "web_search_options"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": []
    }
}

{
    "id": "qwen/qwen-plus-2025-01-25",
    "object": "model",
    "created": 1776880301,
    "owned_by": "qwen",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen-Plus-2025-01-25",
    "description": "Uzun baglamli yardimcilar ve aracli urun akislari icin dengeli Qwen modeli; tarihli snapshot surumu.",
    "context_length": 256000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000004",
        "completion": "0.0000012"
    },
    "top_provider": {
        "context_length": 256000,
        "max_completion_tokens": 8192,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": []
    }
}

{
    "id": "qwen/qwen-plus-2025-04-28",
    "object": "model",
    "created": 1776880301,
    "owned_by": "qwen",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen-Plus-2025-04-28",
    "description": "Uzun baglamli yardimcilar ve aracli urun akislari icin dengeli Qwen modeli; tarihli snapshot surumu.",
    "context_length": 256000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000004",
        "completion": "0.0000012"
    },
    "top_provider": {
        "context_length": 256000,
        "max_completion_tokens": 16384,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p",
        "web_search_options"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": []
    }
}

{
    "id": "qwen/qwen-plus-2025-07-14",
    "object": "model",
    "created": 1776880301,
    "owned_by": "qwen",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen-Plus-2025-07-14",
    "description": "Uzun baglamli yardimcilar ve aracli urun akislari icin dengeli Qwen modeli; tarihli snapshot surumu.",
    "context_length": 256000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000004",
        "completion": "0.0000012"
    },
    "top_provider": {
        "context_length": 256000,
        "max_completion_tokens": 131072,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p",
        "web_search_options"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": []
    }
}

{
    "id": "qwen/qwen-plus-character-ja",
    "object": "model",
    "created": 1776880301,
    "owned_by": "qwen",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen-Plus-Character-Ja",
    "description": "Karakter tutarliligi ve rol yapma icin ozel Qwen modeli.",
    "context_length": 256000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000005",
        "completion": "0.0000014",
        "input_cache_read": "0.0000001"
    },
    "top_provider": {
        "context_length": 256000,
        "max_completion_tokens": 131072,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p",
        "web_search_options"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": []
    }
}

{
    "id": "qwen/qwen-plus-latest",
    "object": "model",
    "created": 1776880301,
    "owned_by": "qwen",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen-Plus-Latest",
    "description": "Uzun baglamli yardimcilar ve aracli urun akislari icin dengeli Qwen modeli.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000004",
        "completion": "0.0000012"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p",
        "web_search_options"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": []
    }
}

{
    "id": "qwen/qwen3.6-plus",
    "object": "model",
    "created": 1776880302,
    "owned_by": "qwen",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen3.6-Plus",
    "description": "Uzun baglamli yardimcilar ve aracli urun akislari icin dengeli Qwen modeli.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000005",
        "completion": "0.000003"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 65536,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p",
        "web_search_options"
    ],
    "per_request_limits": null
}

{
    "id": "qwen/qwen3.6-plus-2026-04-02",
    "object": "model",
    "created": 1776880302,
    "owned_by": "qwen",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen3.6-Plus-2026-04-02",
    "description": "Uzun baglamli yardimcilar ve aracli urun akislari icin dengeli Qwen modeli; tarihli snapshot surumu.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000005",
        "completion": "0.000003"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 65536,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p",
        "web_search_options"
    ],
    "per_request_limits": null
}

{
    "id": "zai/glm-5.3-flash",
    "object": "model",
    "created": 1787764704,
    "owned_by": "zai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-5.3-Flash",
    "description": "1M bağlamlı görsel kodlama ve hızlı ajan işleri için GLM-5.3-Flash.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000135",
        "completion": "0.00000045",
        "input_cache_read": "0.000000027"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 131072,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": [
            "low",
            "high",
            "max"
        ]
    }
}

{
    "id": "zai/glm-5.3-flashx",
    "object": "model",
    "created": 1789806797,
    "owned_by": "zai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-5.3-FlashX",
    "description": "Gecikmenin maliyetten önemli olduğu ajan döngüleri için hızlı GLM-5.3 satırı.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000333",
        "completion": "0.000001125",
        "input_cache_read": "0.0000000675"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 131072,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": [
            "low",
            "high",
            "max"
        ]
    }
}

{
    "id": "zai/glm-5.3",
    "object": "model",
    "created": 1787113304,
    "owned_by": "zai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-5.3",
    "description": "1M baglamli kod ve uzun soluklu ajan isleri icin GLM-5.3.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000126",
        "completion": "0.00000396",
        "input_cache_read": "0.000000234"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 131072,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": [
            "low",
            "high",
            "max"
        ]
    }
}

{
    "id": "zai/glm-5.2",
    "object": "model",
    "created": 1781716776,
    "owned_by": "zai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-5.2",
    "description": "1M contextli uzun kod, ajan ve function calling işleri için GLM-5.2.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000126",
        "completion": "0.00000396",
        "input_cache_read": "0.000000234"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 131072,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": [
            "none",
            "minimal",
            "low",
            "medium",
            "high",
            "xhigh"
        ]
    }
}

{
    "id": "zai/glm-5.1",
    "object": "model",
    "created": 1776880302,
    "owned_by": "zai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-5.1",
    "description": "Agentic engineering icin Z.AI'nin en guclu modeli.",
    "context_length": 128000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000126",
        "completion": "0.00000396",
        "input_cache_read": "0.000000234"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "zai/glm-5",
    "object": "model",
    "created": 1776880302,
    "owned_by": "zai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-5",
    "description": "Uzun ufuklu kod ve ajan isleri icin guclu GLM modeli.",
    "context_length": 128000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000009",
        "completion": "0.00000288",
        "input_cache_read": "0.00000018"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "zai/glm-5-turbo",
    "object": "model",
    "created": 1776880302,
    "owned_by": "zai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-5-Turbo",
    "description": "Uzun görev zincirleri ve araç kullanımı için hızlı GLM modeli.",
    "context_length": 128000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000108",
        "completion": "0.0000036",
        "input_cache_read": "0.000000216"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "zai/glm-5v-turbo",
    "object": "model",
    "created": 1776880303,
    "owned_by": "zai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-5V-Turbo",
    "description": "Gorsel kodlama ve GUI anlama icin GLM'nin guclu multimodal modeli.",
    "context_length": 128000,
    "architecture": {
        "modality": "text+image+file+video->text",
        "input_modalities": [
            "text",
            "image",
            "file",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000108",
        "completion": "0.0000036",
        "input_cache_read": "0.000000216"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "deepseek/deepseek-flash",
    "object": "model",
    "created": 1789033317,
    "owned_by": "deepseek",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "DeepSeek V4.1 Flash",
    "description": "Uzun bağlamlı ajan, kodlama ve görsel analiz işleri için 1M bağlamlı DeepSeek V4.1 Flash.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000015",
        "completion": "0.0000006",
        "input_cache_read": "0.000000003"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 393216,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "deepseek/deepseek-v4-pro",
    "object": "model",
    "created": 1777118751,
    "owned_by": "deepseek",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "DeepSeek V4 Pro",
    "description": "Zor muhakeme, ajan ve kodlama işleri için DeepSeek V4 Pro.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000066",
        "completion": "0.00000198",
        "input_cache_read": "0.000000022"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 393216,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "mistral/mistral-large-4",
    "object": "model",
    "created": 1791384007,
    "owned_by": "mistral",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Mistral Large 4",
    "description": "Talimat izleme, akıl yürütme ve araç kullanan ajan işleri için açık ağırlıklı Mistral modeli: 524K bağlam, görsel girdi, araç çağrısı; düşünme varsayılan olarak açık.",
    "context_length": 524288,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000136",
        "completion": "0.00000418",
        "input_cache_read": "0.00000014"
    },
    "top_provider": {
        "context_length": 524288,
        "max_completion_tokens": 262144,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
            "none",
            "high"
        ]
    }
}

{
    "id": "mistral/mistral-large-latest",
    "object": "model",
    "created": 1776880303,
    "owned_by": "mistral",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Mistral Large 3",
    "description": "Genel ürün yardımcıları ve görsel farkındalık için genel amaçlı büyük Mistral modeli.",
    "context_length": 256000,
    "architecture": {
        "modality": "text+image+file->text",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000005",
        "completion": "0.0000015"
    },
    "top_provider": {
        "context_length": 256000,
        "max_completion_tokens": 256000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "perplexity/sonar",
    "object": "model",
    "created": 1776880303,
    "owned_by": "perplexity",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Sonar",
    "description": "Hizli, kaynakli web cevaplari icin temel Sonar modeli.",
    "context_length": 128000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000001",
        "completion": "0.000001",
        "request": "0.005"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "temperature",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "mistral/mistral-small-latest",
    "object": "model",
    "created": 1776880303,
    "owned_by": "mistral",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Mistral Small 4",
    "description": "Günlük sohbet, reasoning ve kod yardımı için verimli hibrit Mistral modeli.",
    "context_length": 256000,
    "architecture": {
        "modality": "text+image+file->text",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000015",
        "completion": "0.0000006"
    },
    "top_provider": {
        "context_length": 256000,
        "max_completion_tokens": 256000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "perplexity/sonar-pro",
    "object": "model",
    "created": 1776880304,
    "owned_by": "perplexity",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Sonar Pro",
    "description": "Karmasik sorgular icin daha derin arama yapan Sonar.",
    "context_length": 200000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000003",
        "completion": "0.000015",
        "request": "0.006"
    },
    "top_provider": {
        "context_length": 200000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "temperature",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "mistral/mistral-medium-latest",
    "object": "model",
    "created": 1776880303,
    "owned_by": "mistral",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Mistral Medium 3.1",
    "description": "Araçlı ürün akışları ve planning için frontier seviye Mistral modeli.",
    "context_length": 128000,
    "architecture": {
        "modality": "text+image+file->text",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000004",
        "completion": "0.000002"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "perplexity/sonar-reasoning-pro",
    "object": "model",
    "created": 1776880304,
    "owned_by": "perplexity",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Sonar Reasoning Pro",
    "description": "Web kaynaklarını sentezleyerek zor karşılaştırmalar yapmak için Sonar modeli.",
    "context_length": 128000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000002",
        "completion": "0.000008",
        "request": "0.006"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "temperature",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "mistral/devstral-medium-latest",
    "object": "model",
    "created": 1776880303,
    "owned_by": "mistral",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Devstral 2",
    "description": "Yazilim muhendisligi ve kod ajanlari icin guclu Mistral modeli.",
    "context_length": 128000,
    "architecture": {
        "modality": "text+image+file->text",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000004",
        "completion": "0.000002"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "thinkingmachines/inkling",
    "object": "model",
    "created": 1784396336,
    "owned_by": "thinkingmachines",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Inkling",
    "description": "Thinking Machines'in 975B açık ağırlıklı MoE hibrit reasoning modeli; reasoning eforu none–xhigh arası ayarlanır.",
    "context_length": 262144,
    "architecture": {
        "modality": "text+image+audio->text",
        "input_modalities": [
            "text",
            "image",
            "audio"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000187",
        "completion": "0.00000468",
        "input_cache_read": "0.000000374"
    },
    "top_provider": {
        "context_length": 262144,
        "max_completion_tokens": 262144,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
            "none",
            "minimal",
            "low",
            "medium",
            "high",
            "xhigh"
        ]
    }
}

{
    "id": "thinkingmachines/inkling-small",
    "object": "model",
    "created": 1785832741,
    "owned_by": "thinkingmachines",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Inkling Small",
    "description": "Yüksek hacimli reasoning işleri için Inkling'in üçte bir fiyatlı 276B açık ağırlıklı MoE modeli.",
    "context_length": 262144,
    "architecture": {
        "modality": "text+image+audio->text",
        "input_modalities": [
            "text",
            "image",
            "audio"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000058",
        "completion": "0.00000144",
        "input_cache_read": "0.000000116"
    },
    "top_provider": {
        "context_length": 262144,
        "max_completion_tokens": 262144,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
            "none",
            "minimal",
            "low",
            "medium",
            "high",
            "xhigh"
        ]
    }
}

{
    "id": "mimo/mimo-v2.6-pro",
    "object": "model",
    "created": 1790053531,
    "owned_by": "mimo",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "MiMo V2.6 Pro",
    "description": "Uzun bağlamlı ajan ve kodlama işleri için MiMo'nun en güçlü modeli.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text+image+audio+video->text",
        "input_modalities": [
            "text",
            "image",
            "audio",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000435",
        "completion": "0.00000087",
        "input_cache_read": "0.0000000036"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 131072,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "recraft/recraft-v4.1",
    "object": "model",
    "created": 1790235044,
    "owned_by": "recraft",
    "supported_operations": [
        "IMAGES_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/images/generations"
    ],
    "name": "Recraft V4.1",
    "description": "Fotogerçekçi sahneler ve illüstrasyon için Recraft'ın varsayılan V4.1 raster modeli.",
    "context_length": 10000,
    "architecture": {
        "modality": "text+image->image",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "image"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "image_output": "0.035"
    },
    "top_provider": {
        "context_length": 10000,
        "max_completion_tokens": 10000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "mimo/mimo-v2.6-flash",
    "object": "model",
    "created": 1790053531,
    "owned_by": "mimo",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "MiMo V2.6 Flash",
    "description": "Yüksek hacimli metin, görsel, ses ve video işleri için uygun fiyatlı MiMo 2.6.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text+image+audio+video->text",
        "input_modalities": [
            "text",
            "image",
            "audio",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000014",
        "completion": "0.00000028",
        "input_cache_read": "0.0000000028"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 131072,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "recraft/recraft-v4.1-flash",
    "object": "model",
    "created": 1790235044,
    "owned_by": "recraft",
    "supported_operations": [
        "IMAGES_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/images/generations"
    ],
    "name": "Recraft V4.1 Flash",
    "description": "Yüksek hacimli üretim ve hızlı deneme için Recraft V4.1 Flash.",
    "context_length": 10000,
    "architecture": {
        "modality": "text+image->image",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "image"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "image_output": "0.007"
    },
    "top_provider": {
        "context_length": 10000,
        "max_completion_tokens": 10000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "recraft/recraft-v4-styles",
    "object": "model",
    "created": 1790235045,
    "owned_by": "recraft",
    "supported_operations": [
        "IMAGES_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/images/generations"
    ],
    "name": "Recraft V4 Styles",
    "description": "Referans görsellerle tanımlanan tek bir stilde tutarlı görsel setler için Recraft V4 Styles.",
    "context_length": 10000,
    "architecture": {
        "modality": "text+image->image",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "image"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "image_output": "0.035"
    },
    "top_provider": {
        "context_length": 10000,
        "max_completion_tokens": 10000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "krea/krea-2-medium",
    "object": "model",
    "created": 1784609358,
    "owned_by": "krea",
    "supported_operations": [
        "IMAGES_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/images/generations"
    ],
    "name": "Krea 2 Medium",
    "description": "Hizli ve uygun maliyetli metinden gorsel uretimi icin Krea 2 Medium.",
    "context_length": 10000,
    "architecture": {
        "modality": "text+image->image",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "image"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "image_output": "0.03"
    },
    "top_provider": {
        "context_length": 10000,
        "max_completion_tokens": 10000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "krea/krea-2-large",
    "object": "model",
    "created": 1784609358,
    "owned_by": "krea",
    "supported_operations": [
        "IMAGES_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/images/generations"
    ],
    "name": "Krea 2 Large",
    "description": "Fotograf gercekciligi ve en esnek ciktilar icin Krea 2 Large.",
    "context_length": 10000,
    "architecture": {
        "modality": "text+image->image",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "image"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "image_output": "0.06"
    },
    "top_provider": {
        "context_length": 10000,
        "max_completion_tokens": 10000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "sakana/fugu-ultra",
    "object": "model",
    "created": 1782279851,
    "owned_by": "sakana",
    "supported_operations": [
        "CHAT_COMPLETIONS",
        "RESPONSES"
    ],
    "supported_endpoints": [
        "/v1/chat/completions",
        "/v1/responses"
    ],
    "name": "Fugu Ultra",
    "description": "Sakana AI'nin zor reasoning, kodlama ve arastirma isleri icin multi-agent modeli.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000005",
        "completion": "0.00003",
        "input_cache_read": "0.0000005"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 1000000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": [
            "high",
            "xhigh"
        ]
    }
}

{
    "id": "sakana/fugu-max",
    "object": "model",
    "created": 1789102281,
    "owned_by": "sakana",
    "supported_operations": [
        "CHAT_COMPLETIONS",
        "RESPONSES"
    ],
    "supported_endpoints": [
        "/v1/chat/completions",
        "/v1/responses"
    ],
    "name": "Fugu Max",
    "description": "Kodlama, arastirma ve analiz isleri icin Sakana AI'nin sabit fiyatli, genis acik agirlikli havuzlu multi-agent modeli.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000002",
        "completion": "0.000006",
        "input_cache_read": "0.00000025"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 1000000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": [
            "high",
            "xhigh"
        ]
    }
}

{
    "id": "publicai/apertus-v1.5-8b",
    "object": "model",
    "created": 1785126963,
    "owned_by": "publicai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Apertus v1.5 8B",
    "description": "Görsel okuma, araç kullanımı ve 262K bağlam sunan hızlı Apertus modeli.",
    "context_length": 262144,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000001",
        "completion": "0.0000002"
    },
    "top_provider": {
        "context_length": 262144,
        "max_completion_tokens": 262144,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "publicai/apertus-v1.5-70b",
    "object": "model",
    "created": 1785126963,
    "owned_by": "publicai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Apertus v1.5 70B",
    "description": "Görsel okuma, araç kullanımı ve 262K bağlam sunan büyük Apertus modeli.",
    "context_length": 262144,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000082",
        "completion": "0.00000292"
    },
    "top_provider": {
        "context_length": 262144,
        "max_completion_tokens": 262144,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "minimax/minimax-m3.1-flash",
    "object": "model",
    "created": 1792430447,
    "owned_by": "minimax",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "MiniMax M3.1 Flash",
    "description": "Kodlama ve ajan iş akışları için MiniMax M3.1 Flash: 1M bağlam, görsel ve video girdisi, ayarlanabilir düşünme derinliği.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text+image+video->text",
        "input_modalities": [
            "text",
            "image",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000015",
        "completion": "0.0000006",
        "input_cache_read": "0.000000015"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 524288,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": [
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ]
    }
}

{
    "id": "minimax/minimax-m3",
    "object": "model",
    "created": 1780410522,
    "owned_by": "minimax",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "MiniMax M3",
    "description": "Kod, ajan akislari ve 1M baglamli multimodal isler icin MiniMax frontier modeli.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text+image+video->text",
        "input_modalities": [
            "text",
            "image",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000003",
        "completion": "0.0000012",
        "input_cache_read": "0.00000006"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 524288,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "minimax/minimax-m2.7",
    "object": "model",
    "created": 1778959180,
    "owned_by": "minimax",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "MiniMax M2.7",
    "description": "Kod, ofis isleri ve uzun baglamli ajan akislari icin MiniMax M2 modeli.",
    "context_length": 204800,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000003",
        "completion": "0.0000012",
        "input_cache_read": "0.00000006",
        "input_cache_write": "0.000000375"
    },
    "top_provider": {
        "context_length": 204800,
        "max_completion_tokens": 196608,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "meta/muse-spark-1.3",
    "object": "model",
    "created": 1788449283,
    "owned_by": "meta",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Muse Spark 1.3",
    "description": "Uzun soluklu kodlama ve cok adimli ajan isleri icin ayarlanmis, 1M token baglamli guncel Muse Spark checkpoint'i; 1.2 ile ayni fiyattadir.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text+image+file+video->text",
        "input_modalities": [
            "text",
            "image",
            "file",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000125",
        "completion": "0.00000425",
        "input_cache_read": "0.00000015"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 1048576,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
            "minimal",
            "low",
            "medium",
            "high",
            "xhigh"
        ]
    }
}

{
    "id": "meta/muse-glimmer-30b",
    "object": "model",
    "created": 1786423695,
    "owned_by": "meta",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Muse Glimmer 30B",
    "description": "Uzun soluklu ajan akislari icin ayarlanmis, 131K baglamli acik agirlikli reasoning modeli; gorsel ve video okur.",
    "context_length": 131072,
    "architecture": {
        "modality": "text+image+video->text",
        "input_modalities": [
            "text",
            "image",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000035",
        "completion": "0.0000015",
        "input_cache_read": "0.00000004"
    },
    "top_provider": {
        "context_length": 131072,
        "max_completion_tokens": 131072,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
            "none",
            "minimal",
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ]
    }
}

{
    "id": "meta/muse-image-1.0",
    "object": "model",
    "created": 1788757829,
    "owned_by": "meta",
    "supported_operations": [
        "IMAGES_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/images/generations"
    ],
    "name": "Muse Image",
    "description": "Metinden gorsel uretimi icin kullanilan, render etmeden once guncel referanslara bakabilen model.",
    "context_length": 0,
    "architecture": {
        "modality": "text+image->image",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "image"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "image_output": "0.01"
    },
    "top_provider": {
        "context_length": 0,
        "max_completion_tokens": 0,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "nvidia/nemotron-3-ultra-550b-a55b",
    "object": "model",
    "created": 1783242802,
    "owned_by": "nvidia",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Nemotron 3 Ultra 550B A55B",
    "description": "Zor reasoning ve ajan görevleri için günlük kotayla ücretsiz sunulan en büyük Nemotron modeli.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0",
        "completion": "0"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 1000000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "moonshot/kimi-k3.1-pro",
    "object": "model",
    "created": 1792826297,
    "owned_by": "moonshot",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Kimi K3.1 Pro",
    "description": "Uzun soluklu kodlama ve ajan işleri için 1M bağlamlı Kimi amiral gemisi; low, high ve max düşünme seviyeleri.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text+image+video->text",
        "input_modalities": [
            "text",
            "image",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000002",
        "completion": "0.00001",
        "input_cache_read": "0.0000002"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 1048576,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": [
            "low",
            "high",
            "max"
        ]
    }
}

{
    "id": "moonshot/kimi-k3",
    "object": "model",
    "created": 1784286560,
    "owned_by": "moonshot",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Kimi K3",
    "description": "Uzun bağlamlı analiz ve görsel anlama için önceki nesil 1M bağlamlı Kimi amiral gemisi; düşünme kapatılabilir.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000003",
        "completion": "0.000015",
        "input_cache_read": "0.0000003"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 1048576,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "response_format",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "moonshot/kimi-k2.7-code",
    "object": "model",
    "created": 1781364217,
    "owned_by": "moonshot",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Kimi K2.7 Code",
    "description": "Kod ajanları, uzun bağlam ve araçlı teknik işler için Kimi K2 ailesinin kod modeli.",
    "context_length": 262144,
    "architecture": {
        "modality": "text+image+video->text",
        "input_modalities": [
            "text",
            "image",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000095",
        "completion": "0.000004",
        "input_cache_read": "0.00000019",
        "web_search": "0.005"
    },
    "top_provider": {
        "context_length": 262144,
        "max_completion_tokens": 262144,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "temperature",
        "tool_choice",
        "tools",
        "top_p",
        "web_search_options"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "stepfun/step-5-preview",
    "object": "model",
    "created": 1791551635,
    "owned_by": "stepfun",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Step 5 Preview",
    "description": "Ajan isleri, yazilim gelistirme ve uzun belge analizi icin 1M baglamli, gorsel ve video girdili StepFun modeli.",
    "context_length": 1024000,
    "architecture": {
        "modality": "text+image+video->text",
        "input_modalities": [
            "text",
            "image",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000001",
        "completion": "0.0000027",
        "input_cache_read": "0.0000001"
    },
    "top_provider": {
        "context_length": 1024000,
        "max_completion_tokens": 1024000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": [
            "low",
            "medium",
            "high"
        ]
    }
}

{
    "id": "moonshot/kimi-k2.6",
    "object": "model",
    "created": 1776961807,
    "owned_by": "moonshot",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Kimi K2.6",
    "description": "Uzun bağlamlı araştırma ve araçlı multimodal işler için Kimi K2 ailesinin genel amaçlı modeli.",
    "context_length": 256000,
    "architecture": {
        "modality": "text+image+file+video->text",
        "input_modalities": [
            "text",
            "image",
            "file",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000095",
        "completion": "0.000004",
        "input_cache_read": "0.00000016",
        "web_search": "0.005"
    },
    "top_provider": {
        "context_length": 256000,
        "max_completion_tokens": 256000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "response_format",
        "temperature",
        "tool_choice",
        "tools",
        "top_p",
        "web_search_options"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "stepfun/step-3.7-flash",
    "object": "model",
    "created": 1780079750,
    "owned_by": "stepfun",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Step 3.7 Flash",
    "description": "Gorsel ve video girdili agent, kod ve reasoning isleri icin StepFun modeli.",
    "context_length": 256000,
    "architecture": {
        "modality": "text+image+video->text",
        "input_modalities": [
            "text",
            "image",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000002",
        "completion": "0.00000115",
        "input_cache_read": "0.00000004"
    },
    "top_provider": {
        "context_length": 256000,
        "max_completion_tokens": 256000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": [
            "low",
            "medium",
            "high"
        ]
    }
}

{
    "id": "poolside/laguna-xs-2.1",
    "object": "model",
    "created": 1784741890,
    "owned_by": "poolside",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Laguna XS 2.1",
    "description": "Hızlı ajan kodlama için Poolside'ın hafif modeli.",
    "context_length": 262144,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0",
        "completion": "0",
        "input_cache_read": "0"
    },
    "top_provider": {
        "context_length": 262144,
        "max_completion_tokens": 262144,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "aion-labs/aion-3.5",
    "object": "model",
    "created": 1790188215,
    "owned_by": "aion-labs",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "AionLabs: Aion 3.5",
    "description": "Uzun kurgu, roleplay ve karakter odaklı diyaloglar için 256K bağlamlı AionLabs modeli.",
    "context_length": 262144,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000003",
        "completion": "0.000006",
        "input_cache_read": "0.00000075"
    },
    "top_provider": {
        "context_length": 262144,
        "max_completion_tokens": 262144,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": [
            "low",
            "high",
            "max"
        ]
    }
}

{
    "id": "aion-labs/aion-3.5-mini",
    "object": "model",
    "created": 1790188215,
    "owned_by": "aion-labs",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "AionLabs: Aion 3.5 Mini",
    "description": "Yüksek hacimli roleplay ve kurgu akışları için 256K bağlamlı, ekonomik Aion 3.5 modeli.",
    "context_length": 262144,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000007",
        "completion": "0.0000014",
        "input_cache_read": "0.00000018"
    },
    "top_provider": {
        "context_length": 262144,
        "max_completion_tokens": 262144,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": [
            "low",
            "high",
            "max"
        ]
    }
}

{
    "id": "xai/grok-4.7",
    "object": "model",
    "created": 1790014569,
    "owned_by": "xai",
    "supported_operations": [
        "RESPONSES"
    ],
    "supported_endpoints": [
        "/v1/responses"
    ],
    "name": "Grok 4.7",
    "description": "Kod, ajanlar ve bilgi işleri için xAI'nin en yetenekli Grok modeli.",
    "context_length": 500000,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000002",
        "completion": "0.000006",
        "input_cache_read": "0.0000005"
    },
    "top_provider": {
        "context_length": 500000,
        "max_completion_tokens": 500000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
            "low",
            "medium",
            "high",
            "xhigh"
        ]
    }
}

{
    "id": "xai/grok-4.6",
    "object": "model",
    "created": 1786561208,
    "owned_by": "xai",
    "supported_operations": [
        "RESPONSES"
    ],
    "supported_endpoints": [
        "/v1/responses"
    ],
    "name": "Grok 4.6",
    "description": "Kod, ajanlar ve bilgi işleri için önceki nesil Grok modeli.",
    "context_length": 500000,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000002",
        "completion": "0.000006",
        "input_cache_read": "0.0000005"
    },
    "top_provider": {
        "context_length": 500000,
        "max_completion_tokens": 500000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
            "low",
            "medium",
            "high",
            "xhigh"
        ]
    }
}

{
    "id": "xai/grok-4.5",
    "object": "model",
    "created": 1783585136,
    "owned_by": "xai",
    "supported_operations": [
        "RESPONSES"
    ],
    "supported_endpoints": [
        "/v1/responses"
    ],
    "name": "Grok 4.5",
    "description": "Kod, ajanlar ve bilgi işleri için önceki nesil Grok modeli.",
    "context_length": 500000,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000002",
        "completion": "0.000006",
        "input_cache_read": "0.0000003"
    },
    "top_provider": {
        "context_length": 500000,
        "max_completion_tokens": 500000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
            "low",
            "medium",
            "high"
        ]
    }
}

{
    "id": "xai/grok-4.3",
    "object": "model",
    "created": 1778005973,
    "owned_by": "xai",
    "supported_operations": [
        "RESPONSES"
    ],
    "supported_endpoints": [
        "/v1/responses"
    ],
    "name": "Grok 4.3",
    "description": "Uzun bağlamlı analiz ve kod için güçlü Grok modeli.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000125",
        "completion": "0.0000025"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 1000000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "xai/grok-imagine-video-1.5-lite",
    "object": "model",
    "created": 1791433548,
    "owned_by": "xai",
    "supported_operations": [
        "VIDEO_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/video/generations"
    ],
    "name": "Grok Imagine Video 1.5 Lite",
    "description": "Metinden ve görselden sesli video için düşük maliyetli Grok Imagine modeli.",
    "context_length": 0,
    "architecture": {
        "modality": "text+image+audio+video->video",
        "input_modalities": [
            "text",
            "image",
            "audio",
            "video"
        ],
        "output_modalities": [
            "video"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "image": "0.01"
    },
    "top_provider": {
        "context_length": 0,
        "max_completion_tokens": 0,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "xai/grok-imagine-video-1.5",
    "object": "model",
    "created": 1784569225,
    "owned_by": "xai",
    "supported_operations": [
        "VIDEO_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/video/generations"
    ],
    "name": "Grok Imagine Video 1.5",
    "description": "Sesli, metinden ve görselden videoya üretim için Grok Imagine 1.5 modeli.",
    "context_length": 0,
    "architecture": {
        "modality": "text+image+audio+video->video",
        "input_modalities": [
            "text",
            "image",
            "audio",
            "video"
        ],
        "output_modalities": [
            "video"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "image": "0.01"
    },
    "top_provider": {
        "context_length": 0,
        "max_completion_tokens": 0,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "voyageai/voyage-4-large",
    "object": "model",
    "created": 1785304534,
    "owned_by": "voyageai",
    "supported_operations": [
        "EMBEDDINGS"
    ],
    "supported_endpoints": [
        "/v1/embeddings"
    ],
    "name": "Voyage 4 Large",
    "description": "Voyage 4 ailesinin en yüksek doğruluklu genel amaçlı embedding modeli.",
    "context_length": 32000,
    "architecture": {
        "modality": "text->embedding",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "embedding"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000012"
    },
    "top_provider": {
        "context_length": 32000,
        "max_completion_tokens": 32000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "voyageai/voyage-4",
    "object": "model",
    "created": 1785304534,
    "owned_by": "voyageai",
    "supported_operations": [
        "EMBEDDINGS"
    ],
    "supported_endpoints": [
        "/v1/embeddings"
    ],
    "name": "Voyage 4",
    "description": "Doğruluk ile maliyet arasında dengeli genel amaçlı embedding modeli.",
    "context_length": 32000,
    "architecture": {
        "modality": "text->embedding",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "embedding"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000006"
    },
    "top_provider": {
        "context_length": 32000,
        "max_completion_tokens": 32000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "voyageai/voyage-code-4",
    "object": "model",
    "created": 1786947977,
    "owned_by": "voyageai",
    "supported_operations": [
        "EMBEDDINGS"
    ],
    "supported_endpoints": [
        "/v1/embeddings"
    ],
    "name": "Voyage Code 4",
    "description": "Kodlama ajanları için eğitilmiş yeni nesil kod embedding modeli.",
    "context_length": 32000,
    "architecture": {
        "modality": "text->embedding",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "embedding"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000012"
    },
    "top_provider": {
        "context_length": 32000,
        "max_completion_tokens": 32000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "voyageai/voyage-code-3",
    "object": "model",
    "created": 1785304534,
    "owned_by": "voyageai",
    "supported_operations": [
        "EMBEDDINGS"
    ],
    "supported_endpoints": [
        "/v1/embeddings"
    ],
    "name": "Voyage Code 3",
    "description": "Kod arama ve depo indeksleme için özelleşmiş embedding modeli.",
    "context_length": 32000,
    "architecture": {
        "modality": "text->embedding",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "embedding"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000018"
    },
    "top_provider": {
        "context_length": 32000,
        "max_completion_tokens": 32000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "voyageai/voyage-context-4",
    "object": "model",
    "created": 1785304535,
    "owned_by": "voyageai",
    "supported_operations": [
        "EMBEDDINGS"
    ],
    "supported_endpoints": [
        "/v1/embeddings"
    ],
    "name": "Voyage Context 4",
    "description": "Parçaları ait oldukları dokümanın bağlamıyla birlikte vektörleştirir.",
    "context_length": 32000,
    "architecture": {
        "modality": "text->embedding",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "embedding"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000018"
    },
    "top_provider": {
        "context_length": 32000,
        "max_completion_tokens": 32000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "voyageai/voyage-multimodal-3.5",
    "object": "model",
    "created": 1785304535,
    "owned_by": "voyageai",
    "supported_operations": [
        "EMBEDDINGS"
    ],
    "supported_endpoints": [
        "/v1/embeddings"
    ],
    "name": "Voyage Multimodal 3.5",
    "description": "Metin ve görseli tek bir vektör uzayında birleştiren embedding modeli.",
    "context_length": 32000,
    "architecture": {
        "modality": "text+image->embedding",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "embedding"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000012"
    },
    "top_provider": {
        "context_length": 32000,
        "max_completion_tokens": 32000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "voyageai/rerank-3",
    "object": "model",
    "created": 1790832930,
    "owned_by": "voyageai",
    "supported_operations": [
        "RERANK"
    ],
    "supported_endpoints": [
        "/v1/rerank"
    ],
    "name": "Voyage Rerank 3",
    "description": "Arama ve RAG sonuçlarını en yüksek doğrulukla yeniden sıralamak için Voyage reranker'ı.",
    "context_length": 32000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000005"
    },
    "top_provider": {
        "context_length": 32000,
        "max_completion_tokens": 32000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "voyageai/rerank-2.5",
    "object": "model",
    "created": 1785304535,
    "owned_by": "voyageai",
    "supported_operations": [
        "RERANK"
    ],
    "supported_endpoints": [
        "/v1/rerank"
    ],
    "name": "Voyage Rerank 2.5",
    "description": "Retrieval sonuçlarını alaka düzeyine göre yeniden sıralayan model.",
    "context_length": 32768,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000005"
    },
    "top_provider": {
        "context_length": 32768,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "upstage/solar-pro4",
    "object": "model",
    "created": 1786438651,
    "owned_by": "upstage",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Solar Pro 4",
    "description": "Ajan islerine ayarlanmis amiral gemisi; 524K baglam, 128K cikti, yedi kademeli ayarlanabilir dusunme ve arac cagrisi.",
    "context_length": 524288,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000015",
        "completion": "0.0000006",
        "input_cache_read": "0.00000003"
    },
    "top_provider": {
        "context_length": 524288,
        "max_completion_tokens": 131072,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": [
            "none",
            "minimal",
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ]
    }
}

{
    "id": "upstage/solar-mini4",
    "object": "model",
    "created": 1790062100,
    "owned_by": "upstage",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Solar Mini 4",
    "description": "Yuksek hacimli ajan isleri icin kompakt Solar; 524K baglam, yedi kademeli dusunme, arac cagrisi ve yapilandirilmis cikti.",
    "context_length": 524288,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000001",
        "completion": "0.0000004",
        "input_cache_read": "0.00000001"
    },
    "top_provider": {
        "context_length": 524288,
        "max_completion_tokens": 524288,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": [
            "none",
            "minimal",
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ]
    }
}

{
    "id": "gemma/gemma-4-26b-a4b-it",
    "object": "model",
    "created": 1787078890,
    "owned_by": "gemma",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Gemma 4 26B A4B",
    "description": "Google'in acik agirlikli Gemma 4 MoE modeli: 131K baglam, yerel arac cagrisi, acilabilir reasoning ve JSON Schema cikti.",
    "context_length": 131072,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000042",
        "completion": "0.00000022"
    },
    "top_provider": {
        "context_length": 131072,
        "max_completion_tokens": 131072,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": []
    }
}

{
    "id": "gemma/gemma-4-31b-it",
    "object": "model",
    "created": 1787212498,
    "owned_by": "gemma",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Gemma 4 31B",
    "description": "Buyuk baglam penceresi isteyen sohbet, kodlama ve arac kullanan asistan akislari icin 262K baglamli Gemma 4 yogun (dense) model.",
    "context_length": 262144,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000014",
        "completion": "0.0000004"
    },
    "top_provider": {
        "context_length": 262144,
        "max_completion_tokens": 262144,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": []
    }
}

{
    "id": "inception/mercury-3",
    "object": "model",
    "created": 1792438897,
    "owned_by": "inception",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Mercury 3",
    "description": "Ajanlar ve düşük gecikmeli sohbet için difüzyon tabanlı model; 1M bağlam, araç çağrısı, yapısal çıktı, prompt cache.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000001",
        "completion": "0.00000035",
        "input_cache_read": "0.00000001"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 131072,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
            "minimal",
            "low",
            "medium",
            "high"
        ]
    }
}

{
    "id": "llmtr/leyla-english",
    "object": "model",
    "created": 1790679228,
    "owned_by": "llmtr",
    "supported_operations": [
        "SYSTEM_ONE"
    ],
    "supported_endpoints": [
        "/v1/systemone"
    ],
    "name": "Leyla English",
    "description": "Leyla'nın yalnızca İngilizce metin için daha büyük modelli, Türkiye'de barındırılan System One sürümü.",
    "context_length": 512,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000003",
        "completion": "0"
    },
    "top_provider": {
        "context_length": 512,
        "max_completion_tokens": 512,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "llmtr/leyla-typed-decisions",
    "object": "model",
    "created": 1790679228,
    "owned_by": "llmtr",
    "supported_operations": [
        "SYSTEM_ONE"
    ],
    "supported_endpoints": [
        "/v1/systemone"
    ],
    "name": "Leyla Typed Decisions",
    "description": "Fatura, güvenlik olayı, müşteri hizmetleri ve agent trace kararları için İngilizce, Türkiye'de barındırılan System One sürümü.",
    "context_length": 1024,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000003",
        "completion": "0"
    },
    "top_provider": {
        "context_length": 1024,
        "max_completion_tokens": 1024,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "openai/gpt-5.4-nano",
    "object": "model",
    "created": 1776880298,
    "owned_by": "openai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GPT-5.4 nano",
    "description": "Mevcut GPT-5.4 nano entegrasyonları için; 1 Nisan 2027'ye kadar GPT-6 Luna'ya geçin.",
    "context_length": 128000,
    "architecture": {
        "modality": "text+image+file+audio->text",
        "input_modalities": [
            "text",
            "image",
            "file",
            "audio"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000002",
        "completion": "0.00000125"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "openai/gpt-5.1",
    "object": "model",
    "created": 1776880298,
    "owned_by": "openai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GPT-5.1",
    "description": "Mevcut GPT-5.1 entegrasyonları için; 1 Nisan 2027'ye kadar GPT-6 Sol'a geçin.",
    "context_length": 128000,
    "architecture": {
        "modality": "text+image+file+audio->text",
        "input_modalities": [
            "text",
            "image",
            "file",
            "audio"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000125",
        "completion": "0.00001"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "openai/gpt-5",
    "object": "model",
    "created": 1776880298,
    "owned_by": "openai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GPT-5",
    "description": "Genel üretim işleri ve mevcut entegrasyonlar için olgun GPT-5 seçeneği.",
    "context_length": 128000,
    "architecture": {
        "modality": "text+image+file+audio->text",
        "input_modalities": [
            "text",
            "image",
            "file",
            "audio"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000125",
        "completion": "0.00001"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "openai/gpt-5-mini",
    "object": "model",
    "created": 1776880298,
    "owned_by": "openai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GPT-5 mini",
    "description": "Iyi tanimli isler icin hizli ve ekonomik GPT-5 modeli.",
    "context_length": 128000,
    "architecture": {
        "modality": "text+image+file+audio->text",
        "input_modalities": [
            "text",
            "image",
            "file",
            "audio"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000025",
        "completion": "0.000002"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "openai/gpt-5-nano",
    "object": "model",
    "created": 1776880298,
    "owned_by": "openai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GPT-5 nano",
    "description": "Ozetleme ve siniflandirma icin ultra ekonomik GPT-5 modeli.",
    "context_length": 128000,
    "architecture": {
        "modality": "text+image+file+audio->text",
        "input_modalities": [
            "text",
            "image",
            "file",
            "audio"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000005",
        "completion": "0.0000004"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "openai/gpt-4.1",
    "object": "model",
    "created": 1776880298,
    "owned_by": "openai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GPT-4.1",
    "description": "Mevcut GPT-4.1 entegrasyonları için; 14 Ocak 2027'ye kadar GPT-6 Luna'ya geçin.",
    "context_length": 128000,
    "architecture": {
        "modality": "text+image+file+audio->text",
        "input_modalities": [
            "text",
            "image",
            "file",
            "audio"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000002",
        "completion": "0.000008"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "openai/gpt-4.1-mini",
    "object": "model",
    "created": 1776880298,
    "owned_by": "openai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GPT-4.1 mini",
    "description": "Mevcut GPT-4.1 mini entegrasyonları için; 14 Ocak 2027'ye kadar GPT-6 Luna'ya geçin.",
    "context_length": 128000,
    "architecture": {
        "modality": "text+image+file+audio->text",
        "input_modalities": [
            "text",
            "image",
            "file",
            "audio"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000004",
        "completion": "0.0000016"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "openai/gpt-4o",
    "object": "model",
    "created": 1776880299,
    "owned_by": "openai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GPT-4o",
    "description": "Mevcut GPT-4o entegrasyonları için; 14 Ocak 2027'ye kadar GPT-6 Luna'ya geçin.",
    "context_length": 128000,
    "architecture": {
        "modality": "text+image+file+audio->text",
        "input_modalities": [
            "text",
            "image",
            "file",
            "audio"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000025",
        "completion": "0.00001"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 16384,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "openai/gpt-4o-mini",
    "object": "model",
    "created": 1776880299,
    "owned_by": "openai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GPT-4o mini",
    "description": "Mevcut GPT-4o mini entegrasyonları için; 14 Ocak 2027'ye kadar GPT-6 Luna'ya geçin.",
    "context_length": 128000,
    "architecture": {
        "modality": "text+image+file+audio->text",
        "input_modalities": [
            "text",
            "image",
            "file",
            "audio"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000015",
        "completion": "0.0000006"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 16384,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "openai/gpt-5.3-codex",
    "object": "model",
    "created": 1776880299,
    "owned_by": "openai",
    "supported_operations": [
        "RESPONSES"
    ],
    "supported_endpoints": [
        "/v1/responses"
    ],
    "name": "GPT-5.3-Codex",
    "description": "Mevcut GPT-5.3 Codex entegrasyonları için; 1 Nisan 2027'ye kadar GPT-6 Sol'a geçin.",
    "context_length": 400000,
    "architecture": {
        "modality": "text+image+file->text",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000175",
        "completion": "0.000014",
        "input_cache_read": "0.000000175"
    },
    "top_provider": {
        "context_length": 400000,
        "max_completion_tokens": 400000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": [
            "low",
            "medium",
            "high",
            "xhigh"
        ]
    }
}

{
    "id": "openai/gpt-oss-safeguard-20b",
    "object": "model",
    "created": 1787041689,
    "owned_by": "openai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GPT-OSS Safeguard 20B",
    "description": "Icerik siniflandirma ve politika denetimi icin egitilmis, kademeli dusunme seviyeli ucretsiz OpenAI acik agirlikli modeli.",
    "context_length": 131072,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0",
        "completion": "0"
    },
    "top_provider": {
        "context_length": 131072,
        "max_completion_tokens": 65536,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
            "low",
            "medium",
            "high"
        ]
    }
}

{
    "id": "openai/gpt-oss-120b-unmetered",
    "object": "model",
    "created": 1787165425,
    "owned_by": "openai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GPT-OSS 120B",
    "description": "Genel sohbet, kod yardımı, function calling ve JSON çıktı gerektiren akışlar için OpenAI'nin açık ağırlıklı modeli.",
    "context_length": 131072,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000005",
        "completion": "0.00000025"
    },
    "top_provider": {
        "context_length": 131072,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
            "none",
            "high"
        ]
    }
}

{
    "id": "openai/gpt-oss-20b-unmetered",
    "object": "model",
    "created": 1787685060,
    "owned_by": "openai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GPT-OSS 20B",
    "description": "Günlük kotası olmayan, kullandıkça ödenen; hızlı sohbet, function calling ve JSON çıktı gerektiren hafif otomasyon akışları için OpenAI'nin açık ağırlıklı küçük modeli.",
    "context_length": 131072,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000003",
        "completion": "0.00000014"
    },
    "top_provider": {
        "context_length": 131072,
        "max_completion_tokens": 131072,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
            "none",
            "high"
        ]
    }
}

{
    "id": "openai/text-embedding-3-large",
    "object": "model",
    "created": 1787401590,
    "owned_by": "openai",
    "supported_operations": [
        "EMBEDDINGS"
    ],
    "supported_endpoints": [
        "/v1/embeddings"
    ],
    "name": "text-embedding-3-large",
    "description": "Metinleri arama, kümeleme ve öneri sistemleri için en fazla 3072 boyutlu vektöre dönüştüren OpenAI'nin en yetenekli embedding modeli.",
    "context_length": 8192,
    "architecture": {
        "modality": "text->embedding",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "embedding"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000013"
    },
    "top_provider": {
        "context_length": 8192,
        "max_completion_tokens": 8192,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "openai/text-embedding-3-small",
    "object": "model",
    "created": 1787383703,
    "owned_by": "openai",
    "supported_operations": [
        "EMBEDDINGS"
    ],
    "supported_endpoints": [
        "/v1/embeddings"
    ],
    "name": "text-embedding-3-small",
    "description": "Metinleri arama, kümeleme ve öneri sistemleri için en fazla 1536 boyutlu vektöre dönüştüren embedding modeli.",
    "context_length": 8192,
    "architecture": {
        "modality": "text->embedding",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "embedding"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000002"
    },
    "top_provider": {
        "context_length": 8192,
        "max_completion_tokens": 8192,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "openai/text-embedding-ada-002",
    "object": "model",
    "created": 1787230484,
    "owned_by": "openai",
    "supported_operations": [
        "EMBEDDINGS"
    ],
    "supported_endpoints": [
        "/v1/embeddings"
    ],
    "name": "text-embedding-ada-002",
    "description": "Metinleri arama, kümeleme ve öneri sistemleri için 1536 boyutlu vektöre dönüştüren OpenAI embedding modeli.",
    "context_length": 8192,
    "architecture": {
        "modality": "text->embedding",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "embedding"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000001"
    },
    "top_provider": {
        "context_length": 8192,
        "max_completion_tokens": 8192,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "google/gemini-2.5-computer-use-preview-10-2025",
    "object": "model",
    "created": 1776880300,
    "owned_by": "google",
    "supported_operations": [
        "COMPUTER_USE"
    ],
    "supported_endpoints": [],
    "name": "Gemini 2.5 Computer Use Preview",
    "description": "Tarayıcı ve arayüz otomasyonu için Gemini computer-use modeli.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000125",
        "completion": "0.00001"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 1048576,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "google/gemini-3-pro-image",
    "object": "model",
    "created": 1780061473,
    "owned_by": "google",
    "supported_operations": [
        "IMAGES_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/images/generations"
    ],
    "name": "Gemini 3 Pro Image",
    "description": "Karmaşık düzenleme ve yaratıcı kontrol için üst seviye Gemini görüntü modeli.",
    "context_length": 65536,
    "architecture": {
        "modality": "text+image->image",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "image"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000002",
        "completion": "0.000012",
        "image_output": "0.24"
    },
    "top_provider": {
        "context_length": 65536,
        "max_completion_tokens": 65536,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "google/gemini-3.1-flash-image",
    "object": "model",
    "created": 1780061473,
    "owned_by": "google",
    "supported_operations": [
        "IMAGES_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/images/generations"
    ],
    "name": "Gemini 3.1 Flash Image",
    "description": "Daha hızlı ve erişilebilir görsel üretim için Gemini image modeli.",
    "context_length": 131072,
    "architecture": {
        "modality": "text+image+file->image",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "image"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000005",
        "completion": "0.000003",
        "image_output": "0.045"
    },
    "top_provider": {
        "context_length": 131072,
        "max_completion_tokens": 131072,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "google/gemini-3.1-flash-live-preview",
    "object": "model",
    "created": 1776880300,
    "owned_by": "google",
    "supported_operations": [
        "REALTIME_SESSION"
    ],
    "supported_endpoints": [
        "/v1/realtime/sessions"
    ],
    "name": "Gemini 3.1 Flash Live Preview",
    "description": "Gerçek zamanlı sesli konuşma için düşük gecikmeli Gemini Live modeli.",
    "context_length": 128000,
    "architecture": {
        "modality": "text+image+audio+video->text",
        "input_modalities": [
            "text",
            "image",
            "audio",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000075",
        "completion": "0.0000045"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "qwen/qwen-flash",
    "object": "model",
    "created": 1776880300,
    "owned_by": "qwen",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen-Flash",
    "description": "Gunluk sohbet ve yuksek hacimli yardimcilar icin hizli Qwen modeli.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000005",
        "completion": "0.0000004",
        "input_cache_read": "0.00000001"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "temperature",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "qwen/qwen-flash-2025-07-28",
    "object": "model",
    "created": 1776880300,
    "owned_by": "qwen",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen-Flash-2025-07-28",
    "description": "Gunluk sohbet ve yuksek hacimli yardimcilar icin hizli Qwen modeli; tarihli snapshot surumu.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000005",
        "completion": "0.0000004"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "temperature",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "qwen/qwen-mt-flash",
    "object": "model",
    "created": 1776880300,
    "owned_by": "qwen",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen-Mt-Flash",
    "description": "Çok dilli çeviri ve lokalizasyon için Qwen modeli.",
    "context_length": 256000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000016",
        "completion": "0.00000049"
    },
    "top_provider": {
        "context_length": 256000,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "temperature",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "qwen/qwen-mt-plus",
    "object": "model",
    "created": 1776880301,
    "owned_by": "qwen",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen-Mt-Plus",
    "description": "Çok dilli çeviri ve lokalizasyon için Qwen modeli.",
    "context_length": 256000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000246",
        "completion": "0.00000737"
    },
    "top_provider": {
        "context_length": 256000,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p",
        "web_search_options"
    ],
    "per_request_limits": null
}

{
    "id": "qwen/qwen3.6-35b-a3b",
    "object": "model",
    "created": 1787803964,
    "owned_by": "qwen",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen3.6 35B-A3B",
    "description": "Gorsel ve metni birlikte isleyen uzun baglamli isler icin acik agirlikli Qwen3.6 MoE modeli: 262K baglam, yerel arac cagrisi, varsayilan acik reasoning ve JSON Schema cikti.",
    "context_length": 262144,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000007",
        "completion": "0.0000007"
    },
    "top_provider": {
        "context_length": 262144,
        "max_completion_tokens": 262144,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "qwen/qwen-vl-ocr",
    "object": "model",
    "created": 1776880301,
    "owned_by": "qwen",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen-Vl-Ocr",
    "description": "OCR ve belge okuma icin ozel Qwen modeli.",
    "context_length": 256000,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000007",
        "completion": "0.00000016"
    },
    "top_provider": {
        "context_length": 256000,
        "max_completion_tokens": 8192,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "temperature",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "qwen/qwen-vl-ocr-2025-11-20",
    "object": "model",
    "created": 1776880301,
    "owned_by": "qwen",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen-Vl-Ocr-2025-11-20",
    "description": "OCR ve belge okuma icin ozel Qwen modeli; tarihli snapshot surumu.",
    "context_length": 256000,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000007",
        "completion": "0.00000016"
    },
    "top_provider": {
        "context_length": 256000,
        "max_completion_tokens": 8192,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "temperature",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "qwen/qwen3-coder-flash",
    "object": "model",
    "created": 1776880301,
    "owned_by": "qwen",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen3-Coder-Flash",
    "description": "Editor yardimi ve hizli duzeltmeler icin hafif Qwen Coder modeli.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000003",
        "completion": "0.0000015",
        "input_cache_read": "0.00000006"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 65536,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "qwen/qwen3-coder-flash-2025-07-28",
    "object": "model",
    "created": 1776880301,
    "owned_by": "qwen",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen3-Coder-Flash-2025-07-28",
    "description": "Editor yardimi ve hizli duzeltmeler icin hafif Qwen Coder modeli; tarihli snapshot surumu.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000003",
        "completion": "0.0000015"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 65536,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "qwen/qwen3-vl-plus",
    "object": "model",
    "created": 1776880302,
    "owned_by": "qwen",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen3-Vl-Plus",
    "description": "Zor belge sentezi ve gorsel reasoning icin ust seviye Qwen VL modeli.",
    "context_length": 256000,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000002",
        "completion": "0.0000016",
        "input_cache_read": "0.00000004"
    },
    "top_provider": {
        "context_length": 256000,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p",
        "web_search_options"
    ],
    "per_request_limits": null
}

{
    "id": "qwen/qwen3.5-122b-a10b",
    "object": "model",
    "created": 1776880302,
    "owned_by": "qwen",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen3.5-122B-A10b",
    "description": "Genel sohbet, ozetleme ve yardimci akislar icin temel Qwen modeli.",
    "context_length": 256000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000004",
        "completion": "0.0000032"
    },
    "top_provider": {
        "context_length": 256000,
        "max_completion_tokens": 65536,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "temperature",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "qwen/qwen3.5-27b",
    "object": "model",
    "created": 1776880302,
    "owned_by": "qwen",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen3.5-27B",
    "description": "Genel sohbet, ozetleme ve yardimci akislar icin temel Qwen modeli.",
    "context_length": 256000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000003",
        "completion": "0.0000024"
    },
    "top_provider": {
        "context_length": 256000,
        "max_completion_tokens": 65536,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "temperature",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "qwen/qwen3.5-35b-a3b",
    "object": "model",
    "created": 1776880302,
    "owned_by": "qwen",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen3.5-35B-A3b",
    "description": "Genel sohbet, ozetleme ve yardimci akislar icin temel Qwen modeli.",
    "context_length": 256000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000025",
        "completion": "0.000002"
    },
    "top_provider": {
        "context_length": 256000,
        "max_completion_tokens": 65536,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "temperature",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "qwen/qwen3.5-397b-a17b",
    "object": "model",
    "created": 1776880302,
    "owned_by": "qwen",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen3.5-397B-A17b",
    "description": "Genel sohbet, ozetleme ve yardimci akislar icin temel Qwen modeli.",
    "context_length": 256000,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000006",
        "completion": "0.0000036"
    },
    "top_provider": {
        "context_length": 256000,
        "max_completion_tokens": 65536,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "qwen/qwen3.5-flash",
    "object": "model",
    "created": 1776880302,
    "owned_by": "qwen",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen3.5-Flash",
    "description": "Gunluk sohbet ve yuksek hacimli yardimcilar icin hizli Qwen modeli.",
    "context_length": 256000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000001",
        "completion": "0.0000004"
    },
    "top_provider": {
        "context_length": 256000,
        "max_completion_tokens": 65536,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "temperature",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "qwen/qwen3.5-flash-2026-02-23",
    "object": "model",
    "created": 1776880302,
    "owned_by": "qwen",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen3.5-Flash-2026-02-23",
    "description": "Gunluk sohbet ve yuksek hacimli yardimcilar icin hizli Qwen modeli; tarihli snapshot surumu.",
    "context_length": 256000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000001",
        "completion": "0.0000004"
    },
    "top_provider": {
        "context_length": 256000,
        "max_completion_tokens": 65536,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "temperature",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "qwen/qwen3.5-plus",
    "object": "model",
    "created": 1776880302,
    "owned_by": "qwen",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen3.5-Plus",
    "description": "Uzun baglamli yardimcilar ve aracli urun akislari icin dengeli Qwen modeli.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000004",
        "completion": "0.0000024"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 65536,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p",
        "web_search_options"
    ],
    "per_request_limits": null
}

{
    "id": "qwen/qwen3.5-plus-2026-02-15",
    "object": "model",
    "created": 1776880302,
    "owned_by": "qwen",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen3.5-Plus-2026-02-15",
    "description": "Uzun baglamli yardimcilar ve aracli urun akislari icin dengeli Qwen modeli; tarihli snapshot surumu.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000004",
        "completion": "0.0000024"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 65536,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p",
        "web_search_options"
    ],
    "per_request_limits": null
}

{
    "id": "qwen/qwen3.8-27b-free",
    "object": "model",
    "created": 1790010087,
    "owned_by": "qwen",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen3.8 27B",
    "description": "Araç kullanımı, görsel girdi ve yapılandırılmış çıktı için günlük kotayla ücretsiz Qwen modeli.",
    "context_length": 131042,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0",
        "completion": "0"
    },
    "top_provider": {
        "context_length": 131042,
        "max_completion_tokens": 16384,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "qwen/qwen3-reranker-8b",
    "object": "model",
    "created": 1786903888,
    "owned_by": "qwen",
    "supported_operations": [
        "RERANK"
    ],
    "supported_endpoints": [
        "/v1/rerank"
    ],
    "name": "Qwen3 Reranker 8B",
    "description": "Bir sorguyla aday dokumanlari birlikte okuyup alaka puani ureten yeniden siralama modeli.",
    "context_length": 32768,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000005"
    },
    "top_provider": {
        "context_length": 32768,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "alibaba/qwen-image-2.1-pro",
    "object": "model",
    "created": 1792230270,
    "owned_by": "alibaba",
    "supported_operations": [
        "IMAGES_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/images/generations"
    ],
    "name": "Qwen-Image-2.1-Pro",
    "description": "Metinden gorsel uretimi ve referans gorselle duzenleme icin Qwen-Image 2.1 serisinin yuksek kaliteli modeli.",
    "context_length": 0,
    "architecture": {
        "modality": "text+image->image",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "image"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "image_output": "0.04"
    },
    "top_provider": {
        "context_length": 0,
        "max_completion_tokens": 0,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "alibaba/qwen-image-2.1-turbo",
    "object": "model",
    "created": 1792230270,
    "owned_by": "alibaba",
    "supported_operations": [
        "IMAGES_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/images/generations"
    ],
    "name": "Qwen-Image-2.1-Turbo",
    "description": "Metinden gorsel uretimi ve referans gorselle duzenleme icin Qwen-Image 2.1 serisinin hizli ve dusuk maliyetli modeli.",
    "context_length": 0,
    "architecture": {
        "modality": "text+image->image",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "image"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "image_output": "0.016"
    },
    "top_provider": {
        "context_length": 0,
        "max_completion_tokens": 0,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "alibaba/wan3.0-video-prime",
    "object": "model",
    "created": 1787637006,
    "owned_by": "alibaba",
    "supported_operations": [
        "VIDEO_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/video/generations"
    ],
    "name": "Wan3.0-Video-Prime",
    "description": "Metin ve referans medyadan hizli video uretimi icin Alibaba modeli.",
    "context_length": 0,
    "architecture": {
        "modality": "text+image+audio+video->video",
        "input_modalities": [
            "text",
            "image",
            "audio",
            "video"
        ],
        "output_modalities": [
            "video"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": [],
    "top_provider": {
        "context_length": 0,
        "max_completion_tokens": 0,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "alibaba/happyhorse-1.0-t2v",
    "object": "model",
    "created": 1781883764,
    "owned_by": "alibaba",
    "supported_operations": [
        "VIDEO_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/video/generations"
    ],
    "name": "HappyHorse-1.0-T2V",
    "description": "Metinden kisa video uretimi icin Alibaba modeli.",
    "context_length": 0,
    "architecture": {
        "modality": "text+video->video",
        "input_modalities": [
            "text",
            "video"
        ],
        "output_modalities": [
            "video"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": [],
    "top_provider": {
        "context_length": 0,
        "max_completion_tokens": 0,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "zai/glm-4.7",
    "object": "model",
    "created": 1776880302,
    "owned_by": "zai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-4.7",
    "description": "Kod üretimi, prototipleme ve arayüz işleri için güçlendirilmiş GLM modeli.",
    "context_length": 128000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000006",
        "completion": "0.0000022"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "zai/glm-4.7-flashx",
    "object": "model",
    "created": 1776880302,
    "owned_by": "zai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-4.7-FlashX",
    "description": "Hafif kod yardımı ve hızlı ürün entegrasyonları için GLM-4.7 FlashX.",
    "context_length": 128000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000007",
        "completion": "0.0000004"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": []
    }
}

{
    "id": "zai/glm-4.6",
    "object": "model",
    "created": 1776880302,
    "owned_by": "zai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-4.6",
    "description": "Günlük sohbet, analiz ve yardımcı akışlar için oturmuş GLM modeli.",
    "context_length": 128000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000006",
        "completion": "0.0000022"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": []
    }
}

{
    "id": "zai/glm-4.5",
    "object": "model",
    "created": 1776880302,
    "owned_by": "zai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-4.5",
    "description": "Araç çağrıları ve yazılım ajanları için reasoning odaklı GLM modeli.",
    "context_length": 128000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000006",
        "completion": "0.0000022"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": []
    }
}

{
    "id": "zai/glm-4.5-x",
    "object": "model",
    "created": 1776880303,
    "owned_by": "zai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-4.5-X",
    "description": "Daha yuksek performans ve hiz isteyenler icin GLM-4.5-X.",
    "context_length": 96000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000022",
        "completion": "0.0000089"
    },
    "top_provider": {
        "context_length": 96000,
        "max_completion_tokens": 96000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": []
    }
}

{
    "id": "zai/glm-4.5-air",
    "object": "model",
    "created": 1776880303,
    "owned_by": "zai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-4.5-Air",
    "description": "Kod, reasoning ve araç kullanımı için hafif GLM-4.5 agent modeli.",
    "context_length": 128000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000002",
        "completion": "0.0000011"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 98304,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": []
    }
}

{
    "id": "zai/glm-4.5-airx",
    "object": "model",
    "created": 1776880303,
    "owned_by": "zai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-4.5-AirX",
    "description": "Dengeli hiz ve kalite icin GLM-4.5-AirX.",
    "context_length": 128000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000011",
        "completion": "0.0000045"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 98304,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": []
    }
}

{
    "id": "zai/glm-4-32b-0414-128k",
    "object": "model",
    "created": 1776880303,
    "owned_by": "zai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-4-32B-0414-128K",
    "description": "Basit sohbet ve temel özetleme için en ekonomik GLM modellerinden biri.",
    "context_length": 128000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000001",
        "completion": "0.0000001"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "zai/glm-4.6v",
    "object": "model",
    "created": 1776880303,
    "owned_by": "zai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-4.6V",
    "description": "Gorsel anlama icin dengeli Z.AI vision modeli.",
    "context_length": 128000,
    "architecture": {
        "modality": "text+image+file+video->text",
        "input_modalities": [
            "text",
            "image",
            "file",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000003",
        "completion": "0.0000009"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": []
    }
}

{
    "id": "zai/glm-ocr",
    "object": "model",
    "created": 1776880303,
    "owned_by": "zai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-OCR",
    "description": "Belge ve gorsellerden metin cikarmak icin odakli GLM OCR modeli.",
    "context_length": 32000,
    "architecture": {
        "modality": "text+image+file+video->text",
        "input_modalities": [
            "text",
            "image",
            "file",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000003",
        "completion": "0.00000003"
    },
    "top_provider": {
        "context_length": 32000,
        "max_completion_tokens": 32000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "temperature",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "zai/glm-4.6v-flashx",
    "object": "model",
    "created": 1776880303,
    "owned_by": "zai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-4.6V-FlashX",
    "description": "Gorsel isler icin dusuk maliyetli FlashX secenegi.",
    "context_length": 128000,
    "architecture": {
        "modality": "text+image+file+video->text",
        "input_modalities": [
            "text",
            "image",
            "file",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000004",
        "completion": "0.0000004"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": []
    }
}

{
    "id": "zai/glm-4.5v",
    "object": "model",
    "created": 1776880303,
    "owned_by": "zai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-4.5V",
    "description": "Image, video ve GUI gorevleri icin guclu reasoning odakli vision modeli.",
    "context_length": 128000,
    "architecture": {
        "modality": "text+image+file+video->text",
        "input_modalities": [
            "text",
            "image",
            "file",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000006",
        "completion": "0.0000018"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 16384,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": []
    }
}

{
    "id": "deepseek/deepseek-v4.1-flash-1017",
    "object": "model",
    "created": 1792247259,
    "owned_by": "deepseek",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "DeepSeek V4.1 Flash 1017",
    "description": "Uzun bağlamlı kodlama, ajan ve görsel analiz işleri için 17 Ekim 2026 sürümüne sabit DeepSeek V4.1 Flash; fiyat her saat aynı.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000002",
        "completion": "0.0000006",
        "input_cache_read": "0.000000006"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 1048576,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": [
            "none",
            "high"
        ]
    }
}

{
    "id": "deepseek/deepseek-v4-pro-0813",
    "object": "model",
    "created": 1787037211,
    "owned_by": "deepseek",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "DeepSeek V4 Pro 0813",
    "description": "1M baglam ve 384K'ya kadar cikti sunan fp8 hassasiyetli DeepSeek-V4-Pro surumu.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000132",
        "completion": "0.00000396",
        "input_cache_read": "0.000000132"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 393216,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "mistral/magistral-medium-latest",
    "object": "model",
    "created": 1776880303,
    "owned_by": "mistral",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Magistral Medium 1.2",
    "description": "Alan uzmanlığı gerektiren analizler için en güçlü Magistral modeli.",
    "context_length": 128000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000002",
        "completion": "0.000005"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "perplexity/sonar-deep-research",
    "object": "model",
    "created": 1776880304,
    "owned_by": "perplexity",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Sonar Deep Research",
    "description": "Otonom arastirma ve kapsamli raporlar icin Sonar modeli.",
    "context_length": 128000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000002",
        "completion": "0.000008",
        "internal_reasoning": "0.000003"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "temperature",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "mistral/magistral-small-latest",
    "object": "model",
    "created": 1776880303,
    "owned_by": "mistral",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Magistral Small 1.2",
    "description": "Maliyet kontrollü alan analizleri için hafif Magistral modeli.",
    "context_length": 128000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000005",
        "completion": "0.0000015"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "perplexity/pplx-embed-v1-0.6b",
    "object": "model",
    "created": 1776880304,
    "owned_by": "perplexity",
    "supported_operations": [
        "EMBEDDINGS"
    ],
    "supported_endpoints": [
        "/v1/embeddings"
    ],
    "name": "PPLX Embed v1 0.6B",
    "description": "Bagimsiz metinler icin uygun maliyetli standart embedding modeli.",
    "context_length": 32000,
    "architecture": {
        "modality": "text->embedding",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "embedding"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000004"
    },
    "top_provider": {
        "context_length": 32000,
        "max_completion_tokens": 32000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "perplexity/pplx-embed-v1-4b",
    "object": "model",
    "created": 1776880304,
    "owned_by": "perplexity",
    "supported_operations": [
        "EMBEDDINGS"
    ],
    "supported_endpoints": [
        "/v1/embeddings"
    ],
    "name": "PPLX Embed v1 4B",
    "description": "Daha doğru semantik arama ve RAG için yüksek kaliteli embedding modeli.",
    "context_length": 32000,
    "architecture": {
        "modality": "text->embedding",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "embedding"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000003"
    },
    "top_provider": {
        "context_length": 32000,
        "max_completion_tokens": 32000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "mistral/devstral-small-latest",
    "object": "model",
    "created": 1776880303,
    "owned_by": "mistral",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Devstral Small 2",
    "description": "Kod ajanlari icin hafif ve acik kaynak odakli secenek.",
    "context_length": 128000,
    "architecture": {
        "modality": "text+image+file->text",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000001",
        "completion": "0.0000003"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "perplexity/pplx-embed-context-v1-0.6b",
    "object": "model",
    "created": 1776880304,
    "owned_by": "perplexity",
    "supported_operations": [
        "EMBEDDINGS"
    ],
    "supported_endpoints": [
        "/v1/embeddings"
    ],
    "name": "PPLX Embed Context v1 0.6B",
    "description": "Dokuman chunk'lari icin baglam farkindali embedding modeli.",
    "context_length": 32000,
    "architecture": {
        "modality": "text->embedding",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "embedding"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000008"
    },
    "top_provider": {
        "context_length": 32000,
        "max_completion_tokens": 32000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "mistral/codestral-latest",
    "object": "model",
    "created": 1776880303,
    "owned_by": "mistral",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Codestral",
    "description": "Kod tamamlama ve FIM isleri icin saf kod modeli.",
    "context_length": 128000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000003",
        "completion": "0.0000009"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "perplexity/pplx-embed-context-v1-4b",
    "object": "model",
    "created": 1776880304,
    "owned_by": "perplexity",
    "supported_operations": [
        "EMBEDDINGS"
    ],
    "supported_endpoints": [
        "/v1/embeddings"
    ],
    "name": "PPLX Embed Context v1 4B",
    "description": "Belge tabanli retrieval icin yuksek kaliteli baglamsal embedding.",
    "context_length": 32000,
    "architecture": {
        "modality": "text->embedding",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "embedding"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000005"
    },
    "top_provider": {
        "context_length": 32000,
        "max_completion_tokens": 32000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "perplexity/pplx-decider-v1.1-27b",
    "object": "model",
    "created": 1791438037,
    "owned_by": "perplexity",
    "supported_operations": [
        "SYSTEM_ONE"
    ],
    "supported_endpoints": [
        "/v1/systemone"
    ],
    "name": "PPLX Decider v1.1 27B",
    "description": "Metin ve görsel hakkındaki tiplenmiş sorulara serbest metin yerine olasılıkla yanıt veren System One modeli; yönlendirme, sınıflandırma ve onay kararları için.",
    "context_length": 262144,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000002",
        "completion": "0"
    },
    "top_provider": {
        "context_length": 262144,
        "max_completion_tokens": 262144,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "mistral/pixtral-12b",
    "object": "model",
    "created": 1776880303,
    "owned_by": "mistral",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Pixtral 12B",
    "description": "Gorsel anlama icin daha hafif Pixtral secenegi.",
    "context_length": 128000,
    "architecture": {
        "modality": "text+image+file->text",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000015",
        "completion": "0.00000015"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "perplexity/pplx-decider-v1-27b",
    "object": "model",
    "created": 1791438037,
    "owned_by": "perplexity",
    "supported_operations": [
        "SYSTEM_ONE"
    ],
    "supported_endpoints": [
        "/v1/systemone"
    ],
    "name": "PPLX Decider v1 27B",
    "description": "Perplexity'nin System One karar modelinin ilk sürümü: metin ve görsel hakkındaki tiplenmiş sorulara olasılık döndürür; bu sürüme sabitlenmiş entegrasyonlar için.",
    "context_length": 262144,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000002",
        "completion": "0"
    },
    "top_provider": {
        "context_length": 262144,
        "max_completion_tokens": 262144,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "mistral/ministral-14b-latest",
    "object": "model",
    "created": 1776880303,
    "owned_by": "mistral",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Ministral 3 14B",
    "description": "Kenar veya ozel dagitimlar icin guclu Ministral modeli.",
    "context_length": 128000,
    "architecture": {
        "modality": "text+image+file->text",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000002",
        "completion": "0.0000002"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "mistral/ministral-8b-latest",
    "object": "model",
    "created": 1776880303,
    "owned_by": "mistral",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Ministral 3 8B",
    "description": "Edge yardımcıları ve düşük kaynaklı otomasyonlar için orta boy Ministral modeli.",
    "context_length": 128000,
    "architecture": {
        "modality": "text+image+file->text",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000015",
        "completion": "0.00000015"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "mistral/ministral-3b-latest",
    "object": "model",
    "created": 1776880303,
    "owned_by": "mistral",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Ministral 3 3B",
    "description": "Hafif dagitimlar icin en kucuk Ministral secenegi.",
    "context_length": 128000,
    "architecture": {
        "modality": "text+image+file->text",
        "input_modalities": [
            "text",
            "image",
            "file"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000001",
        "completion": "0.0000001"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 128000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "mistral/voxtral-small-latest",
    "object": "model",
    "created": 1776880303,
    "owned_by": "mistral",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Voxtral Small",
    "description": "Transkripsiyon ve sesli yardımcılar için Mistral'in güçlü ses modeli.",
    "context_length": 32768,
    "architecture": {
        "modality": "text+audio->text",
        "input_modalities": [
            "text",
            "audio"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000001",
        "completion": "0.0000003"
    },
    "top_provider": {
        "context_length": 32768,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "mimo/mimo-v2.6-pro-ultraspeed",
    "object": "model",
    "created": 1790053531,
    "owned_by": "mimo",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "MiMo V2.6 Pro UltraSpeed",
    "description": "Gecikmeye duyarlı işler için MiMo 2.6 Pro'nun hızlı sürümü.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text+image+audio+video->text",
        "input_modalities": [
            "text",
            "image",
            "audio",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000435",
        "completion": "0.0000087",
        "input_cache_read": "0.000000036"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 131072,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "recraft/recraft-v4.1-vector",
    "object": "model",
    "created": 1790235044,
    "owned_by": "recraft",
    "supported_operations": [
        "IMAGES_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/images/generations"
    ],
    "name": "Recraft V4.1 Vector",
    "description": "Düzenlenebilir SVG logo, tipografi ve illüstrasyon için Recraft V4.1 Vector.",
    "context_length": 10000,
    "architecture": {
        "modality": "text+image->image",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "image"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "image_output": "0.08"
    },
    "top_provider": {
        "context_length": 10000,
        "max_completion_tokens": 10000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "recraft/recraft-v4.1-pro",
    "object": "model",
    "created": 1790235044,
    "owned_by": "recraft",
    "supported_operations": [
        "IMAGES_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/images/generations"
    ],
    "name": "Recraft V4.1 Pro",
    "description": "Baskıya hazır 2K raster görseller için Recraft V4.1 Pro.",
    "context_length": 10000,
    "architecture": {
        "modality": "text+image->image",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "image"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "image_output": "0.21"
    },
    "top_provider": {
        "context_length": 10000,
        "max_completion_tokens": 10000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "recraft/recraft-v4.1-pro-vector",
    "object": "model",
    "created": 1790235044,
    "owned_by": "recraft",
    "supported_operations": [
        "IMAGES_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/images/generations"
    ],
    "name": "Recraft V4.1 Pro Vector",
    "description": "Teslim kalitesinde SVG tasarım çıktısı için Recraft V4.1 Pro Vector.",
    "context_length": 10000,
    "architecture": {
        "modality": "text+image->image",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "image"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "image_output": "0.3"
    },
    "top_provider": {
        "context_length": 10000,
        "max_completion_tokens": 10000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "recraft/recraft-v4.1-utility",
    "object": "model",
    "created": 1790235044,
    "owned_by": "recraft",
    "supported_operations": [
        "IMAGES_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/images/generations"
    ],
    "name": "Recraft V4.1 Utility",
    "description": "Mockup ve ürün listeleme fotoğrafları için öngörülebilir Recraft V4.1 Utility.",
    "context_length": 10000,
    "architecture": {
        "modality": "text+image->image",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "image"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "image_output": "0.035"
    },
    "top_provider": {
        "context_length": 10000,
        "max_completion_tokens": 10000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "recraft/recraft-v4.1-utility-vector",
    "object": "model",
    "created": 1790235044,
    "owned_by": "recraft",
    "supported_operations": [
        "IMAGES_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/images/generations"
    ],
    "name": "Recraft V4.1 Utility Vector",
    "description": "Sade ve tutarlı SVG ikon ve grafikler için Recraft V4.1 Utility Vector.",
    "context_length": 10000,
    "architecture": {
        "modality": "text+image->image",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "image"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "image_output": "0.08"
    },
    "top_provider": {
        "context_length": 10000,
        "max_completion_tokens": 10000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "recraft/recraft-v4.1-utility-pro",
    "object": "model",
    "created": 1790235044,
    "owned_by": "recraft",
    "supported_operations": [
        "IMAGES_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/images/generations"
    ],
    "name": "Recraft V4.1 Utility Pro",
    "description": "2K çözünürlükte tutarlı ürün ve mockup görselleri için Recraft V4.1 Utility Pro.",
    "context_length": 10000,
    "architecture": {
        "modality": "text+image->image",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "image"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "image_output": "0.21"
    },
    "top_provider": {
        "context_length": 10000,
        "max_completion_tokens": 10000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "recraft/recraft-v4.1-utility-pro-vector",
    "object": "model",
    "created": 1790235044,
    "owned_by": "recraft",
    "supported_operations": [
        "IMAGES_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/images/generations"
    ],
    "name": "Recraft V4.1 Utility Pro Vector",
    "description": "Detaylı ve öngörülebilir SVG çıktısı için Recraft V4.1 Utility Pro Vector.",
    "context_length": 10000,
    "architecture": {
        "modality": "text+image->image",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "image"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "image_output": "0.3"
    },
    "top_provider": {
        "context_length": 10000,
        "max_completion_tokens": 10000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "recraft/recraft-v4",
    "object": "model",
    "created": 1778321935,
    "owned_by": "recraft",
    "supported_operations": [
        "IMAGES_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/images/generations"
    ],
    "name": "Recraft V4",
    "description": "Marka görselleri ve ürün sahneleri için Recraft V4 raster modeli.",
    "context_length": 10000,
    "architecture": {
        "modality": "text+image->image",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "image"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "image_output": "0.04"
    },
    "top_provider": {
        "context_length": 10000,
        "max_completion_tokens": 10000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "recraft/recraft-v4-vector",
    "object": "model",
    "created": 1778321935,
    "owned_by": "recraft",
    "supported_operations": [
        "IMAGES_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/images/generations"
    ],
    "name": "Recraft V4 Vector",
    "description": "Vector logo, ikon ve illüstrasyon için Recraft V4 Vector.",
    "context_length": 10000,
    "architecture": {
        "modality": "text+image->image",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "image"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "image_output": "0.08"
    },
    "top_provider": {
        "context_length": 10000,
        "max_completion_tokens": 10000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "recraft/recraft-v4-pro",
    "object": "model",
    "created": 1778321935,
    "owned_by": "recraft",
    "supported_operations": [
        "IMAGES_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/images/generations"
    ],
    "name": "Recraft V4 Pro",
    "description": "Premium kampanya kreatifi ve detaylı sahneler için Recraft V4 Pro.",
    "context_length": 10000,
    "architecture": {
        "modality": "text+image->image",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "image"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "image_output": "0.25"
    },
    "top_provider": {
        "context_length": 10000,
        "max_completion_tokens": 10000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "recraft/recraft-v4-pro-vector",
    "object": "model",
    "created": 1778321935,
    "owned_by": "recraft",
    "supported_operations": [
        "IMAGES_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/images/generations"
    ],
    "name": "Recraft V4 Pro Vector",
    "description": "En yüksek kontrollü vector üretim için Recraft V4 Pro Vector.",
    "context_length": 10000,
    "architecture": {
        "modality": "text+image->image",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "image"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "image_output": "0.3"
    },
    "top_provider": {
        "context_length": 10000,
        "max_completion_tokens": 10000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "recraft/recraft-v4-styles-vector",
    "object": "model",
    "created": 1790235045,
    "owned_by": "recraft",
    "supported_operations": [
        "IMAGES_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/images/generations"
    ],
    "name": "Recraft V4 Styles Vector",
    "description": "Referans stile bağlı SVG logo ve illüstrasyon setleri için Recraft V4 Styles Vector.",
    "context_length": 10000,
    "architecture": {
        "modality": "text+image->image",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "image"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "image_output": "0.05"
    },
    "top_provider": {
        "context_length": 10000,
        "max_completion_tokens": 10000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "recraft/recraft-v4-styles-pro",
    "object": "model",
    "created": 1790235045,
    "owned_by": "recraft",
    "supported_operations": [
        "IMAGES_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/images/generations"
    ],
    "name": "Recraft V4 Styles Pro",
    "description": "Referans stile bağlı, baskıya hazır 2K görseller için Recraft V4 Styles Pro.",
    "context_length": 10000,
    "architecture": {
        "modality": "text+image->image",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "image"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "image_output": "0.1"
    },
    "top_provider": {
        "context_length": 10000,
        "max_completion_tokens": 10000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "recraft/recraft-v4-styles-pro-vector",
    "object": "model",
    "created": 1790235045,
    "owned_by": "recraft",
    "supported_operations": [
        "IMAGES_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/images/generations"
    ],
    "name": "Recraft V4 Styles Pro Vector",
    "description": "Referans stile bağlı en detaylı SVG çıktısı için Recraft V4 Styles Pro Vector.",
    "context_length": 10000,
    "architecture": {
        "modality": "text+image->image",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "image"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "image_output": "0.12"
    },
    "top_provider": {
        "context_length": 10000,
        "max_completion_tokens": 10000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "recraft/recraft-v3",
    "object": "model",
    "created": 1778321935,
    "owned_by": "recraft",
    "supported_operations": [
        "IMAGES_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/images/generations"
    ],
    "name": "Recraft V3",
    "description": "Erişilebilir görsel üretim ve olgun davranış için önceki Recraft raster modeli.",
    "context_length": 1000,
    "architecture": {
        "modality": "text+image->image",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "image"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "image_output": "0.04"
    },
    "top_provider": {
        "context_length": 1000,
        "max_completion_tokens": 1000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "recraft/recraft-v3-vector",
    "object": "model",
    "created": 1778321935,
    "owned_by": "recraft",
    "supported_operations": [
        "IMAGES_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/images/generations"
    ],
    "name": "Recraft V3 Vector",
    "description": "Önceki nesil vector üretim için Recraft modeli.",
    "context_length": 1000,
    "architecture": {
        "modality": "text+image->image",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "image"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "image_output": "0.08"
    },
    "top_provider": {
        "context_length": 1000,
        "max_completion_tokens": 1000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "publicai/apertus-v1.5-8b-thinking",
    "object": "model",
    "created": 1785126963,
    "owned_by": "publicai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Apertus v1.5 8B Thinking",
    "description": "Kapatılabilir adım adım düşünme, görsel okuma ve 262K bağlam sunan Apertus modeli.",
    "context_length": 262144,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000001",
        "completion": "0.0000002"
    },
    "top_provider": {
        "context_length": 262144,
        "max_completion_tokens": 262144,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "reasoning",
        "response_format",
        "temperature",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "publicai/apertus-8b-instruct",
    "object": "model",
    "created": 1782831794,
    "owned_by": "publicai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Apertus 8B Instruct",
    "description": "Genel sohbet, ozetleme ve hafif otomasyon icin Apertus 8B modeli.",
    "context_length": 65536,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000001",
        "completion": "0.0000002"
    },
    "top_provider": {
        "context_length": 65536,
        "max_completion_tokens": 65536,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "publicai/apertus-70b-instruct",
    "object": "model",
    "created": 1782831795,
    "owned_by": "publicai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Apertus 70B Instruct",
    "description": "Genel metin uretimi, analiz ve yapilandirilmis cikti icin Apertus 70B.",
    "context_length": 65536,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000082",
        "completion": "0.00000292"
    },
    "top_provider": {
        "context_length": 65536,
        "max_completion_tokens": 65536,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "minimax/minimax-m3.1-flash-free",
    "object": "model",
    "created": 1792601649,
    "owned_by": "minimax",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "MiniMax M3.1 Flash (Ücretsiz)",
    "description": "Kodlama ve ajan iş akışları için MiniMax M3.1 Flash; 2 Kasım 2026 23:59'a (TSİ) kadar ücretsiz, hesap başına günde 5 milyon token.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text+image+video->text",
        "input_modalities": [
            "text",
            "image",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0",
        "completion": "0",
        "input_cache_read": "0"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 524288,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": [
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ]
    }
}

{
    "id": "minimax/minimax-m2.7-highspeed",
    "object": "model",
    "created": 1778959180,
    "owned_by": "minimax",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "MiniMax M2.7 Highspeed",
    "description": "Daha dusuk gecikmeli kod ve ajan isleri icin MiniMax M2.7 varyanti.",
    "context_length": 204800,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000006",
        "completion": "0.0000024",
        "input_cache_read": "0.00000006",
        "input_cache_write": "0.000000375"
    },
    "top_provider": {
        "context_length": 204800,
        "max_completion_tokens": 196608,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "minimax/minimax-m2.5",
    "object": "model",
    "created": 1778959180,
    "owned_by": "minimax",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "MiniMax M2.5",
    "description": "Kod uretimi ve refactor isleri icin dengeli MiniMax M2 modeli.",
    "context_length": 204800,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000003",
        "completion": "0.0000012",
        "input_cache_read": "0.00000003",
        "input_cache_write": "0.000000375"
    },
    "top_provider": {
        "context_length": 204800,
        "max_completion_tokens": 196608,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "minimax/minimax-m2.5-highspeed",
    "object": "model",
    "created": 1778959180,
    "owned_by": "minimax",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "MiniMax M2.5 Highspeed",
    "description": "Hiz oncelikli kod yardimi ve refactor icin MiniMax M2.5 varyanti.",
    "context_length": 204800,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000006",
        "completion": "0.0000024",
        "input_cache_read": "0.00000003",
        "input_cache_write": "0.000000375"
    },
    "top_provider": {
        "context_length": 204800,
        "max_completion_tokens": 196608,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "minimax/minimax-h3",
    "object": "model",
    "created": 1788374131,
    "owned_by": "minimax",
    "supported_operations": [
        "VIDEO_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/video/generations"
    ],
    "name": "MiniMax H3",
    "description": "Metin, ilk/son kare ve referans gorsel girdilerinden 2K video uretimi icin MiniMax modeli.",
    "context_length": 0,
    "architecture": {
        "modality": "text+image+video->video",
        "input_modalities": [
            "text",
            "image",
            "video"
        ],
        "output_modalities": [
            "video"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "image": "0.04"
    },
    "top_provider": {
        "context_length": 0,
        "max_completion_tokens": 0,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "minimax/minimax-h3-max",
    "object": "model",
    "created": 1788374131,
    "owned_by": "minimax",
    "supported_operations": [
        "VIDEO_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/video/generations"
    ],
    "name": "MiniMax H3 Max",
    "description": "Hizli metinden video ve gorselden video uretimi icin MiniMax H3 varyanti.",
    "context_length": 0,
    "architecture": {
        "modality": "text+image+video->video",
        "input_modalities": [
            "text",
            "image",
            "video"
        ],
        "output_modalities": [
            "video"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": [],
    "top_provider": {
        "context_length": 0,
        "max_completion_tokens": 0,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "meta/muse-spark-1.2",
    "object": "model",
    "created": 1785994188,
    "owned_by": "meta",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Muse Spark 1.2",
    "description": "1M token baglamli, kodlama ve ajan akislari icin ayarlanmis reasoning modeli; gorsel, video ve PDF okur.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text+image+file+video->text",
        "input_modalities": [
            "text",
            "image",
            "file",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000125",
        "completion": "0.00000425",
        "input_cache_read": "0.00000015"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 1048576,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
            "minimal",
            "low",
            "medium",
            "high",
            "xhigh"
        ]
    }
}

{
    "id": "meta/muse-spark-1.1",
    "object": "model",
    "created": 1785994188,
    "owned_by": "meta",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Muse Spark 1.1",
    "description": "Muse Spark ailesinin onceki checkpoint'i; 1.2 ile ayni 1M baglam, multimodal girdi ve arac cagrisi, ayni fiyat.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text+image+file+video->text",
        "input_modalities": [
            "text",
            "image",
            "file",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000125",
        "completion": "0.00000425",
        "input_cache_read": "0.00000015"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 1048576,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
            "minimal",
            "low",
            "medium",
            "high",
            "xhigh"
        ]
    }
}

{
    "id": "meta/muse-spark-1.2-contributor",
    "object": "model",
    "created": 1785994188,
    "owned_by": "meta",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Muse Spark 1.2 Contributor",
    "description": "Muse Spark 1.2'nin cok daha ucuz katmani; karsiliginda istem ve yanitlariniz Meta model egitiminde kullanilir.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text+image+file+video->text",
        "input_modalities": [
            "text",
            "image",
            "file",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000001",
        "completion": "0.0000002",
        "input_cache_read": "0.000000002"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 1048576,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
            "minimal",
            "low",
            "medium",
            "high",
            "xhigh"
        ]
    }
}

{
    "id": "meta/muse-spark-1.3-contributor",
    "object": "model",
    "created": 1788449284,
    "owned_by": "meta",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Muse Spark 1.3 Contributor",
    "description": "Prototip ve yuk testi icin cok daha ucuz Muse Spark 1.3 katmani; karsiliginda istem ve yanitlariniz Meta model egitiminde kullanilir.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text+image+file+video->text",
        "input_modalities": [
            "text",
            "image",
            "file",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000001",
        "completion": "0.0000002",
        "input_cache_read": "0.000000002"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 1048576,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
            "minimal",
            "low",
            "medium",
            "high",
            "xhigh"
        ]
    }
}

{
    "id": "meta/llama-3.3-70b-instruct-12k",
    "object": "model",
    "created": 1787068792,
    "owned_by": "meta",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Llama 3.3 70B Instruct (12K)",
    "description": "Genel sohbet, çok dilli işler ve araç kullanımı için 12K bağlamlı Llama modeli.",
    "context_length": 12288,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000135",
        "completion": "0.0000004"
    },
    "top_provider": {
        "context_length": 12288,
        "max_completion_tokens": 12288,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "meta/llama-3.1-8b-instruct-16k",
    "object": "model",
    "created": 1787081032,
    "owned_by": "meta",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Llama 3.1 8B Instruct",
    "description": "Hızlı, hafif ve 16K bağlamlı; genel sohbet ve JSON çıktı için Llama modeli.",
    "context_length": 16384,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000002",
        "completion": "0.00000005"
    },
    "top_provider": {
        "context_length": 16384,
        "max_completion_tokens": 16384,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "response_format",
        "temperature",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "meta/muse-spark-open",
    "object": "model",
    "created": 1792161792,
    "owned_by": "meta",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Muse Spark Open",
    "description": "Meta'nın ajan kodlama ve araç kullanımı için eğittiği, 1M token bağlamlı açık ağırlıklı reasoning modeli; görsel, video ve ses okur.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text+image+audio+video->text",
        "input_modalities": [
            "text",
            "image",
            "audio",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000125",
        "completion": "0.00000425",
        "input_cache_read": "0.00000015"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 1048576,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": [
            "low",
            "medium",
            "high",
            "xhigh"
        ]
    }
}

{
    "id": "nvidia/nemotron-3.5-super-vl-free",
    "object": "model",
    "created": 1792088474,
    "owned_by": "nvidia",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Nemotron 3.5 Super VL (Ücretsiz)",
    "description": "Görsel ve video anlama için günlük kotayla ücretsiz NVIDIA Nemotron 3.5 Super VL: 1M bağlam ve araç çağrısı.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text+image+video->text",
        "input_modalities": [
            "text",
            "image",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0",
        "completion": "0"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 1000000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "nvidia/nemotron-3.5-super-vl",
    "object": "model",
    "created": 1792088474,
    "owned_by": "nvidia",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Nemotron 3.5 Super VL",
    "description": "Görsel ve video anlaması gereken uygulamalar ve ajan akışları için NVIDIA MoE modeli: 262K bağlam, araç çağrısı, JSON Schema çıktı ve kapatılabilir düşünme.",
    "context_length": 262144,
    "architecture": {
        "modality": "text+image+video->text",
        "input_modalities": [
            "text",
            "image",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000015",
        "completion": "0.0000005",
        "input_cache_read": "0.00000002"
    },
    "top_provider": {
        "context_length": 262144,
        "max_completion_tokens": 262144,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "nvidia/nemotron-3-ultra-550b-a55b-262k",
    "object": "model",
    "created": 1787295363,
    "owned_by": "nvidia",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Nemotron 3 Ultra 550B A55B 262K",
    "description": "Uzun baglamli reasoning, arac cagrisi ve ajan akislari icin 262K baglamli, prompt cache indirimli Nemotron Ultra.",
    "context_length": 262144,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000005",
        "completion": "0.0000022",
        "input_cache_read": "0.0000001"
    },
    "top_provider": {
        "context_length": 262144,
        "max_completion_tokens": 262144,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "nvidia/nemotron-3-super-120b-a12b",
    "object": "model",
    "created": 1783242802,
    "owned_by": "nvidia",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Nemotron 3 Super 120B A12B",
    "description": "Uzun bağlam ve araç kullanımı için dengeli, günlük kotayla ücretsiz Nemotron modeli.",
    "context_length": 262144,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0",
        "completion": "0"
    },
    "top_provider": {
        "context_length": 262144,
        "max_completion_tokens": 262144,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "moonshot/kimi-k3.1-pro-highspeed",
    "object": "model",
    "created": 1792826297,
    "owned_by": "moonshot",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Kimi K3.1 Pro Highspeed",
    "description": "Bekleme süresinin önemli olduğu etkileşimli işler için Kimi K3.1 Pro'nun daha hızlı sürümü; aynı 1M bağlam, daha yüksek token fiyatı.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text+image+video->text",
        "input_modalities": [
            "text",
            "image",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000004",
        "completion": "0.00002",
        "input_cache_read": "0.0000002"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 1048576,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": [
            "low",
            "high",
            "max"
        ]
    }
}

{
    "id": "stepfun/step-3.5-flash",
    "object": "model",
    "created": 1780079750,
    "owned_by": "stepfun",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Step 3.5 Flash",
    "description": "Uzun baglamli, metin odakli StepFun chat ve reasoning modeli.",
    "context_length": 256000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000001",
        "completion": "0.0000003",
        "input_cache_read": "0.00000002"
    },
    "top_provider": {
        "context_length": 256000,
        "max_completion_tokens": 256000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": []
    }
}

{
    "id": "stepfun/step-3.5-flash-2603",
    "object": "model",
    "created": 1780079750,
    "owned_by": "stepfun",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Step 3.5 Flash 2603",
    "description": "Metin analizi, kod ve kontrollu reasoning icin Step 3.5 Flash varyanti.",
    "context_length": 256000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000001",
        "completion": "0.0000003",
        "input_cache_read": "0.00000002"
    },
    "top_provider": {
        "context_length": 256000,
        "max_completion_tokens": 256000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": [
            "low",
            "high"
        ]
    }
}

{
    "id": "aion-labs/aion-3.0",
    "object": "model",
    "created": 1783601983,
    "owned_by": "aion-labs",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "AionLabs: Aion 3.0",
    "description": "Uzun kurgu, roleplay ve karakter odakli diyaloglar icin AionLabs modeli.",
    "context_length": 131072,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000003",
        "completion": "0.000006",
        "input_cache_read": "0.00000075"
    },
    "top_provider": {
        "context_length": 131072,
        "max_completion_tokens": 131072,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": []
    }
}

{
    "id": "aion-labs/aion-3.0-mini",
    "object": "model",
    "created": 1783601983,
    "owned_by": "aion-labs",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "AionLabs: Aion 3.0 Mini",
    "description": "Yuksek hacimli roleplay ve kurgu akislari icin ekonomik Aion 3 modeli.",
    "context_length": 131072,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000007",
        "completion": "0.0000014",
        "input_cache_read": "0.00000018"
    },
    "top_provider": {
        "context_length": 131072,
        "max_completion_tokens": 131072,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": []
    }
}

{
    "id": "aion-labs/aion-2.0",
    "object": "model",
    "created": 1783601983,
    "owned_by": "aion-labs",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "AionLabs: Aion 2.0",
    "description": "Kontrollu reasoning ile roleplay ve hikaye uretimi icin Aion modeli.",
    "context_length": 131072,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000008",
        "completion": "0.0000016",
        "input_cache_read": "0.0000002"
    },
    "top_provider": {
        "context_length": 131072,
        "max_completion_tokens": 131072,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
            "none",
            "low",
            "medium",
            "high"
        ]
    }
}

{
    "id": "aion-labs/aion-rp-llama-3.1-8b",
    "object": "model",
    "created": 1783601983,
    "owned_by": "aion-labs",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "AionLabs: Aion-RP 1.0 (8B)",
    "description": "Kisa ve orta uzunlukta roleplay sohbetleri icin Llama 3.1 8B tabanli model.",
    "context_length": 32768,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000008",
        "completion": "0.0000016"
    },
    "top_provider": {
        "context_length": 32768,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "tencent/hy4-preview",
    "object": "model",
    "created": 1787910220,
    "owned_by": "tencent",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Tencent: Hy4 Preview",
    "description": "Kod ajanlari, uzun dokuman analizi ve cok adimli arac akislari icin 262K baglamli onizleme modeli. Varsayilan olarak dusunur.",
    "context_length": 262144,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000834",
        "completion": "0.000002501",
        "input_cache_read": "0.000000042"
    },
    "top_provider": {
        "context_length": 262144,
        "max_completion_tokens": 262144,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
            "none"
        ]
    }
}

{
    "id": "tencent/hy3",
    "object": "model",
    "created": 1783934770,
    "owned_by": "tencent",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Tencent: Hy3",
    "description": "295B MoE (token başına ~21B aktif); kod ajanları, uzun doküman analizi ve araç akışları için. Düşünme varsayılan kapalı.",
    "context_length": 196608,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000014",
        "completion": "0.00000058",
        "input_cache_read": "0.000000035"
    },
    "top_provider": {
        "context_length": 196608,
        "max_completion_tokens": 196608,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": [
            "low",
            "high"
        ]
    }
}

{
    "id": "tencent/hy-mt2-lite",
    "object": "model",
    "created": 1787424878,
    "owned_by": "tencent",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Tencent: Hy-MT2 Lite",
    "description": "Hafif belge ve mesaj çevirisi için 1.8B parametreli model; 33 dil ve 5 lehçe çifti destekler. Yalnızca metin.",
    "context_length": 8192,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000044",
        "completion": "0.000000177"
    },
    "top_provider": {
        "context_length": 8192,
        "max_completion_tokens": 4096,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "temperature",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "tencent/hy-mt2-plus",
    "object": "model",
    "created": 1787424878,
    "owned_by": "tencent",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Tencent: Hy-MT2 Plus",
    "description": "Profesyonel doküman çevirisi için 7B parametreli model; 33 dil ve 5 lehçe çifti destekler. Yalnızca metin.",
    "context_length": 8192,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000074",
        "completion": "0.000000295"
    },
    "top_provider": {
        "context_length": 8192,
        "max_completion_tokens": 4096,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "temperature",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "tencent/hy-mt2-pro",
    "object": "model",
    "created": 1787424878,
    "owned_by": "tencent",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Tencent: Hy-MT2 Pro",
    "description": "Kurumsal ölçekli, karmaşık metin çevirisi için 30B-A3B MoE mimarili amiral model; 33 dil ve 5 lehçe çifti destekler. Yalnızca metin.",
    "context_length": 8192,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000074",
        "completion": "0.000000295"
    },
    "top_provider": {
        "context_length": 8192,
        "max_completion_tokens": 4096,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "temperature",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "xai/grok-4.20-multi-agent",
    "object": "model",
    "created": 1778044235,
    "owned_by": "xai",
    "supported_operations": [
        "RESPONSES"
    ],
    "supported_endpoints": [
        "/v1/responses"
    ],
    "name": "Grok 4.20 Multi-Agent",
    "description": "Araştırma akışları için çok ajanlı Grok modeli.",
    "context_length": 2000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000125",
        "completion": "0.0000025"
    },
    "top_provider": {
        "context_length": 2000000,
        "max_completion_tokens": 2000000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "reasoning",
        "reasoning_effort",
        "temperature",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": [
            "low",
            "medium",
            "high",
            "xhigh"
        ]
    }
}

{
    "id": "xai/grok-4.20-0309-reasoning",
    "object": "model",
    "created": 1778044235,
    "owned_by": "xai",
    "supported_operations": [
        "RESPONSES"
    ],
    "supported_endpoints": [
        "/v1/responses"
    ],
    "name": "Grok 4.20 Reasoning 0309",
    "description": "Derin düşünme gerektiren işler için Grok reasoning modeli.",
    "context_length": 2000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000125",
        "completion": "0.0000025"
    },
    "top_provider": {
        "context_length": 2000000,
        "max_completion_tokens": 2000000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "xai/grok-4.20-0309-non-reasoning",
    "object": "model",
    "created": 1778044235,
    "owned_by": "xai",
    "supported_operations": [
        "RESPONSES"
    ],
    "supported_endpoints": [
        "/v1/responses"
    ],
    "name": "Grok 4.20 Non-Reasoning 0309",
    "description": "Hızlı genel metin işleri için Grok varyantı.",
    "context_length": 2000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000125",
        "completion": "0.0000025"
    },
    "top_provider": {
        "context_length": 2000000,
        "max_completion_tokens": 2000000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "xai/grok-imagine-image",
    "object": "model",
    "created": 1778044235,
    "owned_by": "xai",
    "supported_operations": [
        "IMAGES_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/images/generations",
        "/v1/images/edits"
    ],
    "name": "Grok Imagine Image",
    "description": "Günlük görsel üretim ve düzenleme için Grok Imagine modeli.",
    "context_length": 0,
    "architecture": {
        "modality": "text+image->image",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "image"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "image_output": "0.02"
    },
    "top_provider": {
        "context_length": 0,
        "max_completion_tokens": 0,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "xai/grok-imagine-image-quality",
    "object": "model",
    "created": 1778044235,
    "owned_by": "xai",
    "supported_operations": [
        "IMAGES_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/images/generations",
        "/v1/images/edits"
    ],
    "name": "Grok Imagine Image Quality",
    "description": "Premium görsel üretim ve daha sıkı komut takibi için Grok Imagine modeli.",
    "context_length": 0,
    "architecture": {
        "modality": "text+image->image",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "image"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "image_output": "0.05"
    },
    "top_provider": {
        "context_length": 0,
        "max_completion_tokens": 0,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "xai/grok-imagine-video",
    "object": "model",
    "created": 1778044235,
    "owned_by": "xai",
    "supported_operations": [
        "VIDEO_GENERATIONS"
    ],
    "supported_endpoints": [
        "/v1/video/generations"
    ],
    "name": "Grok Imagine Video",
    "description": "Prompt tabanlı video üretimi için Grok Imagine modeli.",
    "context_length": 0,
    "architecture": {
        "modality": "text+video->video",
        "input_modalities": [
            "text",
            "video"
        ],
        "output_modalities": [
            "video"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": [],
    "top_provider": {
        "context_length": 0,
        "max_completion_tokens": 0,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "xai/grok-voice-tts",
    "object": "model",
    "created": 1778044235,
    "owned_by": "xai",
    "supported_operations": [
        "AUDIO_SPEECH"
    ],
    "supported_endpoints": [
        "/v1/audio/speech"
    ],
    "name": "Grok Voice TTS",
    "description": "Metinden sese dönüşüm için Grok Voice modeli.",
    "context_length": 100000,
    "architecture": {
        "modality": "text+audio->audio",
        "input_modalities": [
            "text",
            "audio"
        ],
        "output_modalities": [
            "audio"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": [],
    "top_provider": {
        "context_length": 100000,
        "max_completion_tokens": 100000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "xai/grok-voice-stt",
    "object": "model",
    "created": 1778044235,
    "owned_by": "xai",
    "supported_operations": [
        "AUDIO_TRANSCRIPTIONS"
    ],
    "supported_endpoints": [
        "/v1/audio/transcriptions"
    ],
    "name": "Grok Voice STT",
    "description": "Ses dosyalarını metne çevirmek için Grok Voice modeli.",
    "context_length": 0,
    "architecture": {
        "modality": "text+audio->text",
        "input_modalities": [
            "text",
            "audio"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": [],
    "top_provider": {
        "context_length": 0,
        "max_completion_tokens": 0,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "perceptron/perceptron-mk1.5",
    "object": "model",
    "created": 1790412722,
    "owned_by": "perceptron",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Perceptron Mk1.5",
    "description": "Görsel, video ve ses anlama; zaman damgası, nesne işaretleme ve araç çağrısı için Perceptron modeli.",
    "context_length": 36864,
    "architecture": {
        "modality": "text+image+audio+video->text",
        "input_modalities": [
            "text",
            "image",
            "audio",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000015",
        "completion": "0.0000015"
    },
    "top_provider": {
        "context_length": 36864,
        "max_completion_tokens": 8192,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": [
            "none",
            "minimal",
            "low",
            "medium",
            "high"
        ]
    }
}

{
    "id": "perceptron/perceptron-mk1",
    "object": "model",
    "created": 1778650499,
    "owned_by": "perceptron",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Perceptron Mk1",
    "description": "Gorsel ve video anlama icin Perceptron vision-language modeli.",
    "context_length": 32768,
    "architecture": {
        "modality": "text+image+video->text",
        "input_modalities": [
            "text",
            "image",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000015",
        "completion": "0.0000015"
    },
    "top_provider": {
        "context_length": 32768,
        "max_completion_tokens": 8192,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "reasoning",
        "temperature",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": []
    }
}

{
    "id": "inclusionai/ling-3.0-flash",
    "object": "model",
    "created": 1787037668,
    "owned_by": "inclusionai",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Ling 3.0 Flash",
    "description": "124B MoE (token basina ~5.1B aktif); varsayilan olarak dusunur, arac cagrisi ve prompt cache destekler, 256K baglam sunar.",
    "context_length": 262144,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000006",
        "completion": "0.00000018",
        "input_cache_read": "0.000000012"
    },
    "top_provider": {
        "context_length": 262144,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
            "none"
        ]
    }
}

{
    "id": "voyageai/voyage-4-lite",
    "object": "model",
    "created": 1785304534,
    "owned_by": "voyageai",
    "supported_operations": [
        "EMBEDDINGS"
    ],
    "supported_endpoints": [
        "/v1/embeddings"
    ],
    "name": "Voyage 4 Lite",
    "description": "Yüksek hacimli indeksleme için en ekonomik Voyage embedding modeli.",
    "context_length": 32000,
    "architecture": {
        "modality": "text->embedding",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "embedding"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000002"
    },
    "top_provider": {
        "context_length": 32000,
        "max_completion_tokens": 32000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "voyageai/voyage-finance-2",
    "object": "model",
    "created": 1785304535,
    "owned_by": "voyageai",
    "supported_operations": [
        "EMBEDDINGS"
    ],
    "supported_endpoints": [
        "/v1/embeddings"
    ],
    "name": "Voyage Finance 2",
    "description": "Finans metinleri için alan özelinde eğitilmiş embedding modeli.",
    "context_length": 32000,
    "architecture": {
        "modality": "text->embedding",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "embedding"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000012"
    },
    "top_provider": {
        "context_length": 32000,
        "max_completion_tokens": 32000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "voyageai/voyage-law-2",
    "object": "model",
    "created": 1785304535,
    "owned_by": "voyageai",
    "supported_operations": [
        "EMBEDDINGS"
    ],
    "supported_endpoints": [
        "/v1/embeddings"
    ],
    "name": "Voyage Law 2",
    "description": "Hukuki metinler için alan özelinde eğitilmiş embedding modeli.",
    "context_length": 16000,
    "architecture": {
        "modality": "text->embedding",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "embedding"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000012"
    },
    "top_provider": {
        "context_length": 16000,
        "max_completion_tokens": 16000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "voyageai/rerank-3-lite",
    "object": "model",
    "created": 1790832930,
    "owned_by": "voyageai",
    "supported_operations": [
        "RERANK"
    ],
    "supported_endpoints": [
        "/v1/rerank"
    ],
    "name": "Voyage Rerank 3 Lite",
    "description": "Gecikmeye duyarlı ve yüksek hacimli işler için hızlı reranker.",
    "context_length": 32000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000002"
    },
    "top_provider": {
        "context_length": 32000,
        "max_completion_tokens": 32000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "voyageai/rerank-2.5-lite",
    "object": "model",
    "created": 1785304535,
    "owned_by": "voyageai",
    "supported_operations": [
        "RERANK"
    ],
    "supported_endpoints": [
        "/v1/rerank"
    ],
    "name": "Voyage Rerank 2.5 Lite",
    "description": "Yüksek hacimli yeniden sıralama için ekonomik reranker.",
    "context_length": 32768,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000002"
    },
    "top_provider": {
        "context_length": 32768,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "upstage/solar-pro3",
    "object": "model",
    "created": 1786438651,
    "owned_by": "upstage",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Solar Pro 3",
    "description": "Mevcut Solar Pro 3 entegrasyonlari icin; 29 Ekim 2026 18:00'e (TSI) kadar Solar Pro 4'e gecin.",
    "context_length": 131072,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000015",
        "completion": "0.0000006",
        "input_cache_read": "0.000000015"
    },
    "top_provider": {
        "context_length": 131072,
        "max_completion_tokens": 131072,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": [
            "none",
            "minimal",
            "low",
            "medium",
            "high"
        ]
    }
}

{
    "id": "upstage/solar-pro2",
    "object": "model",
    "created": 1786438651,
    "owned_by": "upstage",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Solar Pro 2",
    "description": "Mevcut Solar Pro 2 entegrasyonlari icin; 29 Ekim 2026 18:00'e (TSI) kadar Solar Pro 4'e gecin.",
    "context_length": 65536,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000015",
        "completion": "0.0000006",
        "input_cache_read": "0.000000015"
    },
    "top_provider": {
        "context_length": 65536,
        "max_completion_tokens": 65536,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": [
            "minimal",
            "low",
            "medium",
            "high"
        ]
    }
}

{
    "id": "upstage/solar-decide",
    "object": "model",
    "created": 1790657553,
    "owned_by": "upstage",
    "supported_operations": [
        "SYSTEM_ONE"
    ],
    "supported_endpoints": [
        "/v1/systemone"
    ],
    "name": "Solar Decide",
    "description": "Yonlendirme, siniflandirma ve politika kontrolu icin serbest metin yerine tiplenmis karar donduren System One modeli.",
    "context_length": 524288,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000001",
        "completion": "0"
    },
    "top_provider": {
        "context_length": 524288,
        "max_completion_tokens": 524288,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "inception/mercury-2.5-preview",
    "object": "model",
    "created": 1788321965,
    "owned_by": "inception",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Mercury 2.5 Preview",
    "description": "Uzun belge analizi ve düşük gecikmeli sohbet için difüzyon modeli; 260K bağlam, araç çağrısı, yapısal çıktı.",
    "context_length": 260000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000004",
        "completion": "0.00000015",
        "input_cache_read": "0.000000004"
    },
    "top_provider": {
        "context_length": 260000,
        "max_completion_tokens": 65536,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
            "none",
            "minimal",
            "medium"
        ]
    }
}

{
    "id": "inception/mercury-2",
    "object": "model",
    "created": 1788321965,
    "owned_by": "inception",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Mercury 2",
    "description": "Düşük gecikmeli sohbet, araç çağrısı ve yapısal çıktı için difüzyon tabanlı model; 128K bağlam, prompt cache.",
    "context_length": 128000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000025",
        "completion": "0.00000075",
        "input_cache_read": "0.000000025"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 50000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
            "minimal",
            "low",
            "medium",
            "high"
        ]
    }
}

{
    "id": "liquid/d1-ultra",
    "object": "model",
    "created": 1792151323,
    "owned_by": "liquid",
    "supported_operations": [
        "SYSTEM_ONE"
    ],
    "supported_endpoints": [
        "/v1/systemone"
    ],
    "name": "d1-ultra",
    "description": "Yönlendirme, sınıflandırma ve görsel kontrolü için Liquid AI'nin en büyük karar modeli: serbest metin yerine olasılıklı, tiplenmiş karar döndürür.",
    "context_length": 32768,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000042",
        "completion": "0"
    },
    "top_provider": {
        "context_length": 32768,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "liquid/lfm-2.5-24b-a2b",
    "object": "model",
    "created": 1792001783,
    "owned_by": "liquid",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "LFM2.5-24B-A2B",
    "description": "Araç çağıran agent'lar ve çok adımlı görevler için her zaman düşünen 24B MoE dil modeli.",
    "context_length": 128000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000005",
        "completion": "0.0000007",
        "input_cache_read": "0.000000025"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 8192,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "liquid/lfm-2.5-embedding-350m-free",
    "object": "model",
    "created": 1787338002,
    "owned_by": "liquid",
    "supported_operations": [
        "EMBEDDINGS"
    ],
    "supported_endpoints": [
        "/v1/embeddings"
    ],
    "name": "LFM2.5-Embedding-350M (free)",
    "description": "Semantik arama ve retrieval için 1024 boyutlu vektörler üreten ücretsiz Liquid AI embedding modeli.",
    "context_length": 512,
    "architecture": {
        "modality": "text->embedding",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "embedding"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0"
    },
    "top_provider": {
        "context_length": 512,
        "max_completion_tokens": 512,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "greenpt/kimi-k3-eu",
    "object": "model",
    "created": 1788950359,
    "owned_by": "greenpt",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Kimi K3",
    "description": "Uzun belge analizi ve görsel okuma için 1M bağlamlı akıl yürüten model; araç çağrısı ve cache destekli.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000004064029",
        "completion": "0.000020320146",
        "input_cache_read": "0.000001016007"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 1000000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "greenpt/glm-5.3-eu",
    "object": "model",
    "created": 1788950359,
    "owned_by": "greenpt",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-5.3",
    "description": "Genel amaçlı sohbet, araç çağrısı ve uzun belge işleyen 1M bağlamlı akıl yürütme modeli.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000001354676",
        "completion": "0.000005418706",
        "input_cache_read": "0.000000338669"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 1000000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "greenpt/glm-5.3-flash-eu",
    "object": "model",
    "created": 1788950359,
    "owned_by": "greenpt",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-5.3 Flash",
    "description": "Yüksek hacimli sohbet ve görsel okuma için bu sağlayıcının en ucuz akıl yürüten modeli.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000135468",
        "completion": "0.000000541871",
        "input_cache_read": "0.000000027094"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 1000000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "greenpt/kimi-k2.7-code-eu",
    "object": "model",
    "created": 1788950359,
    "owned_by": "greenpt",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Kimi K2.7 Code",
    "description": "Kod yazma, şema zorlamalı JSON ve araç çağrısı için 256K bağlamlı model; görsel girdiyi de işler.",
    "context_length": 256000,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000948273",
        "completion": "0.000004741367",
        "input_cache_read": "0.000000243842"
    },
    "top_provider": {
        "context_length": 256000,
        "max_completion_tokens": 256000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "greenpt/kimi-k2.6-eu",
    "object": "model",
    "created": 1788950359,
    "owned_by": "greenpt",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Kimi K2.6",
    "description": "Genel sohbet, araç çağrısı ve görsel okuma için 256K bağlamlı, cache destekli model.",
    "context_length": 256000,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000812806",
        "completion": "0.000004618215",
        "input_cache_read": "0.000000270935"
    },
    "top_provider": {
        "context_length": 256000,
        "max_completion_tokens": 256000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "greenpt/deepseek-v4-flash-0731",
    "object": "model",
    "created": 1788950359,
    "owned_by": "greenpt",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "DeepSeek V4 Flash",
    "description": "Yüksek hacimli metin işleri için 1M bağlamlı, ucuz ve cache destekli akıl yürütme modeli.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000172413",
        "completion": "0.000000431033",
        "input_cache_read": "0.000000049261"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 1000000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "greenpt/glm-5.2-eu",
    "object": "model",
    "created": 1788950359,
    "owned_by": "greenpt",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-5.2",
    "description": "Genel amaçlı sohbet ve araç çağrısı için 1M bağlamlı, ek yönerge taşımayan GLM-5.2 satırı.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000001908862",
        "completion": "0.00000566501",
        "input_cache_read": "0.00000049261"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 1000000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "greenpt/deepseek-v4.1-flash",
    "object": "model",
    "created": 1791044628,
    "owned_by": "greenpt",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "DeepSeek V4.1 Flash",
    "description": "Uzun belge ve görsel içeren işler için 1M bağlamlı, cache destekli akıl yürütme modeli.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000270935",
        "completion": "0.000001354676",
        "input_cache_read": "0.000000013547"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 1000000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "greenpt/green-l",
    "object": "model",
    "created": 1788950359,
    "owned_by": "greenpt",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Green L",
    "description": "Hazır asistan üslubuyla sohbet ve görsel okuma için sağlayıcının kendi 128K bağlamlı modeli.",
    "context_length": 128000,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000307881",
        "completion": "0.000000985219"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "greenpt/green-l-raw",
    "object": "model",
    "created": 1788950359,
    "owned_by": "greenpt",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Green L Raw",
    "description": "Kendi sistem yönergenizi yazacağınız uygulamalar için yönergesiz, görsel okuyan 128K bağlamlı model.",
    "context_length": 128000,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000307881",
        "completion": "0.000000985219"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "greenpt/green-r",
    "object": "model",
    "created": 1788950359,
    "owned_by": "greenpt",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Green R",
    "description": "Adım adım akıl yürütme isteyen işler için sağlayıcının kendi 128K bağlamlı muhakeme satırı.",
    "context_length": 128000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000431033",
        "completion": "0.000001169948"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "greenpt/green-r-raw",
    "object": "model",
    "created": 1788950359,
    "owned_by": "greenpt",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Green R Raw",
    "description": "Kendi yönergesini yazan muhakeme uygulamaları için yönergesiz 128K bağlamlı akıl yürütme satırı.",
    "context_length": 128000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000431033",
        "completion": "0.000001169948"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "greenpt/minimax-m3-eu",
    "object": "model",
    "created": 1792045870,
    "owned_by": "greenpt",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "MiniMax M3",
    "description": "Uzun belge, görsel okuma ve araç çağrısı içeren ajan işleri için 1M bağlamlı, cache destekli akıl yürütme modeli.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000541871",
        "completion": "0.000002709353",
        "input_cache_read": "0.000000135468"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 1000000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "greenpt/gemma4",
    "object": "model",
    "created": 1788950359,
    "owned_by": "greenpt",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Gemma 4",
    "description": "Görsel okuma ve genel sohbet için 256K bağlamlı açık ağırlıklı Gemma 4 satırı.",
    "context_length": 256000,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000615762",
        "completion": "0.000001847286"
    },
    "top_provider": {
        "context_length": 256000,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "greenpt/gpt-oss-120b-eu",
    "object": "model",
    "created": 1788950360,
    "owned_by": "greenpt",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GPT-OSS 120B",
    "description": "Ucuz metin üretimi ve araç çağrısı için 128K bağlamlı açık ağırlıklı model.",
    "context_length": 128000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000246305",
        "completion": "0.000000862067"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "greenpt/qwen3.6-35b-a3b-eu",
    "object": "model",
    "created": 1788950360,
    "owned_by": "greenpt",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen3.6 35B A3B",
    "description": "Görsel okuma ve çok dilli metin işleri için 256K bağlamlı seyrek uzman (MoE) modeli.",
    "context_length": 256000,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000369457",
        "completion": "0.000002216743"
    },
    "top_provider": {
        "context_length": 256000,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "greenpt/qwen3.5-397b-a17b-eu",
    "object": "model",
    "created": 1788950360,
    "owned_by": "greenpt",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen3.5 397B A17B",
    "description": "Zor muhakeme ve görsel okuma işleri için 250K bağlamlı büyük seyrek uzman modeli.",
    "context_length": 250000,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000862067",
        "completion": "0.000005357129"
    },
    "top_provider": {
        "context_length": 250000,
        "max_completion_tokens": 16384,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "greenpt/qwen3-235b-a22b-instruct-2507",
    "object": "model",
    "created": 1788950360,
    "owned_by": "greenpt",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen3 235B A22B Instruct",
    "description": "Akıl yürütme token'ı harcamadan doğrudan yanıt isteyen işler için 250K bağlamlı talimat modeli.",
    "context_length": 250000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000001108372",
        "completion": "0.000003325115"
    },
    "top_provider": {
        "context_length": 250000,
        "max_completion_tokens": 16384,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "greenpt/mistral-medium-3.5-128b",
    "object": "model",
    "created": 1788950360,
    "owned_by": "greenpt",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Mistral Medium 3.5 128B",
    "description": "Ayrıntılı görsel açıklama ve titiz metin işleri için 180K bağlamlı Mistral Medium satırı.",
    "context_length": 180000,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000002216743",
        "completion": "0.000011083716"
    },
    "top_provider": {
        "context_length": 180000,
        "max_completion_tokens": 16384,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "greenpt/mistral-small-3.2-24b-instruct-2506",
    "object": "model",
    "created": 1788950360,
    "owned_by": "greenpt",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Mistral Small 3.2 24B",
    "description": "Ucuz görsel açıklama, şema zorlamalı JSON ve yüksek hacimli sohbet için 128K bağlamlı model.",
    "context_length": 128000,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000246305",
        "completion": "0.00000049261"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "greenpt/llama-3.3-70b-instruct-eu",
    "object": "model",
    "created": 1788950360,
    "owned_by": "greenpt",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Llama 3.3 70B Instruct",
    "description": "Yerleşik açık ağırlıklı davranış isteyen uygulamalar için 128K bağlamlı Llama 3.3 satırı.",
    "context_length": 128000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000001354676",
        "completion": "0.000001354676"
    },
    "top_provider": {
        "context_length": 128000,
        "max_completion_tokens": 16384,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "greenpt/glm-5.2-caveman",
    "object": "model",
    "created": 1788950360,
    "owned_by": "greenpt",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-5.2 Caveman",
    "description": "Caveman üslubunda kısa ve doğrudan yazılım yanıtları için GLM-5.2; 1M bağlam, araç çağrısı, cache.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000001908862",
        "completion": "0.00000566501",
        "input_cache_read": "0.00000049261"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 1000000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "greenpt/glm-5.2-caveman-lite",
    "object": "model",
    "created": 1788950360,
    "owned_by": "greenpt",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-5.2 Caveman Lite",
    "description": "Caveman Lite üslubunda kısa ve doğrudan yazılım yanıtları için GLM-5.2; 1M bağlam, araç çağrısı, cache.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000001908862",
        "completion": "0.00000566501",
        "input_cache_read": "0.00000049261"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 1000000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "greenpt/glm-5.2-caveman-ultra",
    "object": "model",
    "created": 1788950360,
    "owned_by": "greenpt",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-5.2 Caveman Ultra",
    "description": "Caveman Ultra üslubunda kısa ve doğrudan yazılım yanıtları için GLM-5.2; 1M bağlam, araç çağrısı, cache.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000001908862",
        "completion": "0.00000566501",
        "input_cache_read": "0.00000049261"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 1000000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "greenpt/glm-5.2-honey",
    "object": "model",
    "created": 1788950360,
    "owned_by": "greenpt",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-5.2 Honey",
    "description": "Honey üslubunda kısa ve doğrudan yazılım yanıtları için GLM-5.2; 1M bağlam, araç çağrısı, cache.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000001908862",
        "completion": "0.00000566501",
        "input_cache_read": "0.00000049261"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 1000000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "greenpt/glm-5.2-honey-lite",
    "object": "model",
    "created": 1788950360,
    "owned_by": "greenpt",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-5.2 Honey Lite",
    "description": "Honey Lite üslubunda kısa ve doğrudan yazılım yanıtları için GLM-5.2; 1M bağlam, araç çağrısı, cache.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000001908862",
        "completion": "0.00000566501",
        "input_cache_read": "0.00000049261"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 1000000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "greenpt/glm-5.2-honey-ultra",
    "object": "model",
    "created": 1788950360,
    "owned_by": "greenpt",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-5.2 Honey Ultra",
    "description": "Honey Ultra üslubunda kısa ve doğrudan yazılım yanıtları için GLM-5.2; 1M bağlam, araç çağrısı, cache.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000001908862",
        "completion": "0.00000566501",
        "input_cache_read": "0.00000049261"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 1000000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "greenpt/glm-5.2-ponytail",
    "object": "model",
    "created": 1788950360,
    "owned_by": "greenpt",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-5.2 Ponytail",
    "description": "Ponytail üslubunda kısa ve doğrudan yazılım yanıtları için GLM-5.2; 1M bağlam, araç çağrısı, cache.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000001908862",
        "completion": "0.00000566501",
        "input_cache_read": "0.00000049261"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 1000000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "greenpt/glm-5.2-ponytail-lite",
    "object": "model",
    "created": 1788950360,
    "owned_by": "greenpt",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-5.2 Ponytail Lite",
    "description": "Ponytail Lite üslubunda kısa ve doğrudan yazılım yanıtları için GLM-5.2; 1M bağlam, araç çağrısı, cache.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000001908862",
        "completion": "0.00000566501",
        "input_cache_read": "0.00000049261"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 1000000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "greenpt/glm-5.2-ponytail-ultra",
    "object": "model",
    "created": 1788950360,
    "owned_by": "greenpt",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-5.2 Ponytail Ultra",
    "description": "Ponytail Ultra üslubunda kısa ve doğrudan yazılım yanıtları için GLM-5.2; 1M bağlam, araç çağrısı, cache.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000001908862",
        "completion": "0.00000566501",
        "input_cache_read": "0.00000049261"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 1000000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "greenpt/green-embedding",
    "object": "model",
    "created": 1788950360,
    "owned_by": "greenpt",
    "supported_operations": [
        "EMBEDDINGS"
    ],
    "supported_endpoints": [
        "/v1/embeddings"
    ],
    "name": "Green Embedding",
    "description": "Avrupa'da barındırılan arama ve belge getirme yığınları için 2560 boyutlu embedding modeli.",
    "context_length": 32000,
    "architecture": {
        "modality": "text->embedding",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "embedding"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000246305"
    },
    "top_provider": {
        "context_length": 32000,
        "max_completion_tokens": 32000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "greenpt/qwen3-embedding-8b",
    "object": "model",
    "created": 1788950360,
    "owned_by": "greenpt",
    "supported_operations": [
        "EMBEDDINGS"
    ],
    "supported_endpoints": [
        "/v1/embeddings"
    ],
    "name": "Qwen3 Embedding 8B",
    "description": "Çok dilli belge getirme için 4096 boyutlu embedding modeli; sağlayıcının en yüksek boyutlu satırı.",
    "context_length": 32000,
    "architecture": {
        "modality": "text->embedding",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "embedding"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000307881"
    },
    "top_provider": {
        "context_length": 32000,
        "max_completion_tokens": 32000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "greenpt/bge-multilingual-gemma2",
    "object": "model",
    "created": 1788950360,
    "owned_by": "greenpt",
    "supported_operations": [
        "EMBEDDINGS"
    ],
    "supported_endpoints": [
        "/v1/embeddings"
    ],
    "name": "BGE Multilingual Gemma 2",
    "description": "Büyük koleksiyonları düşük maliyetle vektörleştiren işler için 3584 boyutlu çok dilli embedding modeli.",
    "context_length": 8000,
    "architecture": {
        "modality": "text->embedding",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "embedding"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000135468"
    },
    "top_provider": {
        "context_length": 8000,
        "max_completion_tokens": 8000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "greenpt/green-rerank",
    "object": "model",
    "created": 1788950360,
    "owned_by": "greenpt",
    "supported_operations": [
        "RERANK"
    ],
    "supported_endpoints": [
        "/v1/rerank"
    ],
    "name": "Green Rerank",
    "description": "Arama sonuçlarını alaka sırasına dizen işler için Avrupa'da barındırılan yeniden sıralama modeli.",
    "context_length": 32000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000147783"
    },
    "top_provider": {
        "context_length": 32000,
        "max_completion_tokens": 32000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "greenpt/metis",
    "object": "model",
    "created": 1792045870,
    "owned_by": "greenpt",
    "supported_operations": [
        "SYSTEM_ONE"
    ],
    "supported_endpoints": [
        "/v1/systemone"
    ],
    "name": "Metis",
    "description": "Yönlendirme, sınıflandırma ve onay kararları için serbest metin yerine olasılıklı, tiplenmiş yanıt döndüren System One modeli.",
    "context_length": 32768,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000147783",
        "completion": "0"
    },
    "top_provider": {
        "context_length": 32768,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "agnes/agnes-3.0-flash",
    "object": "model",
    "created": 1789414339,
    "owned_by": "agnes",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Agnes 3.0 Flash",
    "description": "Ajan tabanlı kodlama ve araç kullanımı için çok modlu model; 524K bağlam, görsel ve video girdi, ücretsiz.",
    "context_length": 524288,
    "architecture": {
        "modality": "text+image+video->text",
        "input_modalities": [
            "text",
            "image",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0",
        "completion": "0",
        "input_cache_read": "0"
    },
    "top_provider": {
        "context_length": 524288,
        "max_completion_tokens": 65536,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": []
    }
}

{
    "id": "agnes/agnes-2.5-flash",
    "object": "model",
    "created": 1789414339,
    "owned_by": "agnes",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Agnes 2.5 Flash",
    "description": "Sohbet, kodlama ve ajan akışları için çok modlu model; 524K bağlam, görsel ve video girdi, prompt cache, ücretsiz.",
    "context_length": 524288,
    "architecture": {
        "modality": "text+image+video->text",
        "input_modalities": [
            "text",
            "image",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0",
        "completion": "0",
        "input_cache_read": "0"
    },
    "top_provider": {
        "context_length": 524288,
        "max_completion_tokens": 65536,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "typesafe/jev-1.14.0",
    "object": "model",
    "created": 1792134775,
    "owned_by": "typesafe",
    "supported_operations": [
        "SYSTEM_ONE"
    ],
    "supported_endpoints": [
        "/v1/systemone"
    ],
    "name": "Jev 1.14",
    "description": "Yönlendirme, sınıflandırma ve görsel kontrolü için TypeSafe'in en yeni System One modeli: serbest metin yerine tiplenmiş karar döndürür, Box sorusuyla görseldeki nesnenin yerini bulur.",
    "context_length": 32000,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000042",
        "completion": "0"
    },
    "top_provider": {
        "context_length": 32000,
        "max_completion_tokens": 32000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "typesafe/jev",
    "object": "model",
    "created": 1789675167,
    "owned_by": "typesafe",
    "supported_operations": [
        "SYSTEM_ONE"
    ],
    "supported_endpoints": [
        "/v1/systemone"
    ],
    "name": "Jev 1.13",
    "description": "Jev 1.13'e sabitlenmiş TypeSafe System One modeli: yönlendirme ve sınıflandırma için tiplenmiş karar; bu sürüme göre ayarlanmış entegrasyonlar için.",
    "context_length": 32000,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000042",
        "completion": "0"
    },
    "top_provider": {
        "context_length": 32000,
        "max_completion_tokens": 32000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "prismml/ternary-bonsai-2-27b",
    "object": "model",
    "created": 1789829540,
    "owned_by": "prismml",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Ternary Bonsai 2 27B",
    "description": "Kodlama, görsel anlama ve araç kullanan ajan işleri için Qwen3.8 27B'nin üçlü ağırlıklı sıkıştırılmış sürümü: 262K bağlam, zorunlu tool_choice dahil araç çağrısı, varsayılan açık reasoning.",
    "context_length": 262144,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000075",
        "completion": "0.0000005"
    },
    "top_provider": {
        "context_length": 262144,
        "max_completion_tokens": 262144,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "evren/gemma-4-31b",
    "object": "model",
    "created": 1789895802,
    "owned_by": "evren",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Gemma 4 31B",
    "description": "Görsel anlama ve belge okuma için 30,7 milyar parametreli yoğun model: 256K bağlam, metin ve görsel girdi, kendi EVREN anahtarınızla çalışır.",
    "context_length": 256000,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0",
        "completion": "0",
        "input_cache_read": "0"
    },
    "top_provider": {
        "context_length": 256000,
        "max_completion_tokens": 256000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "temperature",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "evren/deepseek-v4-flash-tr",
    "object": "model",
    "created": 1789895802,
    "owned_by": "evren",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "DeepSeek V4 Flash",
    "description": "Kod üretimi ve ajan döngüleri için 284 milyar parametreli MoE model: 1M bağlam, kendi EVREN anahtarınızla çalışır.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0",
        "completion": "0",
        "input_cache_read": "0"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 1000000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "temperature",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "evren/qwen3.8-flash-next",
    "object": "model",
    "created": 1789895802,
    "owned_by": "evren",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen3.8 Flash Next",
    "description": "Yüksek hacimli sohbet ve uzun bağlam ajan görevleri için 180 milyar parametreli MoE model: 256K bağlam, kendi EVREN anahtarınızla çalışır.",
    "context_length": 256000,
    "architecture": {
        "modality": "text+image+video->text",
        "input_modalities": [
            "text",
            "image",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0",
        "completion": "0",
        "input_cache_read": "0"
    },
    "top_provider": {
        "context_length": 256000,
        "max_completion_tokens": 256000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "temperature",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "evren/glm-5.3-fp8",
    "object": "model",
    "created": 1789895802,
    "owned_by": "evren",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-5.3",
    "description": "Derin akıl yürütme ve çok adımlı ajan döngüleri için 753 milyar parametreli amiral MoE model: 512K bağlam, kendi EVREN anahtarınızla çalışır.",
    "context_length": 512000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0",
        "completion": "0",
        "input_cache_read": "0"
    },
    "top_provider": {
        "context_length": 512000,
        "max_completion_tokens": 512000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "temperature",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "evren/qwen3-vl-30b",
    "object": "model",
    "created": 1789895802,
    "owned_by": "evren",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen3 VL 30B",
    "description": "Video analizi ve kare bazlı olay çıkarımı için 30 milyar parametreli MoE model: 256K bağlam, kendi EVREN anahtarınızla çalışır.",
    "context_length": 256000,
    "architecture": {
        "modality": "text+image+video->text",
        "input_modalities": [
            "text",
            "image",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0",
        "completion": "0",
        "input_cache_read": "0"
    },
    "top_provider": {
        "context_length": 256000,
        "max_completion_tokens": 256000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "temperature",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "evren/mimo-v2.6-pro-tr",
    "object": "model",
    "created": 1790603773,
    "owned_by": "evren",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "MiMo V2.6 Pro",
    "description": "Uzun soluklu ajan işleri için 1,02 trilyon parametreli MoE model: 1M bağlam, görsel girdi, araç çağrısı ve ayarlanabilir düşünme, kendi EVREN anahtarınızla çalışır.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0",
        "completion": "0",
        "input_cache_read": "0"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 1048576,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
            "none",
            "minimal"
        ]
    }
}

{
    "id": "evren/deepseek-v4.1-flash-tr",
    "object": "model",
    "created": 1791349371,
    "owned_by": "evren",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "DeepSeek V4.1 Flash",
    "description": "Kod ve ajan işleri için 763 milyar parametreli MoE model: 1M bağlam, görsel girdi, araç çağrısı ve kapatılabilir düşünme, kendi EVREN anahtarınızla çalışır.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0",
        "completion": "0",
        "input_cache_read": "0"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 1048576,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
            "none"
        ]
    }
}

{
    "id": "fastino/gliner2.5-multi-v1",
    "object": "model",
    "created": 1790332071,
    "owned_by": "fastino",
    "supported_operations": [
        "EXTRACTION"
    ],
    "supported_endpoints": [
        "/v1/extract"
    ],
    "name": "GLiNER 2.5 Multilingual",
    "description": "Metinden varlık, sınıflandırma etiketi, alan ve ilişki çıkarmak için çok dilli model; sonucu gönderdiğiniz şemaya göre JSON olarak döndürür.",
    "context_length": 4096,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000003",
        "completion": "0"
    },
    "top_provider": {
        "context_length": 4096,
        "max_completion_tokens": 4096,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "fastino/glide",
    "object": "model",
    "created": 1791009286,
    "owned_by": "fastino",
    "supported_operations": [
        "SYSTEM_ONE"
    ],
    "supported_endpoints": [
        "/v1/systemone"
    ],
    "name": "GLiDE",
    "description": "Yönlendirme, sınıflandırma ve onay kararları için serbest metin yerine olasılıklı, tiplenmiş karar döndüren System One modeli.",
    "context_length": 40000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000015",
        "completion": "0"
    },
    "top_provider": {
        "context_length": 40000,
        "max_completion_tokens": 40000,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "together/tev1-4b-experimental",
    "object": "model",
    "created": 1790846283,
    "owned_by": "together",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Tev1 4B Experimental",
    "description": "Destek talebi yönlendirme ve sınıflandırma gibi karar işleri için deneysel model: A-X harfli 2-24 seçenekten birini seçip yalnızca harfini döndürür; yanıt en fazla 8 token, çıktı ücretsiz.",
    "context_length": 32768,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000042",
        "completion": "0"
    },
    "top_provider": {
        "context_length": 32768,
        "max_completion_tokens": 8,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "temperature",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "unbiased/pareto",
    "object": "model",
    "created": 1790872543,
    "owned_by": "unbiased",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Pareto",
    "description": "Kodlama ve ajan işleri için Unbiased'ın harmanlanmış modeli: tek model kimliği, metin ve görsel girdi, 1M bağlam, araç çağrısı ve otomatik prompt cache.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000008",
        "completion": "0.0000032",
        "input_cache_read": "0.00000003"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 131072,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "apodex/apodex-1.1",
    "object": "model",
    "created": 1791003530,
    "owned_by": "apodex",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Apodex 1.1",
    "description": "Karmaşık akıl yürütme ve uzun belgeler için 397B amiral model; 262K bağlam, görsel girdi, araç çağrısı, prompt cache.",
    "context_length": 262144,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000024",
        "completion": "0.0000024",
        "input_cache_read": "0.000000024"
    },
    "top_provider": {
        "context_length": 262144,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "response_format",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "apodex/apodex-1.1-mini",
    "object": "model",
    "created": 1791003530,
    "owned_by": "apodex",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Apodex 1.1 Mini",
    "description": "Yüksek hacimli sınıflandırma, çıkarım ve taslak için düşük maliyetli 35B model; 262K bağlam, görsel girdi, araç çağrısı.",
    "context_length": 262144,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000008",
        "completion": "0.0000008",
        "input_cache_read": "0.000000008"
    },
    "top_provider": {
        "context_length": 262144,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "response_format",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "tensorx/kimi-k3-tensorx",
    "object": "model",
    "created": 1791577993,
    "owned_by": "tensorx",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Kimi K3",
    "description": "Uzun belge analizi ve görsel okuma için 1M bağlamlı akıl yürütme modeli; araç çağrısı destekli.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000003",
        "completion": "0.000015",
        "input_cache_read": "0.00000075"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 1048576,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "tensorx/kimi-k2.7-code-tensorx",
    "object": "model",
    "created": 1791577994,
    "owned_by": "tensorx",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Kimi K2.7 Code",
    "description": "Kod yazma ve kodlama ajanları için 262K bağlamlı akıl yürütme modeli; araç çağrısı ve cache destekli.",
    "context_length": 262144,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000125",
        "completion": "0.0000045",
        "input_cache_read": "0.00000031"
    },
    "top_provider": {
        "context_length": 262144,
        "max_completion_tokens": 262144,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "tensorx/glm-5.3-tensorx",
    "object": "model",
    "created": 1791577994,
    "owned_by": "tensorx",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-5.3",
    "description": "Genel amaçlı sohbet, araç çağrısı ve uzun belge işleri için 1M bağlamlı akıl yürütme modeli.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000175",
        "completion": "0.0000045",
        "input_cache_read": "0.00000044"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 1048576,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "tensorx/glm-5.3-flash-tensorx",
    "object": "model",
    "created": 1791577994,
    "owned_by": "tensorx",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-5.3 Flash",
    "description": "Görsel içeren ve yüksek hacimli işler için 1M bağlamlı, düşük maliyetli akıl yürütme modeli.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000002",
        "completion": "0.0000005",
        "input_cache_read": "0.00000005"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 1048576,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "tensorx/glm-5.2-tensorx",
    "object": "model",
    "created": 1791577994,
    "owned_by": "tensorx",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "GLM-5.2",
    "description": "Metin ağırlıklı sohbet ve araç çağrısı işleri için 1M bağlamlı akıl yürütme modeli.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000015",
        "completion": "0.0000045",
        "input_cache_read": "0.00000038"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 1048576,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "tensorx/minimax-m3-tensorx",
    "object": "model",
    "created": 1791577994,
    "owned_by": "tensorx",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "MiniMax M3",
    "description": "Ajan döngüleri ve görsel içeren uzun işler için 1M bağlamlı akıl yürütme modeli; araç çağrısı ve cache.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000004",
        "completion": "0.000002",
        "input_cache_read": "0.0000001"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 1048576,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "tensorx/deepseek-v4-pro-0813-tensorx",
    "object": "model",
    "created": 1791577994,
    "owned_by": "tensorx",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "DeepSeek V4 Pro 0813",
    "description": "Zor metin, kod ve ajan işleri için 1M bağlamlı büyük model; araç çağrısı ve cache destekli.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000002",
        "completion": "0.000004",
        "input_cache_read": "0.0000005"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 1048576,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "tensorx/deepseek-v4.1-flash-tensorx",
    "object": "model",
    "created": 1791577994,
    "owned_by": "tensorx",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "DeepSeek V4.1 Flash",
    "description": "Uzun belge ve görsel içeren işler için 1M bağlamlı, düşük maliyetli model; araç çağrısı destekli.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000005",
        "completion": "0.0000015",
        "input_cache_read": "0.00000013"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 1048576,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "tensorx/deepseek-v4-flash-0731-tensorx",
    "object": "model",
    "created": 1791577994,
    "owned_by": "tensorx",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "DeepSeek V4 Flash 0731",
    "description": "Uzun metin işleri ve düşük çıktı maliyeti için 1M bağlamlı model; araç çağrısı destekli.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000025",
        "completion": "0.0000003",
        "input_cache_read": "0.00000006"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 1048576,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "tensorx/qwen3.8-2.4t-a95b-tensorx",
    "object": "model",
    "created": 1791577994,
    "owned_by": "tensorx",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen3.8 2.4T A95B",
    "description": "Zor metin ve kod işleri için 262K bağlamlı büyük akıl yürütme modeli; araç çağrısı ve cache destekli.",
    "context_length": 262144,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000025",
        "completion": "0.000006",
        "input_cache_read": "0.00000063"
    },
    "top_provider": {
        "context_length": 262144,
        "max_completion_tokens": 262144,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "tensorx/qwen3.8-27b-tensorx",
    "object": "model",
    "created": 1791577994,
    "owned_by": "tensorx",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen3.8 27B",
    "description": "Görsel içeren sohbet ve araç kullanan işler için orta boy, 262K bağlamlı akıl yürütme modeli.",
    "context_length": 262144,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000004",
        "completion": "0.0000024",
        "input_cache_read": "0.0000001"
    },
    "top_provider": {
        "context_length": 262144,
        "max_completion_tokens": 262144,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "tensorx/qwen3.8-flash-next-tensorx",
    "object": "model",
    "created": 1791577994,
    "owned_by": "tensorx",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen3.8 Flash Next",
    "description": "Yüksek hacimli sohbet ve görsel içeren işler için düşük maliyetli akıl yürütme modeli; araç çağrısı ve cache.",
    "context_length": 262144,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000002",
        "completion": "0.0000005",
        "input_cache_read": "0.00000005"
    },
    "top_provider": {
        "context_length": 262144,
        "max_completion_tokens": 262144,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "tensorx/qwen3-embedding-8b-tensorx",
    "object": "model",
    "created": 1791577994,
    "owned_by": "tensorx",
    "supported_operations": [
        "EMBEDDINGS"
    ],
    "supported_endpoints": [
        "/v1/embeddings"
    ],
    "name": "Qwen3 Embedding 8B",
    "description": "Çok dilli belge getirme ve anlamsal arama için 4096 boyutlu embedding modeli.",
    "context_length": 40960,
    "architecture": {
        "modality": "text->embedding",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "embedding"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000002"
    },
    "top_provider": {
        "context_length": 40960,
        "max_completion_tokens": 40960,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "tensorx/deepseek-v4.1-flash-1017-tensorx",
    "object": "model",
    "created": 1792386117,
    "owned_by": "tensorx",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "DeepSeek V4.1 Flash 1017",
    "description": "Uzun belge, kodlama ve görsel içeren işler için DeepSeek V4.1 Flash'ın 17 Ekim 2026 sürümü; araç çağrısı ve cache destekli.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000005",
        "completion": "0.0000015",
        "input_cache_read": "0.00000013"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 1048576,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "nace/drex-max-free",
    "object": "model",
    "created": 1792484259,
    "owned_by": "nace",
    "supported_operations": [
        "SYSTEM_ONE"
    ],
    "supported_endpoints": [
        "/v1/systemone"
    ],
    "name": "Drex Max (Ücretsiz)",
    "description": "Metin ve görsel üzerinde sınıflandırma, yönlendirme ve görsel kontrolü için tiplenmiş karar döndüren Nace karar modeli; 31 Ekim 2026 23:59'a (TSİ) kadar ücretsiz.",
    "context_length": 131072,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0",
        "completion": "0"
    },
    "top_provider": {
        "context_length": 131072,
        "max_completion_tokens": 131072,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "nace/drex-v2.0",
    "object": "model",
    "created": 1791998630,
    "owned_by": "nace",
    "supported_operations": [
        "SYSTEM_ONE"
    ],
    "supported_endpoints": [
        "/v1/systemone"
    ],
    "name": "Drex 2.0",
    "description": "Sınıflandırma ve yönlendirme için tiplenmiş karar döndüren Nace karar modelinin en yeni numaralı sürümü; 131K durum.",
    "context_length": 131072,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000006",
        "completion": "0"
    },
    "top_provider": {
        "context_length": 131072,
        "max_completion_tokens": 131072,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "yandex/alice-ai-llm",
    "object": "model",
    "created": 1791794408,
    "owned_by": "yandex",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Alice AI LLM",
    "description": "Sohbet asistanları ve bilgi tabanından yanıt üretme için 131K bağlamlı Yandex modeli; araç çağrısı destekli.",
    "context_length": 131072,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000409836",
        "completion": "0.000009836064"
    },
    "top_provider": {
        "context_length": 131072,
        "max_completion_tokens": 131072,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "yandex/alice-ai-llm-flash",
    "object": "model",
    "created": 1791794408,
    "owned_by": "yandex",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Alice AI LLM Flash",
    "description": "Ajan senaryoları ve araç kullanan asistanlar için hızlı, düşük maliyetli Yandex modeli; 64K bağlam.",
    "context_length": 65536,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000000819672",
        "completion": "0.000001639344",
        "input_cache_read": "0.000000204918"
    },
    "top_provider": {
        "context_length": 65536,
        "max_completion_tokens": 65536,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "yandex/yandexgpt-5.1-pro",
    "object": "model",
    "created": 1791794408,
    "owned_by": "yandex",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "YandexGPT 5.1 Pro",
    "description": "Kurumsal metin işleri ve belge analizi için 32K bağlamlı YandexGPT Pro sürümü; araç çağrısı destekli.",
    "context_length": 32768,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000006557376",
        "completion": "0.000006557376"
    },
    "top_provider": {
        "context_length": 32768,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "yandex/yandexgpt-5-pro",
    "object": "model",
    "created": 1791794408,
    "owned_by": "yandex",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "YandexGPT 5 Pro",
    "description": "Kurumsal ve araştırma odaklı metin işleri için 32K bağlamlı YandexGPT 5 Pro; araç çağrısı destekli.",
    "context_length": 32768,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000009836064",
        "completion": "0.000009836064"
    },
    "top_provider": {
        "context_length": 32768,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "yandex/yandexgpt-5-lite",
    "object": "model",
    "created": 1791794408,
    "owned_by": "yandex",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "YandexGPT 5 Lite",
    "description": "Hızlı ve kararlı kısa yanıtlar gereken sohbet işleri için 32K bağlamlı hafif YandexGPT modeli.",
    "context_length": 32768,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000001639344",
        "completion": "0.000001639344"
    },
    "top_provider": {
        "context_length": 32768,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "heabsy/qwen3.8-27b-heabsy",
    "object": "model",
    "created": 1791951062,
    "owned_by": "heabsy",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen3.8 27B",
    "description": "Görsel girdili sohbet, araç çağrısı ve uzun metin işleri için orta boy Qwen3.8 27B; 262K bağlam.",
    "context_length": 262144,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000001",
        "completion": "0.000003",
        "input_cache_read": "0.0000000761"
    },
    "top_provider": {
        "context_length": 262144,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "heabsy/qwen3.8-27b-heabsy-free",
    "object": "model",
    "created": 1791951062,
    "owned_by": "heabsy",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Qwen3.8 27B (Ücretsiz)",
    "description": "Görsel girdili sohbet ve araç çağrısı için Qwen3.8 27B; 2 Kasım 2026 00:00'a (TSİ) kadar ücretsiz, 262K bağlam.",
    "context_length": 262144,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0",
        "completion": "0",
        "input_cache_read": "0"
    },
    "top_provider": {
        "context_length": 262144,
        "max_completion_tokens": 32768,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "heabsy/mimo-v2.6-flash-heabsy",
    "object": "model",
    "created": 1791951062,
    "owned_by": "heabsy",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "MiMo V2.6 Flash",
    "description": "Görsel girdili sohbet ve ajan işleri için Xiaomi MiMo V2.6 Flash; 1M bağlam, araç çağrısı destekli.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000004762",
        "completion": "0.0000014286",
        "input_cache_read": "0.00000019"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 65536,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "moondream/moondream3.1-9b-a2b",
    "object": "model",
    "created": 1792144188,
    "owned_by": "moondream",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Moondream 3.1",
    "description": "Görsel soru-cevap, görsel açıklama, OCR ve görsel akıl yürütme için Moondream'in küçük vision-language modeli; metin ve görsel girdi, 32K bağlam.",
    "context_length": 32000,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000003",
        "completion": "0.0000025"
    },
    "top_provider": {
        "context_length": 32000,
        "max_completion_tokens": 32000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "reasoning",
        "temperature",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": []
    }
}

{
    "id": "moondream/moondream3-preview",
    "object": "model",
    "created": 1792144188,
    "owned_by": "moondream",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Moondream 3 Preview",
    "description": "Moondream 3'ün önizleme sürümü: görsel soru-cevap, görsel açıklama, OCR ve görsel akıl yürütme için vision-language modeli; 32K bağlam.",
    "context_length": 32000,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000003",
        "completion": "0.0000025"
    },
    "top_provider": {
        "context_length": 32000,
        "max_completion_tokens": 32000,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "reasoning",
        "temperature",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": false,
        "supported_efforts": []
    }
}

{
    "id": "elorian/glimpse",
    "object": "model",
    "created": 1792234461,
    "owned_by": "elorian",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Glimpse",
    "description": "Görsel ve video hakkındaki sorular için Elorian'ın akıl yürütme ajanı: gerektiğinde kod çalıştırır ve web'de arar.",
    "context_length": 220000,
    "architecture": {
        "modality": "text+image+video->text",
        "input_modalities": [
            "text",
            "image",
            "video"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.0000006",
        "completion": "0.000003",
        "input_cache_read": "0.00000006"
    },
    "top_provider": {
        "context_length": 220000,
        "max_completion_tokens": 220000,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "reasoning",
        "reasoning_effort",
        "temperature",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": [
            "low",
            "medium",
            "xhigh"
        ]
    }
}

{
    "id": "ifm/jais-3-mova-36b-a4b",
    "object": "model",
    "created": 1792382037,
    "owned_by": "ifm",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Jais 3 MoVA 36B A4B",
    "description": "Arapça ve İngilizce için geliştirilmiş, araç çağırabilen 36B parametreli (4B aktif) Jais 3 modeli; 5 Kasım 2026 23:59'a kadar ücretsiz, 512K bağlam.",
    "context_length": 524288,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0",
        "completion": "0"
    },
    "top_provider": {
        "context_length": 524288,
        "max_completion_tokens": 524288,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
            "low",
            "high"
        ]
    }
}

{
    "id": "ifm/k2-horizon-375b-a23b",
    "object": "model",
    "created": 1792382037,
    "owned_by": "ifm",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "K2 Horizon 375B A23B",
    "description": "Adım adım akıl yürütme ve araç çağıran iş akışları için IFM'in her yanıttan önce düşünen 375B parametreli (23B aktif) açık ağırlıklı modeli; 5 Kasım 2026 23:59'a kadar ücretsiz, 512K bağlam.",
    "context_length": 524288,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0",
        "completion": "0"
    },
    "top_provider": {
        "context_length": 524288,
        "max_completion_tokens": 524288,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": [
            "medium",
            "high"
        ]
    }
}

{
    "id": "ifm/jais-asr",
    "object": "model",
    "created": 1792382037,
    "owned_by": "ifm",
    "supported_operations": [
        "AUDIO_TRANSCRIPTIONS"
    ],
    "supported_endpoints": [
        "/v1/audio/transcriptions"
    ],
    "name": "Jais ASR",
    "description": "Arapça ve 19 ülkenin lehçesindeki konuşmaları yazıya dökmek için, lehçeyi de bildiren sesten metne modeli; 5 Kasım 2026 23:59'a kadar ücretsiz.",
    "context_length": 0,
    "architecture": {
        "modality": "text+audio->text",
        "input_modalities": [
            "text",
            "audio"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": [],
    "top_provider": {
        "context_length": 0,
        "max_completion_tokens": 0,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "engy/kimi-k3-engy",
    "object": "model",
    "created": 1792502074,
    "owned_by": "engy",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Kimi K3",
    "description": "Uzun belge analizi ve görsel okuma için 1M bağlamlı akıl yürütme modeli; araç çağrısı destekli.",
    "context_length": 1113088,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000195",
        "completion": "0.00000975",
        "input_cache_read": "0.000000195"
    },
    "top_provider": {
        "context_length": 1113088,
        "max_completion_tokens": 1113088,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "engy/deepseek-v4.1-flash-1017-engy",
    "object": "model",
    "created": 1792502074,
    "owned_by": "engy",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "DeepSeek V4.1 Flash 1017",
    "description": "Uzun belge, kodlama ve görsel içeren işler için DeepSeek V4.1 Flash'ın 17 Ekim 2026 sürümü; araç çağrısı ve cache destekli.",
    "context_length": 1048576,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.00000004",
        "completion": "0.00000008",
        "input_cache_read": "0.000000008"
    },
    "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 1048576,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "voltropy/vast-10m-flash-free",
    "object": "model",
    "created": 1792567280,
    "owned_by": "voltropy",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Vast-10M Flash",
    "description": "Sözleşme, dava dosyası, kod tabanı ve kayıt arşivi gibi çok uzun metinleri bölmeden tek istekte okumak için yaklaşık 10 milyon token bağlamlı model; 26 Ekim 2026 23:59'a kadar günde 10 milyon token ücretsiz.",
    "context_length": 10119296,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0",
        "completion": "0"
    },
    "top_provider": {
        "context_length": 10119296,
        "max_completion_tokens": 10119296,
        "is_moderated": false
    },
    "supported_parameters": [
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null
}

{
    "id": "internlm/intern-s2-free",
    "object": "model",
    "created": 1792674836,
    "owned_by": "internlm",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Intern-S2",
    "description": "Shanghai AI Lab'ın bilimsel problemler ve uzun soluklu ajan görevleri için geliştirdiği, görsel de okuyan Intern-S2 modeli; 31 Ekim 2026 23:59'a kadar günde 500 bin token ücretsiz.",
    "context_length": 262144,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0",
        "completion": "0"
    },
    "top_provider": {
        "context_length": 262144,
        "max_completion_tokens": 262144,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "internlm/atria-dawn-free",
    "object": "model",
    "created": 1792674836,
    "owned_by": "internlm",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Atria-Dawn",
    "description": "Shanghai AI Lab'ın araştırma ve mühendislikte araç kullanarak çok adımlı işleri sonuca götürmek için geliştirdiği ajan modeli Atria-Dawn; 31 Ekim 2026 23:59'a kadar günde 500 bin token ücretsiz.",
    "context_length": 524288,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0",
        "completion": "0"
    },
    "top_provider": {
        "context_length": 524288,
        "max_completion_tokens": 524288,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "internlm/atria-dawn-preview-free",
    "object": "model",
    "created": 1792674837,
    "owned_by": "internlm",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Atria-Dawn Preview",
    "description": "Kendi sunucunuzda çalıştırabileceğiniz açık sürümü denemek için Shanghai AI Lab ajan modeli Atria-Dawn'ın MIT lisanslı önizlemesi; 31 Ekim 2026 23:59'a kadar günde 500 bin token ücretsiz.",
    "context_length": 524288,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0",
        "completion": "0"
    },
    "top_provider": {
        "context_length": 524288,
        "max_completion_tokens": 524288,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "internlm/agents-a1-free",
    "object": "model",
    "created": 1792674837,
    "owned_by": "internlm",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Agents-A1",
    "description": "Uzun soluklu arama, mühendislik ve bilimsel araştırma görevleri için Shanghai AI Lab'ın 35 milyar parametreli ajan modeli Agents-A1; 31 Ekim 2026 23:59'a kadar günde 500 bin token ücretsiz.",
    "context_length": 262144,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0",
        "completion": "0"
    },
    "top_provider": {
        "context_length": 262144,
        "max_completion_tokens": 262144,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "internlm/sage-a1.5-free",
    "object": "model",
    "created": 1792674837,
    "owned_by": "internlm",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Sage-A1.5",
    "description": "İşi alt ajanlara dağıtıp sonuçları doğrulaması gereken uzun soluklu bilimsel görevler için Agents-A1 üzerine kurulu Shanghai AI Lab modeli Sage-A1.5; 31 Ekim 2026 23:59'a kadar günde 500 bin token ücretsiz.",
    "context_length": 262144,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0",
        "completion": "0"
    },
    "top_provider": {
        "context_length": 262144,
        "max_completion_tokens": 262144,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": []
    }
}

{
    "id": "baseten/mammoth-1-free",
    "object": "model",
    "created": 1792735017,
    "owned_by": "baseten",
    "supported_operations": [
        "SYSTEM_ONE"
    ],
    "supported_endpoints": [
        "/v1/systemone"
    ],
    "name": "Mammoth-1 (Ücretsiz)",
    "description": "Sınıflandırma, yönlendirme ve puanlama için metin ve görsel üzerinde tiplenmiş karar döndüren Base Labs karar modeli (27B); 27 Ekim 2026 23:59'a (TSİ) kadar ücretsiz.",
    "context_length": 8192,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0",
        "completion": "0"
    },
    "top_provider": {
        "context_length": 8192,
        "max_completion_tokens": 8192,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "baseten/elephant-1-free",
    "object": "model",
    "created": 1792735017,
    "owned_by": "baseten",
    "supported_operations": [
        "SYSTEM_ONE"
    ],
    "supported_endpoints": [
        "/v1/systemone"
    ],
    "name": "Elephant-1 (Ücretsiz)",
    "description": "Sınıflandırma, yönlendirme ve puanlama için metin ve görsel üzerinde tiplenmiş karar döndüren küçük Base Labs karar modeli (9B); 27 Ekim 2026 23:59'a (TSİ) kadar ücretsiz.",
    "context_length": 16384,
    "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
            "text",
            "image"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0",
        "completion": "0"
    },
    "top_provider": {
        "context_length": 16384,
        "max_completion_tokens": 16384,
        "is_moderated": false
    },
    "supported_parameters": [],
    "per_request_limits": null
}

{
    "id": "abliteration/abliterated-model-large-v2",
    "object": "model",
    "created": 1792759991,
    "owned_by": "abliteration",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Abliterated Large v2",
    "description": "Daha az ret gerektiren işler için 1M bağlamlı akıl yürütme modeli; araç çağrısı ve low/high/max düşünme seviyeleri.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000003",
        "completion": "0.000005",
        "input_cache_read": "0.0000003"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 999990,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": [
            "low",
            "high",
            "max"
        ]
    }
}

{
    "id": "abliteration/abliterated-model-large",
    "object": "model",
    "created": 1792759991,
    "owned_by": "abliteration",
    "supported_operations": [
        "CHAT_COMPLETIONS"
    ],
    "supported_endpoints": [
        "/v1/chat/completions"
    ],
    "name": "Abliterated Large",
    "description": "Daha az ret gerektiren işler için 1M bağlamlı akıl yürütme modeli; Abliterated Large v2'nin önceki sürümü.",
    "context_length": 1000000,
    "architecture": {
        "modality": "text->text",
        "input_modalities": [
            "text"
        ],
        "output_modalities": [
            "text"
        ],
        "tokenizer": null,
        "instruct_type": null
    },
    "pricing": {
        "prompt": "0.000003",
        "completion": "0.000005",
        "input_cache_read": "0.0000003"
    },
    "top_provider": {
        "context_length": 1000000,
        "max_completion_tokens": 999990,
        "is_moderated": false
    },
    "supported_parameters": [
        "include_reasoning",
        "max_completion_tokens",
        "max_tokens",
        "parallel_tool_calls",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_p"
    ],
    "per_request_limits": null,
    "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
            "none",
            "high",
            "max"
        ]
    }
}

{
    "name": "models/gemini-2.5-flash",
    "version": "001",
    "displayName": "Gemini 2.5 Flash",
    "description": "Stable version of Gemini 2.5 Flash, our mid-size multimodal model that supports up to 1 million tokens, released in June of 2025.",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-pro",
    "version": "2.5",
    "displayName": "Gemini 2.5 Pro",
    "description": "Stable release (June 17th, 2025) of Gemini 2.5 Pro",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-flash-preview-tts",
    "version": "gemini-2.5-flash-exp-tts-2025-05-19",
    "displayName": "Gemini 2.5 Flash Preview TTS",
    "description": "Gemini 2.5 Flash Preview TTS",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 16384,
    "supportedGenerationMethods": [
        "countTokens",
        "generateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-2.5-pro-preview-tts",
    "version": "gemini-2.5-pro-preview-tts-2025-05-19",
    "displayName": "Gemini 2.5 Pro Preview TTS",
    "description": "Gemini 2.5 Pro Preview TTS",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 16384,
    "supportedGenerationMethods": [
        "countTokens",
        "generateContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemma-4-26b-a4b-it",
    "version": "001",
    "displayName": "Gemma 4 26B A4B IT",
    "description": "Gemma 4 26B A4B IT",
    "inputTokenLimit": 262144,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemma-4-31b-it",
    "version": "001",
    "displayName": "Gemma 4 31B IT",
    "description": "Gemma 4 31B IT",
    "inputTokenLimit": 262144,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-flash-latest",
    "version": "Gemini Flash Latest",
    "displayName": "Gemini Flash Latest",
    "description": "Latest release of Gemini Flash",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-flash-lite-latest",
    "version": "Gemini Flash-Lite Latest",
    "displayName": "Gemini Flash-Lite Latest",
    "description": "Latest release of Gemini Flash-Lite",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-pro-latest",
    "version": "Gemini Pro Latest",
    "displayName": "Gemini Pro Latest",
    "description": "Latest release of Gemini Pro",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-flash-lite",
    "version": "001",
    "displayName": "Gemini 2.5 Flash-Lite",
    "description": "Stable version of Gemini 2.5 Flash-Lite, released in July of 2025",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-flash-image",
    "version": "2.0",
    "displayName": "Nano Banana",
    "description": "Gemini 2.5 Flash Preview Image",
    "inputTokenLimit": 32768,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1
}

{
    "name": "models/gemini-3-flash-preview",
    "version": "3-flash-preview-12-2025",
    "displayName": "Gemini 3 Flash Preview",
    "description": "Gemini 3 Flash Preview",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.1-pro-preview",
    "version": "3.1-pro-preview-01-2026",
    "displayName": "Gemini 3.1 Pro Preview",
    "description": "Gemini 3.1 Pro Preview",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.1-pro-preview-customtools",
    "version": "3.1-pro-preview-01-2026",
    "displayName": "Gemini 3.1 Pro Preview Custom Tools",
    "description": "Gemini 3.1 Pro Preview optimized for custom tool usage",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.1-flash-lite-preview",
    "version": "3.1-flash-lite-preview-03-2026",
    "displayName": "Gemini 3.1 Flash Lite Preview",
    "description": "Gemini 3.1 Flash Lite Preview",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.1-flash-lite",
    "version": "3.1-flash-lite-05-2026",
    "displayName": "Gemini 3.1 Flash Lite",
    "description": "Gemini 3.1 Flash Lite",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3-pro-image-preview",
    "version": "3.0",
    "displayName": "Nano Banana Pro",
    "description": "Gemini 3 Pro Image Preview",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/gemini-3-pro-image",
    "version": "3.0",
    "displayName": "Nano Banana Pro",
    "description": "Gemini 3 Pro Image",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/nano-banana-pro-preview",
    "version": "3.0",
    "displayName": "Nano Banana Pro",
    "description": "Gemini 3 Pro Image Preview",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/gemini-3.1-flash-image-preview",
    "version": "3.0",
    "displayName": "Nano Banana 2",
    "description": "Gemini 3.1 Flash Image Preview.",
    "inputTokenLimit": 65536,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/gemini-3.1-flash-image",
    "version": "3.0",
    "displayName": "Nano Banana 2",
    "description": "Gemini 3.1 Flash Image.",
    "inputTokenLimit": 65536,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/gemini-3.1-flash-lite-image",
    "version": "3.0",
    "displayName": "Nano Banana 2 Lite",
    "description": "Gemini 3.1 Flash Lite Image.",
    "inputTokenLimit": 65536,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/gemini-nano-banana-2.1",
    "version": "3.0",
    "displayName": "Nano Banana 2.1",
    "description": "Gemini Nano Banana 2.1.",
    "inputTokenLimit": 65536,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/gemini-3.5-flash",
    "version": "3.5-flash-05-2026",
    "displayName": "Gemini 3.5 Flash",
    "description": "Gemini 3.5 Flash",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.5-flash-lite",
    "version": "3.5-flash-lite-07-2026",
    "displayName": "Gemini 3.5 Flash Lite",
    "description": "Gemini 3.5 Flash Lite",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-omni-flash-preview",
    "version": "001",
    "displayName": "Gemini Omni Flash Preview",
    "description": "Gemini Omni Flash Preview",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-omni-1.1-flash",
    "version": "001",
    "displayName": "Gemini Omni 1.1 Flash",
    "description": "Gemini Omni 1.1 Flash ",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.5-transcribe",
    "version": "3.5-transcribe-08-2026",
    "displayName": "Gemini 3.5 Transcribe",
    "description": "Gemini 3.5 Transcribe",
    "inputTokenLimit": 98304,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.6-flash",
    "version": "3.6-flash-07-2026",
    "displayName": "Gemini 3.6 Flash",
    "description": "Gemini 3.6 Flash",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.7-flash",
    "version": "3.7-flash-08-2026",
    "displayName": "Gemini 3.7 Flash",
    "description": "Gemini 3.7 Flash",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.8-flash",
    "version": "3.0",
    "displayName": "Gemini 3.8 Flash",
    "description": "Gemini 3.8 Flash",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-4-argon",
    "version": "3.0",
    "displayName": "Gemini 4 Argon",
    "description": "Gemini 4 Argon",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/lyria-3-clip-preview",
    "version": "lyria-3-clip-preview",
    "displayName": "Lyria 3 Clip Preview",
    "description": "Lyria 3 30s model Preview",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/lyria-3-pro-preview",
    "version": "lyria-3-pro-preview",
    "displayName": "Lyria 3 Pro Preview",
    "description": "Lyria 3 Pro Preview",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/lyria-3.5",
    "version": "3.5",
    "displayName": "Lyria 3.5",
    "description": "Music Generation model",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.1-flash-tts-preview",
    "version": "3.1-flash-tts-preview",
    "displayName": "Gemini 3.1 Flash TTS Preview",
    "description": "Gemini 3.1 Flash TTS Preview",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 16384,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.8-flash-tts",
    "version": "3.8-flash-tts",
    "displayName": "Gemini 3.8 Flash TTS",
    "description": "Gemini 3.8 Flash TTS",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 16384,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.8-flash-lite-tts",
    "version": "3.8-flash-lite-tts",
    "displayName": "Gemini 3.8 Flash Lite TTS",
    "description": "Gemini 3.8 Flash Lite TTS",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 16384,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-robotics-er-2-preview",
    "version": "2-preview",
    "displayName": "Gemini Robotics-ER 2 Preview",
    "description": "Gemini Robotics-ER 2 Preview",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-computer-use-preview-10-2025",
    "version": "Gemini 2.5 Computer Use Preview 10-2025",
    "displayName": "Gemini 2.5 Computer Use Preview 10-2025",
    "description": "Gemini 2.5 Computer Use Preview 10-2025",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/antigravity-preview-05-2026",
    "version": "0.1",
    "displayName": "Antigravity Agent Preview",
    "description": "Preview release of Antigravity Agent (05-2026)",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ]
}

{
    "name": "models/antigravity-preview-09-2026",
    "version": "0.1",
    "displayName": "Antigravity Agent Preview",
    "description": "Preview release of Antigravity Agent (09-2026)",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ]
}

{
    "name": "models/antigravity-preview-latest",
    "version": "Antigravity Agent Preview Latest",
    "displayName": "Antigravity Agent Preview Latest",
    "description": "Latest preview release of Antigravity Agent",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ]
}

{
    "name": "models/deep-research-max-preview-04-2026",
    "version": "deepthink-exp-05-20",
    "displayName": "Deep Research Max Preview (Apr-21-2026)",
    "description": "Preview release (April 21st, 2026) of Deep Research Max",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/deep-research-preview-04-2026",
    "version": "deepthink-exp-05-20",
    "displayName": "Deep Research Preview (Apr-21-2026)",
    "description": "Preview release (April 21th, 2026) of Deep Research",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/deep-research-pro-preview-12-2025",
    "version": "deepthink-exp-05-20",
    "displayName": "Deep Research Pro Preview (Dec-12-2025) [Rerouted]",
    "description": "Deprecated preview agent; automatically rerouting traffic to deep-research-preview-04-2026.",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-embedding-001",
    "version": "001",
    "displayName": "Gemini Embedding 001",
    "description": "Obtain a distributed representation of a text.",
    "inputTokenLimit": 2048,
    "outputTokenLimit": 1,
    "supportedGenerationMethods": [
        "embedContent",
        "countTextTokens",
        "countTokens",
        "asyncBatchEmbedContent"
    ]
}

{
    "name": "models/gemini-embedding-2-preview",
    "version": "2",
    "displayName": "Gemini Embedding 2 Preview",
    "description": "Obtain a distributed representation of multimodal content.",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 1,
    "supportedGenerationMethods": [
        "embedContent",
        "countTextTokens",
        "countTokens",
        "asyncBatchEmbedContent"
    ]
}

{
    "name": "models/gemini-embedding-2",
    "version": "2",
    "displayName": "Gemini Embedding 2",
    "description": "Obtain a distributed representation of multimodal content.",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 1,
    "supportedGenerationMethods": [
        "embedContent",
        "countTextTokens",
        "countTokens",
        "asyncBatchEmbedContent"
    ]
}

{
    "name": "models/aqa",
    "version": "001",
    "displayName": "Model that performs Attributed Question Answering.",
    "description": "Model trained to return answers to questions that are grounded in provided sources, along with estimating answerable probability.",
    "inputTokenLimit": 7168,
    "outputTokenLimit": 1024,
    "supportedGenerationMethods": [
        "generateAnswer"
    ],
    "temperature": 0.200000000000000011102230246251565404236316680908203125,
    "topP": 1,
    "topK": 40
}

{
    "name": "models/gemini-3.5-transcribe-live",
    "version": "3.5-transcribe-live-08-2026",
    "displayName": "Gemini 3.5 Transcribe Live",
    "description": "Gemini 3.5 Transcribe Live",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-2.5-flash-native-audio-latest",
    "version": "Gemini 2.5 Flash Native Audio Latest",
    "displayName": "Gemini 2.5 Flash Native Audio Latest",
    "description": "Latest release of Gemini 2.5 Flash Native Audio",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 8192,
    "supportedGenerationMethods": [
        "countTokens",
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-flash-native-audio-preview-09-2025",
    "version": "gemini-2.5-flash-preview-native-audio-dialog-2025-05-19",
    "displayName": "Gemini 2.5 Flash Native Audio Preview 09-2025",
    "description": "Gemini 2.5 Flash Native Audio Preview 09-2025",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 8192,
    "supportedGenerationMethods": [
        "countTokens",
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-flash-native-audio-preview-12-2025",
    "version": "12-2025",
    "displayName": "Gemini 2.5 Flash Native Audio Preview 12-2025",
    "description": "Gemini 2.5 Flash Native Audio Preview 12-2025",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 8192,
    "supportedGenerationMethods": [
        "countTokens",
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.1-flash-live-preview",
    "version": "3.1-flash-live-03-2026",
    "displayName": "Gemini 3.1 Flash Live Preview",
    "description": "Gemini 3.1 Flash Live Preview",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.8-live",
    "version": "3.1-flash-live-03-2026",
    "displayName": "Gemini 3.8 Live",
    "description": "Gemini 3.8 Live",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.8-live-extended-thinking",
    "version": "3.1-flash-live-03-2026",
    "displayName": "Gemini 3.8 Live Extended Thinking",
    "description": "Gemini 3.8 Live Extended Thinking",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-robotics-er-2-streaming-preview",
    "version": "2-streaming-preview",
    "displayName": "Gemini Robotics-ER 2 Streaming Preview",
    "description": "Gemini Robotics-ER 2 Streaming Preview",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.5-live-translate-preview",
    "version": "3.5-live-translate-06-2026",
    "displayName": "Gemini 3.5 Live Translate Preview",
    "description": "Gemini 3.5 Live Translate Preview",
    "inputTokenLimit": 16384,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/lyria-realtime-exp",
    "version": "lyria-realtime-exp",
    "displayName": "Lyria Realtime Experimental",
    "description": "Lyria Realtime Experimental",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "bidiGenerateMusic"
    ]
}

{
    "name": "models/gemini-2.5-flash",
    "version": "001",
    "displayName": "Gemini 2.5 Flash",
    "description": "Stable version of Gemini 2.5 Flash, our mid-size multimodal model that supports up to 1 million tokens, released in June of 2025.",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-pro",
    "version": "2.5",
    "displayName": "Gemini 2.5 Pro",
    "description": "Stable release (June 17th, 2025) of Gemini 2.5 Pro",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-flash-preview-tts",
    "version": "gemini-2.5-flash-exp-tts-2025-05-19",
    "displayName": "Gemini 2.5 Flash Preview TTS",
    "description": "Gemini 2.5 Flash Preview TTS",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 16384,
    "supportedGenerationMethods": [
        "countTokens",
        "generateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-2.5-pro-preview-tts",
    "version": "gemini-2.5-pro-preview-tts-2025-05-19",
    "displayName": "Gemini 2.5 Pro Preview TTS",
    "description": "Gemini 2.5 Pro Preview TTS",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 16384,
    "supportedGenerationMethods": [
        "countTokens",
        "generateContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemma-4-26b-a4b-it",
    "version": "001",
    "displayName": "Gemma 4 26B A4B IT",
    "description": "Gemma 4 26B A4B IT",
    "inputTokenLimit": 262144,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemma-4-31b-it",
    "version": "001",
    "displayName": "Gemma 4 31B IT",
    "description": "Gemma 4 31B IT",
    "inputTokenLimit": 262144,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-flash-latest",
    "version": "Gemini Flash Latest",
    "displayName": "Gemini Flash Latest",
    "description": "Latest release of Gemini Flash",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-flash-lite-latest",
    "version": "Gemini Flash-Lite Latest",
    "displayName": "Gemini Flash-Lite Latest",
    "description": "Latest release of Gemini Flash-Lite",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-pro-latest",
    "version": "Gemini Pro Latest",
    "displayName": "Gemini Pro Latest",
    "description": "Latest release of Gemini Pro",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-flash-lite",
    "version": "001",
    "displayName": "Gemini 2.5 Flash-Lite",
    "description": "Stable version of Gemini 2.5 Flash-Lite, released in July of 2025",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-flash-image",
    "version": "2.0",
    "displayName": "Nano Banana",
    "description": "Gemini 2.5 Flash Preview Image",
    "inputTokenLimit": 32768,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1
}

{
    "name": "models/gemini-3-flash-preview",
    "version": "3-flash-preview-12-2025",
    "displayName": "Gemini 3 Flash Preview",
    "description": "Gemini 3 Flash Preview",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.1-pro-preview",
    "version": "3.1-pro-preview-01-2026",
    "displayName": "Gemini 3.1 Pro Preview",
    "description": "Gemini 3.1 Pro Preview",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.1-pro-preview-customtools",
    "version": "3.1-pro-preview-01-2026",
    "displayName": "Gemini 3.1 Pro Preview Custom Tools",
    "description": "Gemini 3.1 Pro Preview optimized for custom tool usage",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.1-flash-lite-preview",
    "version": "3.1-flash-lite-preview-03-2026",
    "displayName": "Gemini 3.1 Flash Lite Preview",
    "description": "Gemini 3.1 Flash Lite Preview",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.1-flash-lite",
    "version": "3.1-flash-lite-05-2026",
    "displayName": "Gemini 3.1 Flash Lite",
    "description": "Gemini 3.1 Flash Lite",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3-pro-image-preview",
    "version": "3.0",
    "displayName": "Nano Banana Pro",
    "description": "Gemini 3 Pro Image Preview",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/gemini-3-pro-image",
    "version": "3.0",
    "displayName": "Nano Banana Pro",
    "description": "Gemini 3 Pro Image",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/nano-banana-pro-preview",
    "version": "3.0",
    "displayName": "Nano Banana Pro",
    "description": "Gemini 3 Pro Image Preview",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/gemini-3.1-flash-image-preview",
    "version": "3.0",
    "displayName": "Nano Banana 2",
    "description": "Gemini 3.1 Flash Image Preview.",
    "inputTokenLimit": 65536,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/gemini-3.1-flash-image",
    "version": "3.0",
    "displayName": "Nano Banana 2",
    "description": "Gemini 3.1 Flash Image.",
    "inputTokenLimit": 65536,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/gemini-3.1-flash-lite-image",
    "version": "3.0",
    "displayName": "Nano Banana 2 Lite",
    "description": "Gemini 3.1 Flash Lite Image.",
    "inputTokenLimit": 65536,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/gemini-nano-banana-2.1",
    "version": "3.0",
    "displayName": "Nano Banana 2.1",
    "description": "Gemini Nano Banana 2.1.",
    "inputTokenLimit": 65536,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/gemini-3.5-flash",
    "version": "3.5-flash-05-2026",
    "displayName": "Gemini 3.5 Flash",
    "description": "Gemini 3.5 Flash",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.5-flash-lite",
    "version": "3.5-flash-lite-07-2026",
    "displayName": "Gemini 3.5 Flash Lite",
    "description": "Gemini 3.5 Flash Lite",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-omni-flash-preview",
    "version": "001",
    "displayName": "Gemini Omni Flash Preview",
    "description": "Gemini Omni Flash Preview",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-omni-1.1-flash",
    "version": "001",
    "displayName": "Gemini Omni 1.1 Flash",
    "description": "Gemini Omni 1.1 Flash ",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.5-transcribe",
    "version": "3.5-transcribe-08-2026",
    "displayName": "Gemini 3.5 Transcribe",
    "description": "Gemini 3.5 Transcribe",
    "inputTokenLimit": 98304,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.6-flash",
    "version": "3.6-flash-07-2026",
    "displayName": "Gemini 3.6 Flash",
    "description": "Gemini 3.6 Flash",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.7-flash",
    "version": "3.7-flash-08-2026",
    "displayName": "Gemini 3.7 Flash",
    "description": "Gemini 3.7 Flash",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.8-flash",
    "version": "3.0",
    "displayName": "Gemini 3.8 Flash",
    "description": "Gemini 3.8 Flash",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-4-argon",
    "version": "3.0",
    "displayName": "Gemini 4 Argon",
    "description": "Gemini 4 Argon",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/lyria-3-clip-preview",
    "version": "lyria-3-clip-preview",
    "displayName": "Lyria 3 Clip Preview",
    "description": "Lyria 3 30s model Preview",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/lyria-3-pro-preview",
    "version": "lyria-3-pro-preview",
    "displayName": "Lyria 3 Pro Preview",
    "description": "Lyria 3 Pro Preview",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/lyria-3.5",
    "version": "3.5",
    "displayName": "Lyria 3.5",
    "description": "Music Generation model",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.1-flash-tts-preview",
    "version": "3.1-flash-tts-preview",
    "displayName": "Gemini 3.1 Flash TTS Preview",
    "description": "Gemini 3.1 Flash TTS Preview",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 16384,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.8-flash-tts",
    "version": "3.8-flash-tts",
    "displayName": "Gemini 3.8 Flash TTS",
    "description": "Gemini 3.8 Flash TTS",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 16384,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.8-flash-lite-tts",
    "version": "3.8-flash-lite-tts",
    "displayName": "Gemini 3.8 Flash Lite TTS",
    "description": "Gemini 3.8 Flash Lite TTS",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 16384,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-robotics-er-2-preview",
    "version": "2-preview",
    "displayName": "Gemini Robotics-ER 2 Preview",
    "description": "Gemini Robotics-ER 2 Preview",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-computer-use-preview-10-2025",
    "version": "Gemini 2.5 Computer Use Preview 10-2025",
    "displayName": "Gemini 2.5 Computer Use Preview 10-2025",
    "description": "Gemini 2.5 Computer Use Preview 10-2025",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/antigravity-preview-05-2026",
    "version": "0.1",
    "displayName": "Antigravity Agent Preview",
    "description": "Preview release of Antigravity Agent (05-2026)",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ]
}

{
    "name": "models/antigravity-preview-09-2026",
    "version": "0.1",
    "displayName": "Antigravity Agent Preview",
    "description": "Preview release of Antigravity Agent (09-2026)",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ]
}

{
    "name": "models/antigravity-preview-latest",
    "version": "Antigravity Agent Preview Latest",
    "displayName": "Antigravity Agent Preview Latest",
    "description": "Latest preview release of Antigravity Agent",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ]
}

{
    "name": "models/deep-research-max-preview-04-2026",
    "version": "deepthink-exp-05-20",
    "displayName": "Deep Research Max Preview (Apr-21-2026)",
    "description": "Preview release (April 21st, 2026) of Deep Research Max",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/deep-research-preview-04-2026",
    "version": "deepthink-exp-05-20",
    "displayName": "Deep Research Preview (Apr-21-2026)",
    "description": "Preview release (April 21th, 2026) of Deep Research",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/deep-research-pro-preview-12-2025",
    "version": "deepthink-exp-05-20",
    "displayName": "Deep Research Pro Preview (Dec-12-2025) [Rerouted]",
    "description": "Deprecated preview agent; automatically rerouting traffic to deep-research-preview-04-2026.",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-embedding-001",
    "version": "001",
    "displayName": "Gemini Embedding 001",
    "description": "Obtain a distributed representation of a text.",
    "inputTokenLimit": 2048,
    "outputTokenLimit": 1,
    "supportedGenerationMethods": [
        "embedContent",
        "countTextTokens",
        "countTokens",
        "asyncBatchEmbedContent"
    ]
}

{
    "name": "models/gemini-embedding-2-preview",
    "version": "2",
    "displayName": "Gemini Embedding 2 Preview",
    "description": "Obtain a distributed representation of multimodal content.",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 1,
    "supportedGenerationMethods": [
        "embedContent",
        "countTextTokens",
        "countTokens",
        "asyncBatchEmbedContent"
    ]
}

{
    "name": "models/gemini-embedding-2",
    "version": "2",
    "displayName": "Gemini Embedding 2",
    "description": "Obtain a distributed representation of multimodal content.",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 1,
    "supportedGenerationMethods": [
        "embedContent",
        "countTextTokens",
        "countTokens",
        "asyncBatchEmbedContent"
    ]
}

{
    "name": "models/aqa",
    "version": "001",
    "displayName": "Model that performs Attributed Question Answering.",
    "description": "Model trained to return answers to questions that are grounded in provided sources, along with estimating answerable probability.",
    "inputTokenLimit": 7168,
    "outputTokenLimit": 1024,
    "supportedGenerationMethods": [
        "generateAnswer"
    ],
    "temperature": 0.200000000000000011102230246251565404236316680908203125,
    "topP": 1,
    "topK": 40
}

{
    "name": "models/gemini-3.5-transcribe-live",
    "version": "3.5-transcribe-live-08-2026",
    "displayName": "Gemini 3.5 Transcribe Live",
    "description": "Gemini 3.5 Transcribe Live",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-2.5-flash-native-audio-latest",
    "version": "Gemini 2.5 Flash Native Audio Latest",
    "displayName": "Gemini 2.5 Flash Native Audio Latest",
    "description": "Latest release of Gemini 2.5 Flash Native Audio",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 8192,
    "supportedGenerationMethods": [
        "countTokens",
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-flash-native-audio-preview-09-2025",
    "version": "gemini-2.5-flash-preview-native-audio-dialog-2025-05-19",
    "displayName": "Gemini 2.5 Flash Native Audio Preview 09-2025",
    "description": "Gemini 2.5 Flash Native Audio Preview 09-2025",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 8192,
    "supportedGenerationMethods": [
        "countTokens",
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-flash-native-audio-preview-12-2025",
    "version": "12-2025",
    "displayName": "Gemini 2.5 Flash Native Audio Preview 12-2025",
    "description": "Gemini 2.5 Flash Native Audio Preview 12-2025",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 8192,
    "supportedGenerationMethods": [
        "countTokens",
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.1-flash-live-preview",
    "version": "3.1-flash-live-03-2026",
    "displayName": "Gemini 3.1 Flash Live Preview",
    "description": "Gemini 3.1 Flash Live Preview",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.8-live",
    "version": "3.1-flash-live-03-2026",
    "displayName": "Gemini 3.8 Live",
    "description": "Gemini 3.8 Live",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.8-live-extended-thinking",
    "version": "3.1-flash-live-03-2026",
    "displayName": "Gemini 3.8 Live Extended Thinking",
    "description": "Gemini 3.8 Live Extended Thinking",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-robotics-er-2-streaming-preview",
    "version": "2-streaming-preview",
    "displayName": "Gemini Robotics-ER 2 Streaming Preview",
    "description": "Gemini Robotics-ER 2 Streaming Preview",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.5-live-translate-preview",
    "version": "3.5-live-translate-06-2026",
    "displayName": "Gemini 3.5 Live Translate Preview",
    "description": "Gemini 3.5 Live Translate Preview",
    "inputTokenLimit": 16384,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/lyria-realtime-exp",
    "version": "lyria-realtime-exp",
    "displayName": "Lyria Realtime Experimental",
    "description": "Lyria Realtime Experimental",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "bidiGenerateMusic"
    ]
}

{
    "name": "models/gemini-2.5-flash",
    "version": "001",
    "displayName": "Gemini 2.5 Flash",
    "description": "Stable version of Gemini 2.5 Flash, our mid-size multimodal model that supports up to 1 million tokens, released in June of 2025.",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-pro",
    "version": "2.5",
    "displayName": "Gemini 2.5 Pro",
    "description": "Stable release (June 17th, 2025) of Gemini 2.5 Pro",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-flash-preview-tts",
    "version": "gemini-2.5-flash-exp-tts-2025-05-19",
    "displayName": "Gemini 2.5 Flash Preview TTS",
    "description": "Gemini 2.5 Flash Preview TTS",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 16384,
    "supportedGenerationMethods": [
        "countTokens",
        "generateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-2.5-pro-preview-tts",
    "version": "gemini-2.5-pro-preview-tts-2025-05-19",
    "displayName": "Gemini 2.5 Pro Preview TTS",
    "description": "Gemini 2.5 Pro Preview TTS",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 16384,
    "supportedGenerationMethods": [
        "countTokens",
        "generateContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemma-4-26b-a4b-it",
    "version": "001",
    "displayName": "Gemma 4 26B A4B IT",
    "description": "Gemma 4 26B A4B IT",
    "inputTokenLimit": 262144,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemma-4-31b-it",
    "version": "001",
    "displayName": "Gemma 4 31B IT",
    "description": "Gemma 4 31B IT",
    "inputTokenLimit": 262144,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-flash-latest",
    "version": "Gemini Flash Latest",
    "displayName": "Gemini Flash Latest",
    "description": "Latest release of Gemini Flash",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-flash-lite-latest",
    "version": "Gemini Flash-Lite Latest",
    "displayName": "Gemini Flash-Lite Latest",
    "description": "Latest release of Gemini Flash-Lite",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-pro-latest",
    "version": "Gemini Pro Latest",
    "displayName": "Gemini Pro Latest",
    "description": "Latest release of Gemini Pro",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-flash-lite",
    "version": "001",
    "displayName": "Gemini 2.5 Flash-Lite",
    "description": "Stable version of Gemini 2.5 Flash-Lite, released in July of 2025",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-flash-image",
    "version": "2.0",
    "displayName": "Nano Banana",
    "description": "Gemini 2.5 Flash Preview Image",
    "inputTokenLimit": 32768,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1
}

{
    "name": "models/gemini-3-flash-preview",
    "version": "3-flash-preview-12-2025",
    "displayName": "Gemini 3 Flash Preview",
    "description": "Gemini 3 Flash Preview",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.1-pro-preview",
    "version": "3.1-pro-preview-01-2026",
    "displayName": "Gemini 3.1 Pro Preview",
    "description": "Gemini 3.1 Pro Preview",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.1-pro-preview-customtools",
    "version": "3.1-pro-preview-01-2026",
    "displayName": "Gemini 3.1 Pro Preview Custom Tools",
    "description": "Gemini 3.1 Pro Preview optimized for custom tool usage",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.1-flash-lite-preview",
    "version": "3.1-flash-lite-preview-03-2026",
    "displayName": "Gemini 3.1 Flash Lite Preview",
    "description": "Gemini 3.1 Flash Lite Preview",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.1-flash-lite",
    "version": "3.1-flash-lite-05-2026",
    "displayName": "Gemini 3.1 Flash Lite",
    "description": "Gemini 3.1 Flash Lite",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3-pro-image-preview",
    "version": "3.0",
    "displayName": "Nano Banana Pro",
    "description": "Gemini 3 Pro Image Preview",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/gemini-3-pro-image",
    "version": "3.0",
    "displayName": "Nano Banana Pro",
    "description": "Gemini 3 Pro Image",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/nano-banana-pro-preview",
    "version": "3.0",
    "displayName": "Nano Banana Pro",
    "description": "Gemini 3 Pro Image Preview",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/gemini-3.1-flash-image-preview",
    "version": "3.0",
    "displayName": "Nano Banana 2",
    "description": "Gemini 3.1 Flash Image Preview.",
    "inputTokenLimit": 65536,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/gemini-3.1-flash-image",
    "version": "3.0",
    "displayName": "Nano Banana 2",
    "description": "Gemini 3.1 Flash Image.",
    "inputTokenLimit": 65536,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/gemini-3.1-flash-lite-image",
    "version": "3.0",
    "displayName": "Nano Banana 2 Lite",
    "description": "Gemini 3.1 Flash Lite Image.",
    "inputTokenLimit": 65536,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/gemini-nano-banana-2.1",
    "version": "3.0",
    "displayName": "Nano Banana 2.1",
    "description": "Gemini Nano Banana 2.1.",
    "inputTokenLimit": 65536,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/gemini-3.5-flash",
    "version": "3.5-flash-05-2026",
    "displayName": "Gemini 3.5 Flash",
    "description": "Gemini 3.5 Flash",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.5-flash-lite",
    "version": "3.5-flash-lite-07-2026",
    "displayName": "Gemini 3.5 Flash Lite",
    "description": "Gemini 3.5 Flash Lite",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-omni-flash-preview",
    "version": "001",
    "displayName": "Gemini Omni Flash Preview",
    "description": "Gemini Omni Flash Preview",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-omni-1.1-flash",
    "version": "001",
    "displayName": "Gemini Omni 1.1 Flash",
    "description": "Gemini Omni 1.1 Flash ",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.5-transcribe",
    "version": "3.5-transcribe-08-2026",
    "displayName": "Gemini 3.5 Transcribe",
    "description": "Gemini 3.5 Transcribe",
    "inputTokenLimit": 98304,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.6-flash",
    "version": "3.6-flash-07-2026",
    "displayName": "Gemini 3.6 Flash",
    "description": "Gemini 3.6 Flash",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.7-flash",
    "version": "3.7-flash-08-2026",
    "displayName": "Gemini 3.7 Flash",
    "description": "Gemini 3.7 Flash",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.8-flash",
    "version": "3.0",
    "displayName": "Gemini 3.8 Flash",
    "description": "Gemini 3.8 Flash",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-4-argon",
    "version": "3.0",
    "displayName": "Gemini 4 Argon",
    "description": "Gemini 4 Argon",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/lyria-3-clip-preview",
    "version": "lyria-3-clip-preview",
    "displayName": "Lyria 3 Clip Preview",
    "description": "Lyria 3 30s model Preview",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/lyria-3-pro-preview",
    "version": "lyria-3-pro-preview",
    "displayName": "Lyria 3 Pro Preview",
    "description": "Lyria 3 Pro Preview",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/lyria-3.5",
    "version": "3.5",
    "displayName": "Lyria 3.5",
    "description": "Music Generation model",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.1-flash-tts-preview",
    "version": "3.1-flash-tts-preview",
    "displayName": "Gemini 3.1 Flash TTS Preview",
    "description": "Gemini 3.1 Flash TTS Preview",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 16384,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.8-flash-tts",
    "version": "3.8-flash-tts",
    "displayName": "Gemini 3.8 Flash TTS",
    "description": "Gemini 3.8 Flash TTS",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 16384,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.8-flash-lite-tts",
    "version": "3.8-flash-lite-tts",
    "displayName": "Gemini 3.8 Flash Lite TTS",
    "description": "Gemini 3.8 Flash Lite TTS",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 16384,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-robotics-er-2-preview",
    "version": "2-preview",
    "displayName": "Gemini Robotics-ER 2 Preview",
    "description": "Gemini Robotics-ER 2 Preview",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-computer-use-preview-10-2025",
    "version": "Gemini 2.5 Computer Use Preview 10-2025",
    "displayName": "Gemini 2.5 Computer Use Preview 10-2025",
    "description": "Gemini 2.5 Computer Use Preview 10-2025",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/antigravity-preview-05-2026",
    "version": "0.1",
    "displayName": "Antigravity Agent Preview",
    "description": "Preview release of Antigravity Agent (05-2026)",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ]
}

{
    "name": "models/antigravity-preview-09-2026",
    "version": "0.1",
    "displayName": "Antigravity Agent Preview",
    "description": "Preview release of Antigravity Agent (09-2026)",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ]
}

{
    "name": "models/antigravity-preview-latest",
    "version": "Antigravity Agent Preview Latest",
    "displayName": "Antigravity Agent Preview Latest",
    "description": "Latest preview release of Antigravity Agent",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ]
}

{
    "name": "models/deep-research-max-preview-04-2026",
    "version": "deepthink-exp-05-20",
    "displayName": "Deep Research Max Preview (Apr-21-2026)",
    "description": "Preview release (April 21st, 2026) of Deep Research Max",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/deep-research-preview-04-2026",
    "version": "deepthink-exp-05-20",
    "displayName": "Deep Research Preview (Apr-21-2026)",
    "description": "Preview release (April 21th, 2026) of Deep Research",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/deep-research-pro-preview-12-2025",
    "version": "deepthink-exp-05-20",
    "displayName": "Deep Research Pro Preview (Dec-12-2025) [Rerouted]",
    "description": "Deprecated preview agent; automatically rerouting traffic to deep-research-preview-04-2026.",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-embedding-001",
    "version": "001",
    "displayName": "Gemini Embedding 001",
    "description": "Obtain a distributed representation of a text.",
    "inputTokenLimit": 2048,
    "outputTokenLimit": 1,
    "supportedGenerationMethods": [
        "embedContent",
        "countTextTokens",
        "countTokens",
        "asyncBatchEmbedContent"
    ]
}

{
    "name": "models/gemini-embedding-2-preview",
    "version": "2",
    "displayName": "Gemini Embedding 2 Preview",
    "description": "Obtain a distributed representation of multimodal content.",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 1,
    "supportedGenerationMethods": [
        "embedContent",
        "countTextTokens",
        "countTokens",
        "asyncBatchEmbedContent"
    ]
}

{
    "name": "models/gemini-embedding-2",
    "version": "2",
    "displayName": "Gemini Embedding 2",
    "description": "Obtain a distributed representation of multimodal content.",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 1,
    "supportedGenerationMethods": [
        "embedContent",
        "countTextTokens",
        "countTokens",
        "asyncBatchEmbedContent"
    ]
}

{
    "name": "models/aqa",
    "version": "001",
    "displayName": "Model that performs Attributed Question Answering.",
    "description": "Model trained to return answers to questions that are grounded in provided sources, along with estimating answerable probability.",
    "inputTokenLimit": 7168,
    "outputTokenLimit": 1024,
    "supportedGenerationMethods": [
        "generateAnswer"
    ],
    "temperature": 0.200000000000000011102230246251565404236316680908203125,
    "topP": 1,
    "topK": 40
}

{
    "name": "models/gemini-3.5-transcribe-live",
    "version": "3.5-transcribe-live-08-2026",
    "displayName": "Gemini 3.5 Transcribe Live",
    "description": "Gemini 3.5 Transcribe Live",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-2.5-flash-native-audio-latest",
    "version": "Gemini 2.5 Flash Native Audio Latest",
    "displayName": "Gemini 2.5 Flash Native Audio Latest",
    "description": "Latest release of Gemini 2.5 Flash Native Audio",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 8192,
    "supportedGenerationMethods": [
        "countTokens",
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-flash-native-audio-preview-09-2025",
    "version": "gemini-2.5-flash-preview-native-audio-dialog-2025-05-19",
    "displayName": "Gemini 2.5 Flash Native Audio Preview 09-2025",
    "description": "Gemini 2.5 Flash Native Audio Preview 09-2025",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 8192,
    "supportedGenerationMethods": [
        "countTokens",
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-flash-native-audio-preview-12-2025",
    "version": "12-2025",
    "displayName": "Gemini 2.5 Flash Native Audio Preview 12-2025",
    "description": "Gemini 2.5 Flash Native Audio Preview 12-2025",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 8192,
    "supportedGenerationMethods": [
        "countTokens",
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.1-flash-live-preview",
    "version": "3.1-flash-live-03-2026",
    "displayName": "Gemini 3.1 Flash Live Preview",
    "description": "Gemini 3.1 Flash Live Preview",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.8-live",
    "version": "3.1-flash-live-03-2026",
    "displayName": "Gemini 3.8 Live",
    "description": "Gemini 3.8 Live",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.8-live-extended-thinking",
    "version": "3.1-flash-live-03-2026",
    "displayName": "Gemini 3.8 Live Extended Thinking",
    "description": "Gemini 3.8 Live Extended Thinking",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-robotics-er-2-streaming-preview",
    "version": "2-streaming-preview",
    "displayName": "Gemini Robotics-ER 2 Streaming Preview",
    "description": "Gemini Robotics-ER 2 Streaming Preview",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.5-live-translate-preview",
    "version": "3.5-live-translate-06-2026",
    "displayName": "Gemini 3.5 Live Translate Preview",
    "description": "Gemini 3.5 Live Translate Preview",
    "inputTokenLimit": 16384,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/lyria-realtime-exp",
    "version": "lyria-realtime-exp",
    "displayName": "Lyria Realtime Experimental",
    "description": "Lyria Realtime Experimental",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "bidiGenerateMusic"
    ]
}

{
    "name": "models/gemini-2.5-flash",
    "version": "001",
    "displayName": "Gemini 2.5 Flash",
    "description": "Stable version of Gemini 2.5 Flash, our mid-size multimodal model that supports up to 1 million tokens, released in June of 2025.",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-pro",
    "version": "2.5",
    "displayName": "Gemini 2.5 Pro",
    "description": "Stable release (June 17th, 2025) of Gemini 2.5 Pro",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-flash-preview-tts",
    "version": "gemini-2.5-flash-exp-tts-2025-05-19",
    "displayName": "Gemini 2.5 Flash Preview TTS",
    "description": "Gemini 2.5 Flash Preview TTS",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 16384,
    "supportedGenerationMethods": [
        "countTokens",
        "generateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-2.5-pro-preview-tts",
    "version": "gemini-2.5-pro-preview-tts-2025-05-19",
    "displayName": "Gemini 2.5 Pro Preview TTS",
    "description": "Gemini 2.5 Pro Preview TTS",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 16384,
    "supportedGenerationMethods": [
        "countTokens",
        "generateContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemma-4-26b-a4b-it",
    "version": "001",
    "displayName": "Gemma 4 26B A4B IT",
    "description": "Gemma 4 26B A4B IT",
    "inputTokenLimit": 262144,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemma-4-31b-it",
    "version": "001",
    "displayName": "Gemma 4 31B IT",
    "description": "Gemma 4 31B IT",
    "inputTokenLimit": 262144,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-flash-latest",
    "version": "Gemini Flash Latest",
    "displayName": "Gemini Flash Latest",
    "description": "Latest release of Gemini Flash",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-flash-lite-latest",
    "version": "Gemini Flash-Lite Latest",
    "displayName": "Gemini Flash-Lite Latest",
    "description": "Latest release of Gemini Flash-Lite",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-pro-latest",
    "version": "Gemini Pro Latest",
    "displayName": "Gemini Pro Latest",
    "description": "Latest release of Gemini Pro",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-flash-lite",
    "version": "001",
    "displayName": "Gemini 2.5 Flash-Lite",
    "description": "Stable version of Gemini 2.5 Flash-Lite, released in July of 2025",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-flash-image",
    "version": "2.0",
    "displayName": "Nano Banana",
    "description": "Gemini 2.5 Flash Preview Image",
    "inputTokenLimit": 32768,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1
}

{
    "name": "models/gemini-3-flash-preview",
    "version": "3-flash-preview-12-2025",
    "displayName": "Gemini 3 Flash Preview",
    "description": "Gemini 3 Flash Preview",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.1-pro-preview",
    "version": "3.1-pro-preview-01-2026",
    "displayName": "Gemini 3.1 Pro Preview",
    "description": "Gemini 3.1 Pro Preview",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.1-pro-preview-customtools",
    "version": "3.1-pro-preview-01-2026",
    "displayName": "Gemini 3.1 Pro Preview Custom Tools",
    "description": "Gemini 3.1 Pro Preview optimized for custom tool usage",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.1-flash-lite-preview",
    "version": "3.1-flash-lite-preview-03-2026",
    "displayName": "Gemini 3.1 Flash Lite Preview",
    "description": "Gemini 3.1 Flash Lite Preview",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.1-flash-lite",
    "version": "3.1-flash-lite-05-2026",
    "displayName": "Gemini 3.1 Flash Lite",
    "description": "Gemini 3.1 Flash Lite",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3-pro-image-preview",
    "version": "3.0",
    "displayName": "Nano Banana Pro",
    "description": "Gemini 3 Pro Image Preview",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/gemini-3-pro-image",
    "version": "3.0",
    "displayName": "Nano Banana Pro",
    "description": "Gemini 3 Pro Image",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/nano-banana-pro-preview",
    "version": "3.0",
    "displayName": "Nano Banana Pro",
    "description": "Gemini 3 Pro Image Preview",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/gemini-3.1-flash-image-preview",
    "version": "3.0",
    "displayName": "Nano Banana 2",
    "description": "Gemini 3.1 Flash Image Preview.",
    "inputTokenLimit": 65536,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/gemini-3.1-flash-image",
    "version": "3.0",
    "displayName": "Nano Banana 2",
    "description": "Gemini 3.1 Flash Image.",
    "inputTokenLimit": 65536,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/gemini-3.1-flash-lite-image",
    "version": "3.0",
    "displayName": "Nano Banana 2 Lite",
    "description": "Gemini 3.1 Flash Lite Image.",
    "inputTokenLimit": 65536,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/gemini-nano-banana-2.1",
    "version": "3.0",
    "displayName": "Nano Banana 2.1",
    "description": "Gemini Nano Banana 2.1.",
    "inputTokenLimit": 65536,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/gemini-3.5-flash",
    "version": "3.5-flash-05-2026",
    "displayName": "Gemini 3.5 Flash",
    "description": "Gemini 3.5 Flash",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.5-flash-lite",
    "version": "3.5-flash-lite-07-2026",
    "displayName": "Gemini 3.5 Flash Lite",
    "description": "Gemini 3.5 Flash Lite",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-omni-flash-preview",
    "version": "001",
    "displayName": "Gemini Omni Flash Preview",
    "description": "Gemini Omni Flash Preview",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-omni-1.1-flash",
    "version": "001",
    "displayName": "Gemini Omni 1.1 Flash",
    "description": "Gemini Omni 1.1 Flash ",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.5-transcribe",
    "version": "3.5-transcribe-08-2026",
    "displayName": "Gemini 3.5 Transcribe",
    "description": "Gemini 3.5 Transcribe",
    "inputTokenLimit": 98304,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.6-flash",
    "version": "3.6-flash-07-2026",
    "displayName": "Gemini 3.6 Flash",
    "description": "Gemini 3.6 Flash",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.7-flash",
    "version": "3.7-flash-08-2026",
    "displayName": "Gemini 3.7 Flash",
    "description": "Gemini 3.7 Flash",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.8-flash",
    "version": "3.0",
    "displayName": "Gemini 3.8 Flash",
    "description": "Gemini 3.8 Flash",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-4-argon",
    "version": "3.0",
    "displayName": "Gemini 4 Argon",
    "description": "Gemini 4 Argon",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/lyria-3-clip-preview",
    "version": "lyria-3-clip-preview",
    "displayName": "Lyria 3 Clip Preview",
    "description": "Lyria 3 30s model Preview",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/lyria-3-pro-preview",
    "version": "lyria-3-pro-preview",
    "displayName": "Lyria 3 Pro Preview",
    "description": "Lyria 3 Pro Preview",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/lyria-3.5",
    "version": "3.5",
    "displayName": "Lyria 3.5",
    "description": "Music Generation model",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.1-flash-tts-preview",
    "version": "3.1-flash-tts-preview",
    "displayName": "Gemini 3.1 Flash TTS Preview",
    "description": "Gemini 3.1 Flash TTS Preview",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 16384,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.8-flash-tts",
    "version": "3.8-flash-tts",
    "displayName": "Gemini 3.8 Flash TTS",
    "description": "Gemini 3.8 Flash TTS",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 16384,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.8-flash-lite-tts",
    "version": "3.8-flash-lite-tts",
    "displayName": "Gemini 3.8 Flash Lite TTS",
    "description": "Gemini 3.8 Flash Lite TTS",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 16384,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-robotics-er-2-preview",
    "version": "2-preview",
    "displayName": "Gemini Robotics-ER 2 Preview",
    "description": "Gemini Robotics-ER 2 Preview",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-computer-use-preview-10-2025",
    "version": "Gemini 2.5 Computer Use Preview 10-2025",
    "displayName": "Gemini 2.5 Computer Use Preview 10-2025",
    "description": "Gemini 2.5 Computer Use Preview 10-2025",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/antigravity-preview-05-2026",
    "version": "0.1",
    "displayName": "Antigravity Agent Preview",
    "description": "Preview release of Antigravity Agent (05-2026)",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ]
}

{
    "name": "models/antigravity-preview-09-2026",
    "version": "0.1",
    "displayName": "Antigravity Agent Preview",
    "description": "Preview release of Antigravity Agent (09-2026)",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ]
}

{
    "name": "models/antigravity-preview-latest",
    "version": "Antigravity Agent Preview Latest",
    "displayName": "Antigravity Agent Preview Latest",
    "description": "Latest preview release of Antigravity Agent",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ]
}

{
    "name": "models/deep-research-max-preview-04-2026",
    "version": "deepthink-exp-05-20",
    "displayName": "Deep Research Max Preview (Apr-21-2026)",
    "description": "Preview release (April 21st, 2026) of Deep Research Max",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/deep-research-preview-04-2026",
    "version": "deepthink-exp-05-20",
    "displayName": "Deep Research Preview (Apr-21-2026)",
    "description": "Preview release (April 21th, 2026) of Deep Research",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/deep-research-pro-preview-12-2025",
    "version": "deepthink-exp-05-20",
    "displayName": "Deep Research Pro Preview (Dec-12-2025) [Rerouted]",
    "description": "Deprecated preview agent; automatically rerouting traffic to deep-research-preview-04-2026.",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-embedding-001",
    "version": "001",
    "displayName": "Gemini Embedding 001",
    "description": "Obtain a distributed representation of a text.",
    "inputTokenLimit": 2048,
    "outputTokenLimit": 1,
    "supportedGenerationMethods": [
        "embedContent",
        "countTextTokens",
        "countTokens",
        "asyncBatchEmbedContent"
    ]
}

{
    "name": "models/gemini-embedding-2-preview",
    "version": "2",
    "displayName": "Gemini Embedding 2 Preview",
    "description": "Obtain a distributed representation of multimodal content.",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 1,
    "supportedGenerationMethods": [
        "embedContent",
        "countTextTokens",
        "countTokens",
        "asyncBatchEmbedContent"
    ]
}

{
    "name": "models/gemini-embedding-2",
    "version": "2",
    "displayName": "Gemini Embedding 2",
    "description": "Obtain a distributed representation of multimodal content.",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 1,
    "supportedGenerationMethods": [
        "embedContent",
        "countTextTokens",
        "countTokens",
        "asyncBatchEmbedContent"
    ]
}

{
    "name": "models/aqa",
    "version": "001",
    "displayName": "Model that performs Attributed Question Answering.",
    "description": "Model trained to return answers to questions that are grounded in provided sources, along with estimating answerable probability.",
    "inputTokenLimit": 7168,
    "outputTokenLimit": 1024,
    "supportedGenerationMethods": [
        "generateAnswer"
    ],
    "temperature": 0.200000000000000011102230246251565404236316680908203125,
    "topP": 1,
    "topK": 40
}

{
    "name": "models/gemini-3.5-transcribe-live",
    "version": "3.5-transcribe-live-08-2026",
    "displayName": "Gemini 3.5 Transcribe Live",
    "description": "Gemini 3.5 Transcribe Live",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-2.5-flash-native-audio-latest",
    "version": "Gemini 2.5 Flash Native Audio Latest",
    "displayName": "Gemini 2.5 Flash Native Audio Latest",
    "description": "Latest release of Gemini 2.5 Flash Native Audio",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 8192,
    "supportedGenerationMethods": [
        "countTokens",
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-flash-native-audio-preview-09-2025",
    "version": "gemini-2.5-flash-preview-native-audio-dialog-2025-05-19",
    "displayName": "Gemini 2.5 Flash Native Audio Preview 09-2025",
    "description": "Gemini 2.5 Flash Native Audio Preview 09-2025",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 8192,
    "supportedGenerationMethods": [
        "countTokens",
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-flash-native-audio-preview-12-2025",
    "version": "12-2025",
    "displayName": "Gemini 2.5 Flash Native Audio Preview 12-2025",
    "description": "Gemini 2.5 Flash Native Audio Preview 12-2025",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 8192,
    "supportedGenerationMethods": [
        "countTokens",
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.1-flash-live-preview",
    "version": "3.1-flash-live-03-2026",
    "displayName": "Gemini 3.1 Flash Live Preview",
    "description": "Gemini 3.1 Flash Live Preview",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.8-live",
    "version": "3.1-flash-live-03-2026",
    "displayName": "Gemini 3.8 Live",
    "description": "Gemini 3.8 Live",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.8-live-extended-thinking",
    "version": "3.1-flash-live-03-2026",
    "displayName": "Gemini 3.8 Live Extended Thinking",
    "description": "Gemini 3.8 Live Extended Thinking",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-robotics-er-2-streaming-preview",
    "version": "2-streaming-preview",
    "displayName": "Gemini Robotics-ER 2 Streaming Preview",
    "description": "Gemini Robotics-ER 2 Streaming Preview",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.5-live-translate-preview",
    "version": "3.5-live-translate-06-2026",
    "displayName": "Gemini 3.5 Live Translate Preview",
    "description": "Gemini 3.5 Live Translate Preview",
    "inputTokenLimit": 16384,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/lyria-realtime-exp",
    "version": "lyria-realtime-exp",
    "displayName": "Lyria Realtime Experimental",
    "description": "Lyria Realtime Experimental",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "bidiGenerateMusic"
    ]
}

{
    "name": "models/gemini-2.5-flash",
    "version": "001",
    "displayName": "Gemini 2.5 Flash",
    "description": "Stable version of Gemini 2.5 Flash, our mid-size multimodal model that supports up to 1 million tokens, released in June of 2025.",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-pro",
    "version": "2.5",
    "displayName": "Gemini 2.5 Pro",
    "description": "Stable release (June 17th, 2025) of Gemini 2.5 Pro",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-flash-preview-tts",
    "version": "gemini-2.5-flash-exp-tts-2025-05-19",
    "displayName": "Gemini 2.5 Flash Preview TTS",
    "description": "Gemini 2.5 Flash Preview TTS",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 16384,
    "supportedGenerationMethods": [
        "countTokens",
        "generateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-2.5-pro-preview-tts",
    "version": "gemini-2.5-pro-preview-tts-2025-05-19",
    "displayName": "Gemini 2.5 Pro Preview TTS",
    "description": "Gemini 2.5 Pro Preview TTS",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 16384,
    "supportedGenerationMethods": [
        "countTokens",
        "generateContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemma-4-26b-a4b-it",
    "version": "001",
    "displayName": "Gemma 4 26B A4B IT",
    "description": "Gemma 4 26B A4B IT",
    "inputTokenLimit": 262144,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemma-4-31b-it",
    "version": "001",
    "displayName": "Gemma 4 31B IT",
    "description": "Gemma 4 31B IT",
    "inputTokenLimit": 262144,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-flash-latest",
    "version": "Gemini Flash Latest",
    "displayName": "Gemini Flash Latest",
    "description": "Latest release of Gemini Flash",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-flash-lite-latest",
    "version": "Gemini Flash-Lite Latest",
    "displayName": "Gemini Flash-Lite Latest",
    "description": "Latest release of Gemini Flash-Lite",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-pro-latest",
    "version": "Gemini Pro Latest",
    "displayName": "Gemini Pro Latest",
    "description": "Latest release of Gemini Pro",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-flash-lite",
    "version": "001",
    "displayName": "Gemini 2.5 Flash-Lite",
    "description": "Stable version of Gemini 2.5 Flash-Lite, released in July of 2025",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-flash-image",
    "version": "2.0",
    "displayName": "Nano Banana",
    "description": "Gemini 2.5 Flash Preview Image",
    "inputTokenLimit": 32768,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1
}

{
    "name": "models/gemini-3-flash-preview",
    "version": "3-flash-preview-12-2025",
    "displayName": "Gemini 3 Flash Preview",
    "description": "Gemini 3 Flash Preview",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.1-pro-preview",
    "version": "3.1-pro-preview-01-2026",
    "displayName": "Gemini 3.1 Pro Preview",
    "description": "Gemini 3.1 Pro Preview",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.1-pro-preview-customtools",
    "version": "3.1-pro-preview-01-2026",
    "displayName": "Gemini 3.1 Pro Preview Custom Tools",
    "description": "Gemini 3.1 Pro Preview optimized for custom tool usage",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.1-flash-lite-preview",
    "version": "3.1-flash-lite-preview-03-2026",
    "displayName": "Gemini 3.1 Flash Lite Preview",
    "description": "Gemini 3.1 Flash Lite Preview",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.1-flash-lite",
    "version": "3.1-flash-lite-05-2026",
    "displayName": "Gemini 3.1 Flash Lite",
    "description": "Gemini 3.1 Flash Lite",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3-pro-image-preview",
    "version": "3.0",
    "displayName": "Nano Banana Pro",
    "description": "Gemini 3 Pro Image Preview",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/gemini-3-pro-image",
    "version": "3.0",
    "displayName": "Nano Banana Pro",
    "description": "Gemini 3 Pro Image",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/nano-banana-pro-preview",
    "version": "3.0",
    "displayName": "Nano Banana Pro",
    "description": "Gemini 3 Pro Image Preview",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/gemini-3.1-flash-image-preview",
    "version": "3.0",
    "displayName": "Nano Banana 2",
    "description": "Gemini 3.1 Flash Image Preview.",
    "inputTokenLimit": 65536,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/gemini-3.1-flash-image",
    "version": "3.0",
    "displayName": "Nano Banana 2",
    "description": "Gemini 3.1 Flash Image.",
    "inputTokenLimit": 65536,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/gemini-3.1-flash-lite-image",
    "version": "3.0",
    "displayName": "Nano Banana 2 Lite",
    "description": "Gemini 3.1 Flash Lite Image.",
    "inputTokenLimit": 65536,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/gemini-nano-banana-2.1",
    "version": "3.0",
    "displayName": "Nano Banana 2.1",
    "description": "Gemini Nano Banana 2.1.",
    "inputTokenLimit": 65536,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 1,
    "thinking": true
}

{
    "name": "models/gemini-3.5-flash",
    "version": "3.5-flash-05-2026",
    "displayName": "Gemini 3.5 Flash",
    "description": "Gemini 3.5 Flash",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.5-flash-lite",
    "version": "3.5-flash-lite-07-2026",
    "displayName": "Gemini 3.5 Flash Lite",
    "description": "Gemini 3.5 Flash Lite",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-omni-flash-preview",
    "version": "001",
    "displayName": "Gemini Omni Flash Preview",
    "description": "Gemini Omni Flash Preview",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-omni-1.1-flash",
    "version": "001",
    "displayName": "Gemini Omni 1.1 Flash",
    "description": "Gemini Omni 1.1 Flash ",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.5-transcribe",
    "version": "3.5-transcribe-08-2026",
    "displayName": "Gemini 3.5 Transcribe",
    "description": "Gemini 3.5 Transcribe",
    "inputTokenLimit": 98304,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.6-flash",
    "version": "3.6-flash-07-2026",
    "displayName": "Gemini 3.6 Flash",
    "description": "Gemini 3.6 Flash",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.7-flash",
    "version": "3.7-flash-08-2026",
    "displayName": "Gemini 3.7 Flash",
    "description": "Gemini 3.7 Flash",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.8-flash",
    "version": "3.0",
    "displayName": "Gemini 3.8 Flash",
    "description": "Gemini 3.8 Flash",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-4-argon",
    "version": "3.0",
    "displayName": "Gemini 4 Argon",
    "description": "Gemini 4 Argon",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/lyria-3-clip-preview",
    "version": "lyria-3-clip-preview",
    "displayName": "Lyria 3 Clip Preview",
    "description": "Lyria 3 30s model Preview",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/lyria-3-pro-preview",
    "version": "lyria-3-pro-preview",
    "displayName": "Lyria 3 Pro Preview",
    "description": "Lyria 3 Pro Preview",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/lyria-3.5",
    "version": "3.5",
    "displayName": "Lyria 3.5",
    "description": "Music Generation model",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.1-flash-tts-preview",
    "version": "3.1-flash-tts-preview",
    "displayName": "Gemini 3.1 Flash TTS Preview",
    "description": "Gemini 3.1 Flash TTS Preview",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 16384,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.8-flash-tts",
    "version": "3.8-flash-tts",
    "displayName": "Gemini 3.8 Flash TTS",
    "description": "Gemini 3.8 Flash TTS",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 16384,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.8-flash-lite-tts",
    "version": "3.8-flash-lite-tts",
    "displayName": "Gemini 3.8 Flash Lite TTS",
    "description": "Gemini 3.8 Flash Lite TTS",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 16384,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-robotics-er-2-preview",
    "version": "2-preview",
    "displayName": "Gemini Robotics-ER 2 Preview",
    "description": "Gemini Robotics-ER 2 Preview",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens",
        "createCachedContent",
        "batchGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-computer-use-preview-10-2025",
    "version": "Gemini 2.5 Computer Use Preview 10-2025",
    "displayName": "Gemini 2.5 Computer Use Preview 10-2025",
    "description": "Gemini 2.5 Computer Use Preview 10-2025",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/antigravity-preview-05-2026",
    "version": "0.1",
    "displayName": "Antigravity Agent Preview",
    "description": "Preview release of Antigravity Agent (05-2026)",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ]
}

{
    "name": "models/antigravity-preview-09-2026",
    "version": "0.1",
    "displayName": "Antigravity Agent Preview",
    "description": "Preview release of Antigravity Agent (09-2026)",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ]
}

{
    "name": "models/antigravity-preview-latest",
    "version": "Antigravity Agent Preview Latest",
    "displayName": "Antigravity Agent Preview Latest",
    "description": "Latest preview release of Antigravity Agent",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ]
}

{
    "name": "models/deep-research-max-preview-04-2026",
    "version": "deepthink-exp-05-20",
    "displayName": "Deep Research Max Preview (Apr-21-2026)",
    "description": "Preview release (April 21st, 2026) of Deep Research Max",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/deep-research-preview-04-2026",
    "version": "deepthink-exp-05-20",
    "displayName": "Deep Research Preview (Apr-21-2026)",
    "description": "Preview release (April 21th, 2026) of Deep Research",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/deep-research-pro-preview-12-2025",
    "version": "deepthink-exp-05-20",
    "displayName": "Deep Research Pro Preview (Dec-12-2025) [Rerouted]",
    "description": "Deprecated preview agent; automatically rerouting traffic to deep-research-preview-04-2026.",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-embedding-001",
    "version": "001",
    "displayName": "Gemini Embedding 001",
    "description": "Obtain a distributed representation of a text.",
    "inputTokenLimit": 2048,
    "outputTokenLimit": 1,
    "supportedGenerationMethods": [
        "embedContent",
        "countTextTokens",
        "countTokens",
        "asyncBatchEmbedContent"
    ]
}

{
    "name": "models/gemini-embedding-2-preview",
    "version": "2",
    "displayName": "Gemini Embedding 2 Preview",
    "description": "Obtain a distributed representation of multimodal content.",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 1,
    "supportedGenerationMethods": [
        "embedContent",
        "countTextTokens",
        "countTokens",
        "asyncBatchEmbedContent"
    ]
}

{
    "name": "models/gemini-embedding-2",
    "version": "2",
    "displayName": "Gemini Embedding 2",
    "description": "Obtain a distributed representation of multimodal content.",
    "inputTokenLimit": 8192,
    "outputTokenLimit": 1,
    "supportedGenerationMethods": [
        "embedContent",
        "countTextTokens",
        "countTokens",
        "asyncBatchEmbedContent"
    ]
}

{
    "name": "models/aqa",
    "version": "001",
    "displayName": "Model that performs Attributed Question Answering.",
    "description": "Model trained to return answers to questions that are grounded in provided sources, along with estimating answerable probability.",
    "inputTokenLimit": 7168,
    "outputTokenLimit": 1024,
    "supportedGenerationMethods": [
        "generateAnswer"
    ],
    "temperature": 0.200000000000000011102230246251565404236316680908203125,
    "topP": 1,
    "topK": 40
}

{
    "name": "models/gemini-3.5-transcribe-live",
    "version": "3.5-transcribe-live-08-2026",
    "displayName": "Gemini 3.5 Transcribe Live",
    "description": "Gemini 3.5 Transcribe Live",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-2.5-flash-native-audio-latest",
    "version": "Gemini 2.5 Flash Native Audio Latest",
    "displayName": "Gemini 2.5 Flash Native Audio Latest",
    "description": "Latest release of Gemini 2.5 Flash Native Audio",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 8192,
    "supportedGenerationMethods": [
        "countTokens",
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-flash-native-audio-preview-09-2025",
    "version": "gemini-2.5-flash-preview-native-audio-dialog-2025-05-19",
    "displayName": "Gemini 2.5 Flash Native Audio Preview 09-2025",
    "description": "Gemini 2.5 Flash Native Audio Preview 09-2025",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 8192,
    "supportedGenerationMethods": [
        "countTokens",
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-2.5-flash-native-audio-preview-12-2025",
    "version": "12-2025",
    "displayName": "Gemini 2.5 Flash Native Audio Preview 12-2025",
    "description": "Gemini 2.5 Flash Native Audio Preview 12-2025",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 8192,
    "supportedGenerationMethods": [
        "countTokens",
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-3.1-flash-live-preview",
    "version": "3.1-flash-live-03-2026",
    "displayName": "Gemini 3.1 Flash Live Preview",
    "description": "Gemini 3.1 Flash Live Preview",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.8-live",
    "version": "3.1-flash-live-03-2026",
    "displayName": "Gemini 3.8 Live",
    "description": "Gemini 3.8 Live",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.8-live-extended-thinking",
    "version": "3.1-flash-live-03-2026",
    "displayName": "Gemini 3.8 Live Extended Thinking",
    "description": "Gemini 3.8 Live Extended Thinking",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2,
    "thinking": true
}

{
    "name": "models/gemini-robotics-er-2-streaming-preview",
    "version": "2-streaming-preview",
    "displayName": "Gemini Robotics-ER 2 Streaming Preview",
    "description": "Gemini Robotics-ER 2 Streaming Preview",
    "inputTokenLimit": 131072,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/gemini-3.5-live-translate-preview",
    "version": "3.5-live-translate-06-2026",
    "displayName": "Gemini 3.5 Live Translate Preview",
    "description": "Gemini 3.5 Live Translate Preview",
    "inputTokenLimit": 16384,
    "outputTokenLimit": 32768,
    "supportedGenerationMethods": [
        "bidiGenerateContent"
    ],
    "temperature": 1,
    "topP": 0.9499999999999999555910790149937383830547332763671875,
    "topK": 64,
    "maxTemperature": 2
}

{
    "name": "models/lyria-realtime-exp",
    "version": "lyria-realtime-exp",
    "displayName": "Lyria Realtime Experimental",
    "description": "Lyria Realtime Experimental",
    "inputTokenLimit": 1048576,
    "outputTokenLimit": 65536,
    "supportedGenerationMethods": [
        "bidiGenerateMusic"
    ]
}

{
    "created": 1730000000,
    "id": "gpt-5.5",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "gpt-5.6-luna",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "gpt-5.6-sol",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "grok-4.5",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "glm-5.2",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "gemma-2-2b",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "qwen3.8-max",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "qwen3.7-max",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "claude-opus-4.6",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "kimi-k2.6",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "muse-spark-1.1",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "claude-opus-5",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "claude-fable-5",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "kimi-k3",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "deepseek-v4-pro-0813",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "gemini-3.6-flash",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "gemini-3.1-pro",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "seed-2.1-turbo",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "deepseek-v4-pro-max",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "gpt-5.6-terra",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "claude-mythos-preview",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "gemini-3.7-flash",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "grok-4.6",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "qwen3.8-27b",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "claude-fable-5.1",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "deepseek-v4-flash-0731",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "seed-2.1-pro",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "gpt-5.5-pro",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "claude-opus-4.7",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "claude-opus-5.5",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "claude-opus-4.8",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "glm-5.3",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "claude-sonnet-5",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "muse-spark-1.1",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "claude-opus-5",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "claude-fable-5",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "kimi-k3",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "deepseek-v4-pro-0813",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "gemini-3.6-flash",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "gemini-3.1-pro",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "seed-2.1-turbo",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "deepseek-v4-pro-max",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "gpt-5.6-terra",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "claude-mythos-preview",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "gemini-3.7-flash",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "grok-4.6",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "qwen3.8-27b",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "claude-fable-5.1",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "deepseek-v4-flash-0731",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "seed-2.1-pro",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "gpt-5.5-pro",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "claude-opus-4.7",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "claude-opus-5.5",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "claude-opus-4.8",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "glm-5.3",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "claude-sonnet-5",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "gpt-5.5",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "gpt-5.6-luna",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "gpt-5.6-sol",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "grok-4.5",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "glm-5.2",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "gemma-2-2b",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "qwen3.8-max",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "qwen3.7-max",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "claude-opus-4.6",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1730000000,
    "id": "kimi-k2.6",
    "object": "model",
    "owned_by": "cleanapis"
}

{
    "created": 1626777600,
    "id": "claude-opus-5-5",
    "object": "model",
    "owned_by": "aero-claude",
    "supported_endpoint_types": [
        "anthropic"
    ]
}

{
    "created": 1626777600,
    "id": "claude-opus-5",
    "object": "model",
    "owned_by": "aero-claude",
    "supported_endpoint_types": [
        "anthropic"
    ]
}

{
    "created": 1626777600,
    "id": "claude-opus-4-8",
    "object": "model",
    "owned_by": "aero-claude",
    "supported_endpoint_types": [
        "anthropic"
    ]
}

{
    "created": 1626777600,
    "id": "claude-opus-4-7",
    "object": "model",
    "owned_by": "aero-claude",
    "supported_endpoint_types": [
        "anthropic"
    ]
}

{
    "created": 1626777600,
    "id": "claude-opus-4-6",
    "object": "model",
    "owned_by": "aero-claude",
    "supported_endpoint_types": [
        "anthropic"
    ]
}

{
    "created": 1626777600,
    "id": "claude-opus-4-5-20251101",
    "object": "model",
    "owned_by": "aero-claude",
    "supported_endpoint_types": [
        "anthropic"
    ]
}

{
    "created": 1626777600,
    "id": "claude-sonnet-5-5",
    "object": "model",
    "owned_by": "aero-claude",
    "supported_endpoint_types": [
        "anthropic"
    ]
}

{
    "created": 1626777600,
    "id": "claude-sonnet-5",
    "object": "model",
    "owned_by": "aero-claude",
    "supported_endpoint_types": [
        "anthropic"
    ]
}

{
    "created": 1626777600,
    "id": "claude-sonnet-4-6",
    "object": "model",
    "owned_by": "aero-claude",
    "supported_endpoint_types": [
        "anthropic"
    ]
}

{
    "id": "apertus-70b",
    "object": "model",
    "created": 1677610602,
    "owned_by": "openai"
}

{
    "id": "brick-complexity-pro",
    "object": "model",
    "created": 1677610602,
    "owned_by": "openai"
}

{
    "id": "brick-v1-beta",
    "object": "model",
    "created": 1677610602,
    "owned_by": "openai"
}

{
    "id": "clef-flash",
    "object": "model",
    "created": 1677610602,
    "owned_by": "openai"
}

{
    "id": "deepseek-ocr-2",
    "object": "model",
    "created": 1677610602,
    "owned_by": "openai"
}

{
    "id": "faster-whisper-large-v3",
    "object": "model",
    "created": 1677610602,
    "owned_by": "openai"
}

{
    "id": "gemma4-31b",
    "object": "model",
    "created": 1677610602,
    "owned_by": "openai"
}

{
    "id": "glm5.2",
    "object": "model",
    "created": 1677610602,
    "owned_by": "openai"
}

{
    "id": "gpt-oss-120b",
    "object": "model",
    "created": 1677610602,
    "owned_by": "openai"
}

{
    "id": "gpt-oss-20b",
    "object": "model",
    "created": 1677610602,
    "owned_by": "openai"
}

{
    "id": "mistral-small-4-119b",
    "object": "model",
    "created": 1677610602,
    "owned_by": "openai"
}

{
    "id": "qwen3.5-122b",
    "object": "model",
    "created": 1677610602,
    "owned_by": "openai"
}

{
    "id": "qwen3.5-9b",
    "object": "model",
    "created": 1677610602,
    "owned_by": "openai"
}

{
    "id": "qwen3.8-27b",
    "object": "model",
    "created": 1677610602,
    "owned_by": "openai"
}

{
    "id": "Qwen-Image",
    "object": "model",
    "created": 1677610602,
    "owned_by": "openai"
}

{
    "id": "Qwen3-Embedding-8B",
    "object": "model",
    "created": 1677610602,
    "owned_by": "openai"
}

{
    "id": "Qwen3-Reranker-4B",
    "object": "model",
    "created": 1677610602,
    "owned_by": "openai"
}

{
    "context_length": 512000,
    "endpoints": [
        "chat"
    ],
    "id": "agnes-2-5-flash:free",
    "modalities": {
        "input": [
            "text",
            "image",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "agnes-2-5-flash:free",
    "object": "model",
    "owned_by": "agnes",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": true,
        "input": null,
        "output": null,
        "unit": "micro_idr_per_1m_tokens"
    },
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "tool_call": true
}

{
    "context_length": 512000,
    "endpoints": [
        "chat"
    ],
    "id": "agnes-3-0-flash:free",
    "modalities": {
        "input": [
            "text",
            "image",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "agnes-3-0-flash:free",
    "object": "model",
    "owned_by": "agnes",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": true,
        "input": null,
        "output": null,
        "unit": "micro_idr_per_1m_tokens"
    },
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "tool_call": true
}

{
    "endpoints": [
        "images"
    ],
    "id": "agnes-image-2-0-flash:free",
    "modalities": {
        "input": [
            "text",
            "image"
        ],
        "output": [
            "image"
        ]
    },
    "name": "Agnes Image 2.0 Flash",
    "object": "model",
    "owned_by": "agnes",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": true,
        "input": null,
        "output": null,
        "unit": "micro_idr_per_1m_tokens"
    },
    "reasoning_toggle": false,
    "sunset_at": null
}

{
    "endpoints": [
        "images"
    ],
    "id": "agnes-image-2-1-flash:free",
    "modalities": {
        "input": [
            "text",
            "image"
        ],
        "output": [
            "image"
        ]
    },
    "name": "Agnes Image 2.1 Flash",
    "object": "model",
    "owned_by": "agnes",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": true,
        "input": null,
        "output": null,
        "unit": "micro_idr_per_1m_tokens"
    },
    "reasoning_toggle": false,
    "sunset_at": null
}

{
    "endpoints": [
        "images"
    ],
    "id": "agnes-image-2-5-flash:free",
    "modalities": {
        "input": [
            "text",
            "image"
        ],
        "output": [
            "image"
        ]
    },
    "name": "Agnes Image 2.5 Flash",
    "object": "model",
    "owned_by": "agnes",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": true,
        "input": null,
        "output": null,
        "unit": "micro_idr_per_1m_tokens"
    },
    "reasoning_toggle": false,
    "sunset_at": null
}

{
    "context_length": 262144,
    "endpoints": [
        "chat"
    ],
    "id": "beam-1-0:free",
    "modalities": {
        "input": [
            "text",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "Beam 1.0",
    "object": "model",
    "owned_by": "reflection",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": true,
        "input": null,
        "output": null,
        "unit": "micro_idr_per_1m_tokens"
    },
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning_toggle": false,
    "sunset_at": null
}

{
    "context_length": 1000000,
    "endpoints": [
        "chat"
    ],
    "id": "claude-fable-5",
    "max_output_tokens": 128000,
    "modalities": {
        "input": [
            "text",
            "image",
            "pdf",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "claude-fable-5",
    "object": "model",
    "owned_by": "anthropic",
    "pricing": {
        "cache_read": 21000000000,
        "cache_write": 260000000000,
        "currency": "IDR",
        "free": false,
        "input": 210000000000,
        "output": 1000000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 210000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 1000000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 21000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_write",
            "endpoint": "chat",
            "micro_idr": 260000000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "tool_call": true
}

{
    "context_length": 1000000,
    "endpoints": [
        "chat"
    ],
    "id": "claude-haiku-5-5",
    "max_output_tokens": 128000,
    "modalities": {
        "input": [
            "text",
            "image",
            "pdf",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "claude-haiku-5-5",
    "object": "model",
    "owned_by": "anthropic",
    "pricing": {
        "cache_read": 250000000,
        "cache_write": 2500000000,
        "currency": "IDR",
        "free": false,
        "input": 2500000000,
        "output": 12500000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 2500000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 12500000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 250000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_write",
            "endpoint": "chat",
            "micro_idr": 2500000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "tool_call": true
}

{
    "context_length": 1000000,
    "endpoints": [
        "chat"
    ],
    "id": "claude-opus-4-7",
    "max_output_tokens": 128000,
    "modalities": {
        "input": [
            "text",
            "image",
            "pdf",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "claude-opus-4-7",
    "object": "model",
    "owned_by": "anthropic",
    "pricing": {
        "cache_read": 10000000000,
        "cache_write": 130000000000,
        "currency": "IDR",
        "free": false,
        "input": 100000000000,
        "output": 520000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 100000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 520000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 10000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_write",
            "endpoint": "chat",
            "micro_idr": 130000000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "tool_call": true
}

{
    "context_length": 1000000,
    "endpoints": [
        "chat"
    ],
    "id": "claude-opus-4-8",
    "max_output_tokens": 128000,
    "modalities": {
        "input": [
            "text",
            "image",
            "pdf",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "claude-opus-4-8",
    "object": "model",
    "owned_by": "anthropic",
    "pricing": {
        "cache_read": 10000000000,
        "cache_write": 130000000000,
        "currency": "IDR",
        "free": false,
        "input": 100000000000,
        "output": 520000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 100000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 520000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 10000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_write",
            "endpoint": "chat",
            "micro_idr": 130000000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "tool_call": true
}

{
    "context_length": 1000000,
    "endpoints": [
        "chat"
    ],
    "id": "claude-opus-5",
    "max_output_tokens": 128000,
    "modalities": {
        "input": [
            "text",
            "image",
            "pdf",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "claude-opus-5",
    "object": "model",
    "owned_by": "anthropic",
    "pricing": {
        "cache_read": 40000000000,
        "cache_write": 100000000000,
        "currency": "IDR",
        "free": false,
        "input": 100000000000,
        "output": 500000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 100000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 500000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 40000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_write",
            "endpoint": "chat",
            "micro_idr": 100000000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "tool_call": true
}

{
    "context_length": 1000000,
    "endpoints": [
        "chat"
    ],
    "id": "claude-opus-5-5",
    "max_output_tokens": 128000,
    "modalities": {
        "input": [
            "text",
            "image",
            "pdf",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "claude-opus-5-5",
    "object": "model",
    "owned_by": "anthropic",
    "pricing": {
        "cache_read": 8000000000,
        "cache_write": 100000000000,
        "currency": "IDR",
        "free": false,
        "input": 80000000000,
        "output": 400000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 80000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 400000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 8000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_write",
            "endpoint": "chat",
            "micro_idr": 100000000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "tool_call": true
}

{
    "context_length": 1000000,
    "endpoints": [
        "chat"
    ],
    "id": "claude-sonnet-4-6",
    "max_output_tokens": 128000,
    "modalities": {
        "input": [
            "text",
            "image",
            "pdf",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "claude-sonnet-4-6",
    "object": "model",
    "owned_by": "anthropic",
    "pricing": {
        "cache_read": 6300000000,
        "cache_write": 78000000000,
        "currency": "IDR",
        "free": false,
        "input": 63000000000,
        "output": 310000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 63000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 310000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 6300000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_write",
            "endpoint": "chat",
            "micro_idr": 78000000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "low",
        "medium",
        "high",
        "max"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "low",
        "medium",
        "high",
        "max"
    ],
    "tool_call": true
}

{
    "context_length": 1000000,
    "endpoints": [
        "chat"
    ],
    "id": "claude-sonnet-5",
    "max_output_tokens": 128000,
    "modalities": {
        "input": [
            "text",
            "image",
            "pdf",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "claude-sonnet-5",
    "object": "model",
    "owned_by": "anthropic",
    "pricing": {
        "cache_read": 10000000000,
        "cache_write": 30000000000,
        "currency": "IDR",
        "free": false,
        "input": 25000000000,
        "output": 125000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 25000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 125000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 10000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_write",
            "endpoint": "chat",
            "micro_idr": 30000000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "tool_call": true
}

{
    "context_length": 1000000,
    "endpoints": [
        "chat"
    ],
    "id": "claude-sonnet-5-5",
    "max_output_tokens": 128000,
    "modalities": {
        "input": [
            "text",
            "image",
            "pdf",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "claude-sonnet-5-5",
    "object": "model",
    "owned_by": "anthropic",
    "pricing": {
        "cache_read": 15000000000,
        "cache_write": 50000000000,
        "currency": "IDR",
        "free": false,
        "input": 40000000000,
        "output": 200000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 40000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 200000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 15000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_write",
            "endpoint": "chat",
            "micro_idr": 50000000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "tool_call": true
}

{
    "context_length": 1000000,
    "endpoints": [
        "chat"
    ],
    "id": "deepseek-v4-1-flash",
    "max_output_tokens": 384000,
    "modalities": {
        "input": [
            "text",
            "image",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "deepseek-v4-1-flash",
    "object": "model",
    "owned_by": "deepseek",
    "pricing": {
        "cache_read": 65000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 2750000000,
        "output": 5500000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 65000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 2750000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 5500000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "none",
        "low",
        "high",
        "max"
    ],
    "reasoning_toggle": true,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "none",
        "low",
        "high",
        "max"
    ],
    "tool_call": true
}

{
    "context_length": 1000000,
    "endpoints": [
        "chat"
    ],
    "id": "deepseek-v4-flash",
    "max_output_tokens": 384000,
    "modalities": {
        "input": [
            "text",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "deepseek-v4-flash",
    "object": "model",
    "owned_by": "deepseek",
    "pricing": {
        "cache_read": 65000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 2750000000,
        "output": 5500000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 65000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 2750000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 5500000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "low",
        "high",
        "max"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "low",
        "high",
        "max"
    ],
    "tool_call": true
}

{
    "context_length": 1000000,
    "endpoints": [
        "chat"
    ],
    "id": "deepseek-v4-pro",
    "max_output_tokens": 384000,
    "modalities": {
        "input": [
            "text",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "deepseek-v4-pro",
    "object": "model",
    "owned_by": "deepseek",
    "pricing": {
        "cache_read": 100000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 10000000000,
        "output": 20000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 10000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 20000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 100000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "low",
        "high",
        "max"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "low",
        "high",
        "max"
    ],
    "tool_call": true
}

{
    "context_length": 512000,
    "endpoints": [
        "chat"
    ],
    "id": "dots-3-note-preview:free",
    "max_output_tokens": 460800,
    "modalities": {
        "input": [
            "text",
            "image",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "dots-3-note-preview:free",
    "object": "model",
    "owned_by": "dots-studio",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": true,
        "input": null,
        "output": null,
        "unit": "micro_idr_per_1m_tokens"
    },
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_toggle": false,
    "sunset_at": null,
    "tool_call": true
}

{
    "context_length": 262144,
    "endpoints": [
        "chat"
    ],
    "id": "flint-v1-0:free",
    "max_output_tokens": 235929,
    "modalities": {
        "input": [
            "text",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "Flint 1.0",
    "object": "model",
    "owned_by": "recursive",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": true,
        "input": null,
        "output": null,
        "unit": "micro_idr_per_1m_tokens"
    },
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_toggle": false,
    "sunset_at": null,
    "tool_call": true
}

{
    "context_length": 1048576,
    "endpoints": [
        "chat"
    ],
    "id": "gemini-3-1-flash-lite",
    "max_output_tokens": 65536,
    "modalities": {
        "input": [
            "text",
            "image",
            "video",
            "audio",
            "pdf",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "gemini-3-1-flash-lite",
    "object": "model",
    "owned_by": "google",
    "pricing": {
        "cache_read": 500000000,
        "cache_write": 1500000000,
        "currency": "IDR",
        "free": false,
        "input": 5000000000,
        "output": 30000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 5000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 30000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 500000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_write",
            "endpoint": "chat",
            "micro_idr": 1500000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "minimal",
        "low",
        "medium",
        "high"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "minimal",
        "low",
        "medium",
        "high"
    ],
    "tool_call": true
}

{
    "endpoints": [
        "audio_speech"
    ],
    "formats": [
        "mp3"
    ],
    "id": "gemini-3-1-flash-tts",
    "modalities": {
        "input": [
            "text"
        ],
        "output": [
            "audio"
        ]
    },
    "name": "Gemini 3.1 Flash TTS",
    "object": "model",
    "owned_by": "google",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 0,
        "output": 0,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "output_audio",
            "endpoint": "audio_speech",
            "micro_idr": 250000000,
            "unit": "1k_chars",
            "variant": null
        }
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "voices": [
        "Achernar",
        "Achird",
        "Algenib",
        "Algieba",
        "Alnilam",
        "Aoede",
        "Autonoe",
        "Callirrhoe",
        "Charon",
        "Despina",
        "Enceladus",
        "Erinome",
        "Fenrir",
        "Gacrux",
        "Iapetus",
        "Kore",
        "Laomedeia",
        "Leda",
        "Orus",
        "Puck",
        "Pulcherrima",
        "Rasalgethi",
        "Sadachbia",
        "Sadaltager",
        "Schedar",
        "Sulafat",
        "Umbriel",
        "Vindemiatrix",
        "Zephyr",
        "Zubenelgenubi"
    ]
}

{
    "context_length": 1048576,
    "endpoints": [
        "chat"
    ],
    "id": "gemini-3-1-pro",
    "max_output_tokens": 65536,
    "modalities": {
        "input": [
            "text",
            "image",
            "video",
            "audio",
            "pdf",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "gemini-3-1-pro",
    "object": "model",
    "owned_by": "google",
    "pricing": {
        "cache_read": 2100000000,
        "cache_write": 3900000000,
        "currency": "IDR",
        "free": false,
        "input": 21000000000,
        "output": 125000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 21000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 125000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 2100000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_write",
            "endpoint": "chat",
            "micro_idr": 3900000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "low",
        "medium",
        "high"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "low",
        "medium",
        "high"
    ],
    "tool_call": true
}

{
    "context_length": 1048576,
    "endpoints": [
        "chat"
    ],
    "id": "gemini-3-8-flash",
    "max_output_tokens": 65536,
    "modalities": {
        "input": [
            "text",
            "image",
            "video",
            "audio",
            "pdf",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "gemini-3-8-flash",
    "object": "model",
    "owned_by": "google",
    "pricing": {
        "cache_read": 600000000,
        "cache_write": 300000000,
        "currency": "IDR",
        "free": false,
        "input": 6000000000,
        "output": 30000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 6000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 30000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 600000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_write",
            "endpoint": "chat",
            "micro_idr": 300000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "low",
        "medium",
        "high"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "low",
        "medium",
        "high"
    ],
    "tool_call": true
}

{
    "endpoints": [
        "videos"
    ],
    "id": "gemini-omni-flash",
    "modalities": {
        "input": [
            "image",
            "video"
        ],
        "output": [
            "video"
        ]
    },
    "name": "Gemini Omni Flash",
    "object": "model",
    "owned_by": "google",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 0,
        "output": 0,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "output_video",
            "endpoint": "videos",
            "micro_idr": 350000000,
            "unit": "second",
            "variant": "360p"
        },
        {
            "billable": "output_video",
            "endpoint": "videos",
            "micro_idr": 750000000,
            "unit": "second",
            "variant": "720p"
        },
        {
            "billable": "output_video",
            "endpoint": "videos",
            "micro_idr": 900000000,
            "unit": "second",
            "variant": "1080p"
        }
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "video_durations": [
        4,
        6,
        8,
        10,
        3,
        5,
        7,
        9
    ],
    "video_resolutions": [
        "360p",
        "720p",
        "1080p"
    ]
}

{
    "context_length": 262144,
    "endpoints": [
        "chat"
    ],
    "id": "gemma-4-31b-it",
    "max_output_tokens": 16384,
    "modalities": {
        "input": [
            "image",
            "text",
            "video",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "gemma-4-31b-it",
    "object": "model",
    "owned_by": "google",
    "pricing": {
        "cache_read": 720000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 1800000000,
        "output": 7100000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 1800000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 7100000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 720000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_toggle": true,
    "sunset_at": null,
    "tool_call": true
}

{
    "context_length": 200000,
    "endpoints": [
        "chat"
    ],
    "id": "glm-4-7-flash:free",
    "max_output_tokens": 117964,
    "modalities": {
        "input": [
            "text",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "glm-4-7-flash:free",
    "object": "model",
    "owned_by": "z-ai",
    "pricing": {
        "cache_read": 190000000,
        "cache_write": null,
        "currency": "IDR",
        "free": true,
        "input": 1100000000,
        "output": 7700000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_toggle": true,
    "sunset_at": null,
    "tool_call": true
}

{
    "context_length": 1048576,
    "endpoints": [
        "chat"
    ],
    "id": "glm-5-2",
    "max_output_tokens": 943718,
    "modalities": {
        "input": [
            "text",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "glm-5-2",
    "object": "model",
    "owned_by": "z-ai",
    "pricing": {
        "cache_read": 930000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 5000000000,
        "output": 60000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 5000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 60000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 930000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "none",
        "high",
        "xhigh"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "none",
        "high",
        "xhigh"
    ],
    "tool_call": true
}

{
    "context_length": 1000000,
    "endpoints": [
        "chat"
    ],
    "id": "glm-5-3",
    "max_output_tokens": 128000,
    "modalities": {
        "input": [
            "text",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "glm-5-3",
    "object": "model",
    "owned_by": "z-ai",
    "pricing": {
        "cache_read": 930000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 5000000000,
        "output": 60000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 930000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 5000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 60000000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "low",
        "high",
        "max"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "low",
        "high",
        "max"
    ],
    "tool_call": true
}

{
    "context_length": 1000000,
    "endpoints": [
        "chat"
    ],
    "id": "glm-5-3-flash",
    "max_output_tokens": 128000,
    "modalities": {
        "input": [
            "text",
            "image",
            "video",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "glm-5-3-flash",
    "object": "model",
    "owned_by": "z-ai",
    "pricing": {
        "cache_read": 400000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 2000000000,
        "output": 6000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 400000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 2000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 6000000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "low",
        "high",
        "max"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "low",
        "high",
        "max"
    ],
    "tool_call": true
}

{
    "context_length": 272000,
    "endpoints": [
        "chat"
    ],
    "id": "gpt-5-5",
    "max_output_tokens": 128000,
    "modalities": {
        "input": [
            "text",
            "image",
            "pdf",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "gpt-5-5",
    "object": "model",
    "owned_by": "openai",
    "pricing": {
        "cache_read": 10000000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 100000000000,
        "output": 630000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 100000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 630000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 10000000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "none",
        "low",
        "medium",
        "high",
        "xhigh"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "none",
        "low",
        "medium",
        "high",
        "xhigh"
    ],
    "tool_call": true
}

{
    "context_length": 1050000,
    "endpoints": [
        "chat"
    ],
    "id": "gpt-5-6-luna",
    "max_input_tokens": 922000,
    "max_output_tokens": 128000,
    "modalities": {
        "input": [
            "text",
            "image",
            "pdf",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "gpt-5-6-luna",
    "object": "model",
    "owned_by": "openai",
    "pricing": {
        "cache_read": 350000000,
        "cache_write": 4500000000,
        "currency": "IDR",
        "free": false,
        "input": 3500000000,
        "output": 20000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 350000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_write",
            "endpoint": "chat",
            "micro_idr": 4500000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 3500000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 20000000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "none",
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "none",
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "tool_call": true
}

{
    "context_length": 1050000,
    "endpoints": [
        "chat"
    ],
    "id": "gpt-5-6-sol",
    "max_input_tokens": 922000,
    "max_output_tokens": 128000,
    "modalities": {
        "input": [
            "text",
            "image",
            "pdf",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "gpt-5-6-sol",
    "object": "model",
    "owned_by": "openai",
    "pricing": {
        "cache_read": 20800000000,
        "cache_write": 65000000000,
        "currency": "IDR",
        "free": false,
        "input": 52000000000,
        "output": 310000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 20800000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_write",
            "endpoint": "chat",
            "micro_idr": 65000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 52000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 310000000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "none",
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "none",
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "tool_call": true
}

{
    "context_length": 1050000,
    "endpoints": [
        "chat"
    ],
    "id": "gpt-6-1-sol",
    "max_input_tokens": 922000,
    "max_output_tokens": 128000,
    "modalities": {
        "input": [
            "text",
            "image",
            "pdf",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "gpt-6-1-sol",
    "object": "model",
    "owned_by": "openai",
    "pricing": {
        "cache_read": 4000000000,
        "cache_write": 50000000000,
        "currency": "IDR",
        "free": false,
        "input": 40000000000,
        "output": 200000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 4000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_write",
            "endpoint": "chat",
            "micro_idr": 50000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 40000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 200000000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "tool_call": true
}

{
    "context_length": 1050000,
    "endpoints": [
        "chat"
    ],
    "id": "gpt-6-astra",
    "max_input_tokens": 922000,
    "max_output_tokens": 128000,
    "modalities": {
        "input": [
            "text",
            "image",
            "pdf",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "gpt-6-astra",
    "object": "model",
    "owned_by": "openai",
    "pricing": {
        "cache_read": 20000000000,
        "cache_write": 200000000000,
        "currency": "IDR",
        "free": false,
        "input": 200000000000,
        "output": 1000000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 20000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_write",
            "endpoint": "chat",
            "micro_idr": 200000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 200000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 1000000000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "tool_call": true
}

{
    "context_length": 1050000,
    "endpoints": [
        "chat"
    ],
    "id": "gpt-6-luna",
    "max_input_tokens": 922000,
    "max_output_tokens": 128000,
    "modalities": {
        "input": [
            "text",
            "image",
            "pdf",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "gpt-6-luna",
    "object": "model",
    "owned_by": "openai",
    "pricing": {
        "cache_read": 175000000,
        "cache_write": 2000000000,
        "currency": "IDR",
        "free": false,
        "input": 1750000000,
        "output": 8500000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 175000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_write",
            "endpoint": "chat",
            "micro_idr": 2000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 1750000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 8500000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "none",
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "none",
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "tool_call": true
}

{
    "context_length": 1050000,
    "endpoints": [
        "chat"
    ],
    "id": "gpt-6-sol",
    "max_input_tokens": 922000,
    "max_output_tokens": 128000,
    "modalities": {
        "input": [
            "text",
            "image",
            "pdf",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "gpt-6-sol",
    "object": "model",
    "owned_by": "openai",
    "pricing": {
        "cache_read": 4000000000,
        "cache_write": 40000000000,
        "currency": "IDR",
        "free": false,
        "input": 40000000000,
        "output": 200000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 4000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_write",
            "endpoint": "chat",
            "micro_idr": 40000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 40000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 200000000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "none",
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "none",
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "tool_call": true
}

{
    "endpoints": [
        "images"
    ],
    "id": "gpt-image-2",
    "modalities": {
        "input": [
            "text",
            "image"
        ],
        "output": [
            "image"
        ]
    },
    "name": "gpt-image-2",
    "object": "model",
    "owned_by": "openai",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 0,
        "output": 0,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "output_image",
            "endpoint": "images",
            "micro_idr": 125000000,
            "unit": "image",
            "variant": null
        }
    ],
    "reasoning": false,
    "reasoning_toggle": false,
    "sunset_at": null,
    "tool_call": false
}

{
    "endpoints": [
        "images"
    ],
    "id": "gpt-image-2-5-flare",
    "modalities": {
        "input": [
            "image"
        ],
        "output": [
            "image"
        ]
    },
    "name": "gpt-image-2-5-flare",
    "object": "model",
    "owned_by": "openai",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 0,
        "output": 0,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "output_image",
            "endpoint": "images",
            "micro_idr": 550000000,
            "unit": "image",
            "variant": null
        }
    ],
    "reasoning_toggle": false,
    "sunset_at": null
}

{
    "endpoints": [
        "images"
    ],
    "id": "gpt-image-2-5-sunburst",
    "modalities": {
        "input": [
            "image"
        ],
        "output": [
            "image"
        ]
    },
    "name": "gpt-image-2-5-sunburst",
    "object": "model",
    "owned_by": "openai",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 0,
        "output": 0,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "output_image",
            "endpoint": "images",
            "micro_idr": 750000000,
            "unit": "image",
            "variant": null
        }
    ],
    "reasoning_toggle": false,
    "sunset_at": null
}

{
    "context_length": 128000,
    "endpoints": [
        "chat"
    ],
    "id": "gpt-oss-120b",
    "max_output_tokens": 65536,
    "modalities": {
        "input": [
            "text",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "gpt-oss-120b",
    "object": "model",
    "owned_by": "openai",
    "pricing": {
        "cache_read": 63000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 630000000,
        "output": 3500000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 630000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 3500000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 63000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "low",
        "medium",
        "high"
    ],
    "reasoning_toggle": true,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "low",
        "medium",
        "high"
    ],
    "tool_call": true
}

{
    "context_length": 128000,
    "endpoints": [
        "chat"
    ],
    "id": "gpt-oss-20b",
    "max_output_tokens": 32768,
    "modalities": {
        "input": [
            "text",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "gpt-oss-20b",
    "object": "model",
    "owned_by": "openai",
    "pricing": {
        "cache_read": 65000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 630000000,
        "output": 2700000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 630000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 2700000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 65000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "low",
        "medium",
        "high"
    ],
    "reasoning_toggle": true,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "low",
        "medium",
        "high"
    ],
    "tool_call": true
}

{
    "context_length": 500000,
    "endpoints": [
        "chat"
    ],
    "id": "grok-4-5",
    "max_output_tokens": 450000,
    "modalities": {
        "input": [
            "text",
            "image",
            "pdf",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "grok-4-5",
    "object": "model",
    "owned_by": "x-ai",
    "pricing": {
        "cache_read": 6000000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 40000000000,
        "output": 120000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 40000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 120000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 6000000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "low",
        "medium",
        "high"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "low",
        "medium",
        "high"
    ],
    "tool_call": true,
    "video_extensions": true
}

{
    "context_length": 500000,
    "endpoints": [
        "chat"
    ],
    "id": "grok-4-6",
    "max_output_tokens": 450000,
    "modalities": {
        "input": [
            "text",
            "image",
            "pdf",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "grok-4-6",
    "object": "model",
    "owned_by": "x-ai",
    "pricing": {
        "cache_read": 6000000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 40000000000,
        "output": 120000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 40000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 120000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 6000000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "low",
        "medium",
        "high",
        "xhigh"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "low",
        "medium",
        "high",
        "xhigh"
    ],
    "tool_call": true,
    "video_extensions": true
}

{
    "context_length": 500000,
    "endpoints": [
        "chat"
    ],
    "id": "grok-4-7",
    "max_output_tokens": 450000,
    "modalities": {
        "input": [
            "text",
            "image",
            "pdf",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "grok-4-7",
    "object": "model",
    "owned_by": "x-ai",
    "pricing": {
        "cache_read": 6000000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 40000000000,
        "output": 120000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 40000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 120000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 6000000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "low",
        "medium",
        "high",
        "xhigh"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "low",
        "medium",
        "high",
        "xhigh"
    ],
    "tool_call": true,
    "video_extensions": true
}

{
    "endpoints": [
        "images"
    ],
    "id": "grok-imagine-image",
    "modalities": {
        "input": [
            "text"
        ],
        "output": [
            "image"
        ]
    },
    "name": "grok-imagine-image",
    "object": "model",
    "owned_by": "x-ai",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 0,
        "output": 0,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "output_image",
            "endpoint": "images",
            "micro_idr": 300000000,
            "unit": "image",
            "variant": null
        }
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "video_extensions": true
}

{
    "endpoints": [
        "images"
    ],
    "id": "grok-imagine-image-2-0",
    "modalities": {
        "input": [
            "text"
        ],
        "output": [
            "image"
        ]
    },
    "name": "grok-imagine-image-2-0",
    "object": "model",
    "owned_by": "x-ai",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 0,
        "output": 0,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "output_image",
            "endpoint": "images",
            "micro_idr": 900000000,
            "unit": "image",
            "variant": null
        }
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "video_extensions": true
}

{
    "endpoints": [
        "images"
    ],
    "id": "grok-imagine-image-quality",
    "modalities": {
        "input": [
            "text"
        ],
        "output": [
            "image"
        ]
    },
    "name": "grok-imagine-image-quality",
    "object": "model",
    "owned_by": "x-ai",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 0,
        "output": 0,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "output_image",
            "endpoint": "images",
            "micro_idr": 750000000,
            "unit": "image",
            "variant": null
        }
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "video_extensions": true
}

{
    "endpoints": [
        "images"
    ],
    "id": "hunyuan-image-alpha",
    "modalities": {
        "input": [
            "text",
            "image"
        ],
        "output": [
            "image"
        ]
    },
    "name": "Hunyuan-Image-Alpha",
    "object": "model",
    "owned_by": "tencent",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 0,
        "output": 0,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "output_image",
            "endpoint": "images",
            "micro_idr": 350000000,
            "unit": "image",
            "variant": null
        }
    ],
    "reasoning_toggle": false,
    "sunset_at": null
}

{
    "endpoints": [
        "images"
    ],
    "id": "hunyuan-image-v2.0",
    "modalities": {
        "input": [
            "text",
            "image"
        ],
        "output": [
            "image"
        ]
    },
    "name": "Hunyuan-Image-v2.0",
    "object": "model",
    "owned_by": "tencent",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 0,
        "output": 0,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "output_image",
            "endpoint": "images",
            "micro_idr": 150000000,
            "unit": "image",
            "variant": null
        }
    ],
    "reasoning_toggle": false,
    "sunset_at": null
}

{
    "endpoints": [
        "images"
    ],
    "id": "hunyuan-image-v3.0",
    "modalities": {
        "input": [
            "text"
        ],
        "output": [
            "image"
        ]
    },
    "name": "Hunyuan-Image-v3.0",
    "object": "model",
    "owned_by": "tencent",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 0,
        "output": 0,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "output_image",
            "endpoint": "images",
            "micro_idr": 250000000,
            "unit": "image",
            "variant": null
        }
    ],
    "reasoning_toggle": false,
    "sunset_at": null
}

{
    "endpoints": [
        "images"
    ],
    "id": "hunyuan-image-v3.0-art",
    "modalities": {
        "input": [
            "text"
        ],
        "output": [
            "image"
        ]
    },
    "name": "Hunyuan-Image-v3.0-Art",
    "object": "model",
    "owned_by": "tencent",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 0,
        "output": 0,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "output_image",
            "endpoint": "images",
            "micro_idr": 300000000,
            "unit": "image",
            "variant": null
        }
    ],
    "reasoning_toggle": false,
    "sunset_at": null
}

{
    "endpoints": [
        "videos"
    ],
    "id": "hunyuan-video-art",
    "max_reference_images": 0,
    "modalities": {
        "input": [
            "text"
        ],
        "output": [
            "video"
        ]
    },
    "name": "Hunyuan Video Art, 1280×720",
    "object": "model",
    "owned_by": "tencent",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 0,
        "output": 0,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "output_video",
            "endpoint": "videos",
            "micro_idr": 550000000,
            "unit": "second",
            "variant": "720p"
        }
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "video_durations": [
        5
    ],
    "video_resolutions": [
        "720p"
    ]
}

{
    "context_length": 196608,
    "endpoints": [
        "chat"
    ],
    "id": "hy3",
    "max_output_tokens": 128000,
    "modalities": {
        "input": [
            "text",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "hy3",
    "object": "model",
    "owned_by": "tencent",
    "pricing": {
        "cache_read": 270000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 2700000000,
        "output": 11000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 270000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 2700000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 11000000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "none",
        "low",
        "high"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "none",
        "low",
        "high"
    ],
    "tool_call": true
}

{
    "context_length": 196608,
    "endpoints": [
        "chat"
    ],
    "id": "hy3:free",
    "max_output_tokens": 128000,
    "modalities": {
        "input": [
            "text",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "hy3:free",
    "object": "model",
    "owned_by": "tencent",
    "pricing": {
        "cache_read": 2700000000,
        "cache_write": null,
        "currency": "IDR",
        "free": true,
        "input": 2700000000,
        "output": 11000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "none",
        "low",
        "high"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "none",
        "low",
        "high"
    ],
    "tool_call": true
}

{
    "context_length": 1048576,
    "endpoints": [
        "chat"
    ],
    "id": "hy4-preview",
    "max_output_tokens": 64000,
    "modalities": {
        "input": [
            "text",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "hy4-preview",
    "object": "model",
    "owned_by": "tencent",
    "pricing": {
        "cache_read": 1200000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 12000000000,
        "output": 42000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 12000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 42000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 1200000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "none",
        "low",
        "high"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "none",
        "low",
        "high"
    ],
    "tool_call": true
}

{
    "context_length": 262144,
    "endpoints": [
        "chat"
    ],
    "id": "kimi-k2-6",
    "max_output_tokens": 235929,
    "modalities": {
        "input": [
            "text",
            "image",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "kimi-k2-6",
    "object": "model",
    "owned_by": "moonshotai",
    "pricing": {
        "cache_read": 5000000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 10000000000,
        "output": 50000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 10000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 50000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 5000000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_toggle": false,
    "sunset_at": null,
    "tool_call": true
}

{
    "context_length": 262144,
    "endpoints": [
        "chat"
    ],
    "id": "kimi-k2-7-code",
    "max_output_tokens": 235929,
    "modalities": {
        "input": [
            "text",
            "image",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "kimi-k2-7-code",
    "object": "model",
    "owned_by": "moonshotai",
    "pricing": {
        "cache_read": 2000000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 10000000000,
        "output": 50000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 10000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 50000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 2000000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_toggle": false,
    "sunset_at": null,
    "tool_call": true
}

{
    "context_length": 1048576,
    "endpoints": [
        "chat"
    ],
    "id": "kimi-k3",
    "max_output_tokens": 943718,
    "modalities": {
        "input": [
            "text",
            "image",
            "video",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "kimi-k3",
    "object": "model",
    "owned_by": "moonshotai",
    "pricing": {
        "cache_read": 2000000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 15000000000,
        "output": 150000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 15000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 150000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 2000000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "low",
        "high",
        "max"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "low",
        "high",
        "max"
    ],
    "tool_call": true
}

{
    "context_length": 1048576,
    "endpoints": [
        "chat"
    ],
    "id": "kimi-k3-1-pro",
    "max_output_tokens": 943718,
    "modalities": {
        "input": [
            "text",
            "image",
            "video",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "kimi-k3-1-pro",
    "object": "model",
    "owned_by": "moonshotai",
    "pricing": {
        "cache_read": 1100000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 11000000000,
        "output": 111000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 11000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 111000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 1100000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "low",
        "high",
        "max"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "low",
        "high",
        "max"
    ],
    "tool_call": true
}

{
    "endpoints": [
        "videos"
    ],
    "id": "kling-v3",
    "max_reference_images": 0,
    "modalities": {
        "input": [
            "text",
            "image"
        ],
        "output": [
            "video"
        ]
    },
    "name": "Kling v3, 1920×1080",
    "object": "model",
    "owned_by": "kuaishou",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 0,
        "output": 0,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "output_video",
            "endpoint": "videos",
            "micro_idr": 750000000,
            "unit": "second",
            "variant": "1080p"
        }
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "video_durations": [
        5
    ],
    "video_resolutions": [
        "1080p"
    ]
}

{
    "endpoints": [
        "videos"
    ],
    "id": "kling-video-v3",
    "max_reference_images": 0,
    "modalities": {
        "input": [
            "text"
        ],
        "output": [
            "video"
        ]
    },
    "name": "Kling Video v3, 1280×720",
    "object": "model",
    "owned_by": "kuaishou",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 0,
        "output": 0,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "output_video",
            "endpoint": "videos",
            "micro_idr": 750000000,
            "unit": "second",
            "variant": "720p"
        }
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "video_durations": [
        5,
        3
    ],
    "video_resolutions": [
        "720p"
    ]
}

{
    "endpoints": [
        "audio_speech"
    ],
    "formats": [
        "mp3",
        "opus",
        "aac",
        "flac"
    ],
    "id": "kokoro-tts",
    "modalities": {
        "input": [
            "text"
        ],
        "output": [
            "audio"
        ]
    },
    "name": "kokoro-tts",
    "object": "model",
    "owned_by": "kokoro",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 0,
        "output": 0,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "output_audio",
            "endpoint": "audio_speech",
            "micro_idr": 75000000,
            "unit": "1k_chars",
            "variant": null
        }
    ],
    "reasoning_toggle": false,
    "sunset_at": null
}

{
    "context_length": 262144,
    "endpoints": [
        "chat"
    ],
    "id": "laguna-s-2-1:free",
    "max_output_tokens": 32768,
    "modalities": {
        "input": [
            "text",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "laguna-s-2-1:free",
    "object": "model",
    "owned_by": "poolside",
    "pricing": {
        "cache_read": 190000000,
        "cache_write": null,
        "currency": "IDR",
        "free": true,
        "input": 1900000000,
        "output": 3800000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_toggle": false,
    "sunset_at": null,
    "tool_call": true
}

{
    "context_length": 262144,
    "endpoints": [
        "chat"
    ],
    "id": "laguna-xs-2-1:free",
    "max_output_tokens": 32768,
    "modalities": {
        "input": [
            "text",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "laguna-xs-2-1:free",
    "object": "model",
    "owned_by": "poolside",
    "pricing": {
        "cache_read": 1200000000,
        "cache_write": null,
        "currency": "IDR",
        "free": true,
        "input": 1200000000,
        "output": 2500000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_toggle": false,
    "sunset_at": null,
    "tool_call": true
}

{
    "context_length": 1000000,
    "endpoints": [
        "chat"
    ],
    "id": "longcat-2-5-preview:free",
    "modalities": {
        "input": [
            "text",
            "image",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "longcat-2-5-preview:free",
    "object": "model",
    "owned_by": "meituan",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": true,
        "input": null,
        "output": null,
        "unit": "micro_idr_per_1m_tokens"
    },
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning_toggle": false,
    "sunset_at": null
}

{
    "endpoints": [
        "music"
    ],
    "formats": [
        "m4a",
        "wav"
    ],
    "id": "lyria-3-5",
    "modalities": {
        "input": [
            "text"
        ],
        "output": [
            "audio"
        ]
    },
    "name": "lyria-3-5",
    "object": "model",
    "owned_by": "google",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 0,
        "output": 0,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "output_audio",
            "endpoint": "music",
            "micro_idr": 1500000000,
            "unit": "song",
            "variant": null
        }
    ],
    "reasoning_toggle": false,
    "sunset_at": null
}

{
    "endpoints": [
        "music"
    ],
    "formats": [
        "m4a",
        "wav"
    ],
    "id": "lyria-3-pro",
    "modalities": {
        "input": [
            "text"
        ],
        "output": [
            "audio"
        ]
    },
    "name": "lyria-3-pro",
    "object": "model",
    "owned_by": "google",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 0,
        "output": 0,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "output_audio",
            "endpoint": "music",
            "micro_idr": 1000000000,
            "unit": "song",
            "variant": null
        }
    ],
    "reasoning_toggle": false,
    "sunset_at": null
}

{
    "context_length": 1050000,
    "endpoints": [
        "chat"
    ],
    "id": "mimo-v2-6-flash",
    "max_output_tokens": 131072,
    "modalities": {
        "input": [
            "text",
            "image",
            "audio",
            "video",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "mimo-v2-6-flash",
    "object": "model",
    "owned_by": "xiaomi",
    "pricing": {
        "cache_read": 70000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 3000000000,
        "output": 6000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 3000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 6000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 70000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_toggle": false,
    "sunset_at": null,
    "tool_call": true
}

{
    "context_length": 1050000,
    "endpoints": [
        "chat"
    ],
    "id": "mimo-v2-6-flash:free",
    "max_output_tokens": 131072,
    "modalities": {
        "input": [
            "text",
            "image",
            "audio",
            "video",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "mimo-v2-6-flash:free",
    "object": "model",
    "owned_by": "xiaomi",
    "pricing": {
        "cache_read": 2900000000,
        "cache_write": null,
        "currency": "IDR",
        "free": true,
        "input": 2900000000,
        "output": 5800000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_toggle": false,
    "sunset_at": 1792940400,
    "tool_call": true
}

{
    "context_length": 1050000,
    "endpoints": [
        "chat"
    ],
    "id": "mimo-v2-6-pro",
    "max_output_tokens": 131072,
    "modalities": {
        "input": [
            "text",
            "image",
            "audio",
            "video",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "mimo-v2-6-pro",
    "object": "model",
    "owned_by": "xiaomi",
    "pricing": {
        "cache_read": 900000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 9000000000,
        "output": 18000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 9000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 18000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 900000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_toggle": false,
    "sunset_at": null,
    "tool_call": true
}

{
    "context_length": 204800,
    "endpoints": [
        "chat"
    ],
    "id": "minimax-m2-7",
    "max_output_tokens": 131072,
    "modalities": {
        "input": [
            "text",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "minimax-m2-7",
    "object": "model",
    "owned_by": "minimax",
    "pricing": {
        "cache_read": 1200000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 6300000000,
        "output": 25000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 6300000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 25000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 1200000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_toggle": false,
    "sunset_at": null,
    "tool_call": true
}

{
    "context_length": 204800,
    "endpoints": [
        "chat"
    ],
    "id": "minimax-m2-7-highspeed",
    "max_output_tokens": 131072,
    "modalities": {
        "input": [
            "text",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "minimax-m2-7-highspeed",
    "object": "model",
    "owned_by": "minimax",
    "pricing": {
        "cache_read": 2000000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 10400000000,
        "output": 42000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 10400000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 42000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 2000000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_toggle": false,
    "sunset_at": null,
    "tool_call": true
}

{
    "context_length": 1048576,
    "endpoints": [
        "chat"
    ],
    "id": "minimax-m3",
    "max_output_tokens": 512000,
    "modalities": {
        "input": [
            "text",
            "image",
            "video",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "minimax-m3",
    "object": "model",
    "owned_by": "minimax",
    "pricing": {
        "cache_read": 120000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 630000000,
        "output": 2500000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 630000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 2500000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 120000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_toggle": false,
    "sunset_at": null,
    "tool_call": true
}

{
    "context_length": 1000000,
    "endpoints": [
        "chat"
    ],
    "id": "minimax-m3-1-flash",
    "max_output_tokens": 512000,
    "modalities": {
        "input": [
            "text",
            "image",
            "video",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "minimax-m3-1-flash",
    "object": "model",
    "owned_by": "minimax",
    "pricing": {
        "cache_read": 60000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 320000000,
        "output": 1300000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 320000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 1300000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 60000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "tool_call": true
}

{
    "context_length": 1048576,
    "endpoints": [
        "chat"
    ],
    "id": "muse-spark-1-2",
    "max_output_tokens": 131072,
    "modalities": {
        "input": [
            "text",
            "image",
            "video",
            "pdf",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "muse-spark-1-2",
    "object": "model",
    "owned_by": "meta",
    "pricing": {
        "cache_read": 2000000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 20000000000,
        "output": 80000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 20000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 80000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 2000000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "minimal",
        "low",
        "medium",
        "high",
        "xhigh"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "minimal",
        "low",
        "medium",
        "high",
        "xhigh"
    ],
    "tool_call": true
}

{
    "context_length": 1048576,
    "endpoints": [
        "chat"
    ],
    "id": "muse-spark-1-2-contributor",
    "max_output_tokens": 131072,
    "modalities": {
        "input": [
            "text",
            "image",
            "video",
            "pdf",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "muse-spark-1-2-contributor",
    "object": "model",
    "owned_by": "meta",
    "pricing": {
        "cache_read": 200000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 2000000000,
        "output": 4000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 2000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 4000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 200000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "minimal",
        "low",
        "medium",
        "high",
        "xhigh"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "minimal",
        "low",
        "medium",
        "high",
        "xhigh"
    ],
    "tool_call": true
}

{
    "context_length": 1048576,
    "endpoints": [
        "chat"
    ],
    "id": "muse-spark-1-3",
    "max_output_tokens": 131072,
    "modalities": {
        "input": [
            "text",
            "image",
            "video",
            "pdf",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "muse-spark-1-3",
    "object": "model",
    "owned_by": "meta",
    "pricing": {
        "cache_read": 2000000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 20000000000,
        "output": 80000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 20000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 80000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 2000000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "minimal",
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "minimal",
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "tool_call": true
}

{
    "context_length": 1048576,
    "endpoints": [
        "chat"
    ],
    "id": "muse-spark-1-3-contributor",
    "max_output_tokens": 131072,
    "modalities": {
        "input": [
            "text",
            "image",
            "video",
            "pdf",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "muse-spark-1-3-contributor",
    "object": "model",
    "owned_by": "meta",
    "pricing": {
        "cache_read": 200000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 2000000000,
        "output": 4000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 2000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 4000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 200000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "minimal",
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "minimal",
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "tool_call": true
}

{
    "context_length": 1048576,
    "endpoints": [
        "chat"
    ],
    "id": "muse-spark-1-3-contributor:free",
    "max_output_tokens": 131072,
    "modalities": {
        "input": [
            "text",
            "image",
            "video",
            "pdf",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "muse-spark-1-3-contributor:free",
    "object": "model",
    "owned_by": "meta",
    "pricing": {
        "cache_read": 2100000000,
        "cache_write": null,
        "currency": "IDR",
        "free": true,
        "input": 2100000000,
        "output": 4200000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "minimal",
        "low",
        "medium",
        "high",
        "xhigh"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "minimal",
        "low",
        "medium",
        "high",
        "xhigh"
    ],
    "tool_call": true
}

{
    "context_length": 1048576,
    "endpoints": [
        "chat"
    ],
    "id": "muse-spark-open",
    "max_output_tokens": 943718,
    "modalities": {
        "input": [
            "text",
            "image",
            "video",
            "pdf",
            "audio",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "muse-spark-open",
    "object": "model",
    "owned_by": "meta",
    "pricing": {
        "cache_read": 2000000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 20000000000,
        "output": 80000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 20000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 80000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 2000000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "low",
        "medium",
        "high",
        "xhigh"
    ],
    "reasoning_toggle": true,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "low",
        "medium",
        "high",
        "xhigh"
    ],
    "tool_call": true
}

{
    "context_length": 1007997,
    "endpoints": [
        "chat"
    ],
    "id": "muse-wonder-1-0",
    "max_output_tokens": 128000,
    "modalities": {
        "input": [
            "text",
            "image",
            "pdf",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "muse-wonder-1-0",
    "object": "model",
    "owned_by": "meta",
    "pricing": {
        "cache_read": 3500000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 70000000000,
        "output": 350000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 70000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 3500000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 350000000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "minimal",
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "minimal",
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "tool_call": true
}

{
    "endpoints": [
        "images"
    ],
    "id": "nano-banana",
    "modalities": {
        "input": [
            "text",
            "image"
        ],
        "output": [
            "image"
        ]
    },
    "name": "Nano Banana",
    "object": "model",
    "owned_by": "google",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 0,
        "output": 0,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "output_image",
            "endpoint": "images",
            "micro_idr": 150000000,
            "unit": "image",
            "variant": null
        }
    ],
    "reasoning_toggle": false,
    "sunset_at": null
}

{
    "context_length": 131072,
    "endpoints": [
        "images"
    ],
    "id": "nano-banana-2",
    "max_output_tokens": 32768,
    "modalities": {
        "input": [
            "image",
            "text"
        ],
        "output": [
            "text",
            "image"
        ]
    },
    "name": "nano-banana-2",
    "object": "model",
    "owned_by": "google",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 0,
        "output": 0,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "output_image",
            "endpoint": "images",
            "micro_idr": 250000000,
            "unit": "image",
            "variant": null
        }
    ],
    "reasoning": true,
    "reasoning_options": [
        "minimal",
        "high"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "minimal",
        "high"
    ],
    "tool_call": false
}

{
    "endpoints": [
        "images"
    ],
    "id": "nano-banana-2-1",
    "modalities": {
        "input": [
            "image"
        ],
        "output": [
            "image"
        ]
    },
    "name": "nano-banana-2-1",
    "object": "model",
    "owned_by": "google",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 0,
        "output": 0,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "output_image",
            "endpoint": "images",
            "micro_idr": 300000000,
            "unit": "image",
            "variant": null
        }
    ],
    "reasoning_toggle": false,
    "sunset_at": null
}

{
    "endpoints": [
        "images"
    ],
    "id": "nano-banana-2-lite",
    "modalities": {
        "input": [
            "text"
        ],
        "output": [
            "image"
        ]
    },
    "name": "Nano Banana 2 Lite",
    "object": "model",
    "owned_by": "google",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 0,
        "output": 0,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "output_image",
            "endpoint": "images",
            "micro_idr": 150000000,
            "unit": "image",
            "variant": null
        }
    ],
    "reasoning_toggle": false,
    "sunset_at": null
}

{
    "endpoints": [
        "images"
    ],
    "id": "nano-banana-pro",
    "modalities": {
        "input": [
            "text"
        ],
        "output": [
            "image"
        ]
    },
    "name": "Nano Banana Pro",
    "object": "model",
    "owned_by": "google",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 0,
        "output": 0,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "output_image",
            "endpoint": "images",
            "micro_idr": 350000000,
            "unit": "image",
            "variant": null
        }
    ],
    "reasoning_toggle": false,
    "sunset_at": null
}

{
    "context_length": 1000000,
    "endpoints": [
        "chat"
    ],
    "id": "nemotron-3-5-super-vl:free",
    "max_output_tokens": 235929,
    "modalities": {
        "input": [
            "text",
            "image",
            "video",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "nemotron-3-5-super-vl:free",
    "object": "model",
    "owned_by": "nvidia",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": true,
        "input": null,
        "output": null,
        "unit": "micro_idr_per_1m_tokens"
    },
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_toggle": false,
    "sunset_at": null,
    "tool_call": true
}

{
    "context_length": 256000,
    "endpoints": [
        "chat"
    ],
    "id": "nemotron-3-nano-omni-30b-a3b-reasoning:free",
    "max_output_tokens": 65536,
    "modalities": {
        "input": [
            "text",
            "image",
            "video",
            "audio",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "nemotron-3-nano-omni-30b-a3b-reasoning:free",
    "object": "model",
    "owned_by": "nvidia",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": true,
        "input": null,
        "output": null,
        "unit": "micro_idr_per_1m_tokens"
    },
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_toggle": false,
    "sunset_at": null,
    "tool_call": true
}

{
    "context_length": 262144,
    "endpoints": [
        "chat"
    ],
    "id": "nemotron-3-super-120b-a12b",
    "max_output_tokens": 235929,
    "modalities": {
        "input": [
            "text",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "nemotron-3-super-120b-a12b",
    "object": "model",
    "owned_by": "nvidia",
    "pricing": {
        "cache_read": 170000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 1700000000,
        "output": 8400000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 1700000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 8400000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 170000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "none",
        "low",
        "medium"
    ],
    "reasoning_toggle": true,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "none",
        "low",
        "medium"
    ],
    "tool_call": true
}

{
    "context_length": 262144,
    "endpoints": [
        "chat"
    ],
    "id": "nemotron-3-super-120b-a12b:free",
    "max_output_tokens": 235929,
    "modalities": {
        "input": [
            "text",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "nemotron-3-super-120b-a12b:free",
    "object": "model",
    "owned_by": "nvidia",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": true,
        "input": 1600000000,
        "output": 7700000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "none",
        "low",
        "medium"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "none",
        "low",
        "medium"
    ],
    "tool_call": true
}

{
    "context_length": 1000000,
    "endpoints": [
        "chat"
    ],
    "id": "nemotron-3-ultra-550b-a55b",
    "max_output_tokens": 65536,
    "modalities": {
        "input": [
            "text",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "nemotron-3-ultra-550b-a55b",
    "object": "model",
    "owned_by": "nvidia",
    "pricing": {
        "cache_read": 1200000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 12000000000,
        "output": 75000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 12000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 75000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 1200000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "none",
        "medium",
        "high"
    ],
    "reasoning_toggle": true,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "none",
        "medium",
        "high"
    ],
    "tool_call": true
}

{
    "context_length": 1000000,
    "endpoints": [
        "chat"
    ],
    "id": "nemotron-3-ultra-550b-a55b:free",
    "max_output_tokens": 65536,
    "modalities": {
        "input": [
            "text",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "nemotron-3-ultra-550b-a55b:free",
    "object": "model",
    "owned_by": "nvidia",
    "pricing": {
        "cache_read": 4200000000,
        "cache_write": null,
        "currency": "IDR",
        "free": true,
        "input": 12000000000,
        "output": 75000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "none",
        "medium",
        "high"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "none",
        "medium",
        "high"
    ],
    "tool_call": true
}

{
    "context_length": 262144,
    "endpoints": [
        "chat"
    ],
    "id": "ornith-1-5-122b:free",
    "modalities": {
        "input": [
            "text",
            "image",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "Ornith 1.5 122B",
    "object": "model",
    "owned_by": "ornith",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": true,
        "input": null,
        "output": null,
        "unit": "micro_idr_per_1m_tokens"
    },
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "tool_call": true
}

{
    "endpoints": [
        "images"
    ],
    "id": "qwen-image-2.0-pro",
    "modalities": {
        "input": [
            "text",
            "image"
        ],
        "output": [
            "image"
        ]
    },
    "name": "Qwen-Image-2.0-Pro",
    "object": "model",
    "owned_by": "qwen",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 0,
        "output": 0,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "output_image",
            "endpoint": "images",
            "micro_idr": 150000000,
            "unit": "image",
            "variant": null
        }
    ],
    "reasoning_toggle": false,
    "sunset_at": null
}

{
    "endpoints": [
        "images"
    ],
    "id": "qwen-image-3.0-pro",
    "modalities": {
        "input": [
            "text",
            "image"
        ],
        "output": [
            "image"
        ]
    },
    "name": "Qwen-Image-3.0-Pro",
    "object": "model",
    "owned_by": "qwen",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 0,
        "output": 0,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "output_image",
            "endpoint": "images",
            "micro_idr": 150000000,
            "unit": "image",
            "variant": null
        }
    ],
    "reasoning_toggle": false,
    "sunset_at": null
}

{
    "context_length": 1000000,
    "endpoints": [
        "chat"
    ],
    "id": "qwen3-7-plus",
    "max_output_tokens": 131072,
    "modalities": {
        "input": [
            "text",
            "image",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "qwen3-7-plus",
    "object": "model",
    "owned_by": "qwen",
    "pricing": {
        "cache_read": 1300000000,
        "cache_write": 8400000000,
        "currency": "IDR",
        "free": false,
        "input": 6700000000,
        "output": 26000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 6700000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 26000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 1300000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_write",
            "endpoint": "chat",
            "micro_idr": 8400000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_toggle": false,
    "sunset_at": null,
    "tool_call": true
}

{
    "context_length": 262144,
    "endpoints": [
        "chat"
    ],
    "id": "qwen3-8-27b-uncensored",
    "max_output_tokens": 32768,
    "modalities": {
        "input": [
            "text",
            "image",
            "video",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "Qwen3.8 27B Uncensored",
    "object": "model",
    "owned_by": "qwen",
    "pricing": {
        "cache_read": 1000000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 5000000000,
        "output": 25000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 1000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 5000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 25000000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "low",
        "medium",
        "high"
    ],
    "reasoning_toggle": true,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "low",
        "medium",
        "high"
    ],
    "tool_call": true
}

{
    "context_length": 1000000,
    "endpoints": [
        "chat"
    ],
    "id": "qwen3-8-flash",
    "max_output_tokens": 131072,
    "modalities": {
        "input": [
            "text",
            "image",
            "video",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "qwen3-8-flash",
    "object": "model",
    "owned_by": "qwen",
    "pricing": {
        "cache_read": 300000000,
        "cache_write": 750000000,
        "currency": "IDR",
        "free": false,
        "input": 3000000000,
        "output": 7500000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 3000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 7500000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 300000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_write",
            "endpoint": "chat",
            "micro_idr": 750000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_toggle": false,
    "sunset_at": null,
    "tool_call": true
}

{
    "endpoints": [
        "chat"
    ],
    "id": "qwen3-8-max",
    "modalities": {
        "input": [
            "text",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "qwen3-8-max",
    "object": "model",
    "owned_by": "qwen",
    "pricing": {
        "cache_read": 5200000000,
        "cache_write": 52000000000,
        "currency": "IDR",
        "free": false,
        "input": 42000000000,
        "output": 120000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 42000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 120000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 5200000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_write",
            "endpoint": "chat",
            "micro_idr": 52000000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning_toggle": false,
    "sunset_at": null
}

{
    "context_length": 1000000,
    "endpoints": [
        "chat"
    ],
    "id": "qwen3-8-omni-flash",
    "max_output_tokens": 131072,
    "modalities": {
        "input": [
            "text",
            "image",
            "audio",
            "video",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "qwen3-8-omni-flash",
    "object": "model",
    "owned_by": "qwen",
    "pricing": {
        "cache_read": 250000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 2500000000,
        "output": 7500000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 2500000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 7500000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 250000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_toggle": false,
    "sunset_at": null,
    "tool_call": true
}

{
    "context_length": 1000000,
    "endpoints": [
        "chat"
    ],
    "id": "qwen3-8-omni-flash:free",
    "max_output_tokens": 131072,
    "modalities": {
        "input": [
            "text",
            "image",
            "audio",
            "video",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "qwen3-8-omni-flash:free",
    "object": "model",
    "owned_by": "qwen",
    "pricing": {
        "cache_read": 330000000,
        "cache_write": null,
        "currency": "IDR",
        "free": true,
        "input": 3100000000,
        "output": 9800000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_toggle": false,
    "sunset_at": null,
    "tool_call": true
}

{
    "endpoints": [
        "videos"
    ],
    "id": "seedance-2.0",
    "max_reference_images": 9,
    "modalities": {
        "input": [
            "text",
            "image"
        ],
        "output": [
            "video"
        ]
    },
    "name": "Seedance 2.0, 1280x720",
    "object": "model",
    "owned_by": "bytedance",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 0,
        "output": 0,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "output_video",
            "endpoint": "videos",
            "micro_idr": 750000000,
            "unit": "second",
            "variant": null
        }
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "video_durations": [
        5,
        4,
        6,
        7,
        8,
        9,
        10,
        11,
        12,
        13,
        14,
        15
    ],
    "video_resolutions": [
        "720p"
    ]
}

{
    "endpoints": [
        "videos"
    ],
    "id": "seedance-2.0-fast",
    "max_reference_images": 9,
    "modalities": {
        "input": [
            "text",
            "image"
        ],
        "output": [
            "video"
        ]
    },
    "name": "Seedance 2.0 Fast, 1280×720",
    "object": "model",
    "owned_by": "bytedance",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 0,
        "output": 0,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "output_video",
            "endpoint": "videos",
            "micro_idr": 500000000,
            "unit": "second",
            "variant": "720p"
        }
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "video_durations": [
        5,
        4,
        6,
        7,
        8,
        9,
        10,
        11,
        12,
        13,
        14,
        15
    ],
    "video_resolutions": [
        "720p"
    ]
}

{
    "endpoints": [
        "videos"
    ],
    "id": "seedance-2.5",
    "max_reference_images": 9,
    "modalities": {
        "input": [
            "text",
            "image"
        ],
        "output": [
            "video"
        ]
    },
    "name": "Seedance 2.5, 1280×720",
    "object": "model",
    "owned_by": "bytedance",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 0,
        "output": 0,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "output_video",
            "endpoint": "videos",
            "micro_idr": 750000000,
            "unit": "second",
            "variant": "720p"
        }
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "video_durations": [
        5,
        4,
        6,
        7,
        8,
        9,
        10,
        11,
        12,
        13,
        14,
        15,
        16,
        17,
        18,
        19,
        20,
        21,
        22,
        23,
        24,
        25,
        26,
        27,
        28,
        29,
        30
    ],
    "video_resolutions": [
        "720p"
    ]
}

{
    "context_length": 524288,
    "endpoints": [
        "chat"
    ],
    "id": "solar-mini4:free",
    "max_output_tokens": 131072,
    "modalities": {
        "input": [
            "text",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "solar-mini4:free",
    "object": "model",
    "owned_by": "upstage",
    "pricing": {
        "cache_read": 1000000000,
        "cache_write": null,
        "currency": "IDR",
        "free": true,
        "input": 1000000000,
        "output": 4200000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "none",
        "minimal",
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "none",
        "minimal",
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
    ],
    "tool_call": true
}

{
    "context_length": 262144,
    "endpoints": [
        "chat"
    ],
    "id": "step-3-7-flash",
    "max_output_tokens": 230400,
    "modalities": {
        "input": [
            "text",
            "image",
            "video",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "step-3-7-flash",
    "object": "model",
    "owned_by": "stepfun",
    "pricing": {
        "cache_read": 840000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 4200000000,
        "output": 24000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 4200000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 24000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 840000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "low",
        "medium",
        "high"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "low",
        "medium",
        "high"
    ],
    "tool_call": true
}

{
    "context_length": 1048576,
    "endpoints": [
        "chat"
    ],
    "id": "step-5-preview",
    "max_output_tokens": 64000,
    "modalities": {
        "input": [
            "text",
            "image",
            "video",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "step-5-preview",
    "object": "model",
    "owned_by": "stepfun",
    "pricing": {
        "cache_read": 1000000000,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 20000000000,
        "output": 50000000000,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input",
            "endpoint": "chat",
            "micro_idr": 20000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "output",
            "endpoint": "chat",
            "micro_idr": 50000000000,
            "unit": "token_1m",
            "variant": null
        },
        {
            "billable": "cache_read",
            "endpoint": "chat",
            "micro_idr": 1000000000,
            "unit": "token_1m",
            "variant": null
        }
    ],
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_options": [
        "low",
        "medium",
        "high"
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "supported_reasoning_levels": [
        "low",
        "medium",
        "high"
    ],
    "tool_call": true
}

{
    "endpoints": [
        "videos"
    ],
    "id": "veo-3.1-lite",
    "modalities": {
        "input": [
            "text",
            "image"
        ],
        "output": [
            "video"
        ]
    },
    "name": "Veo 3.1 Lite",
    "object": "model",
    "owned_by": "google",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 0,
        "output": 0,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "output_video",
            "endpoint": "videos",
            "micro_idr": 500000000,
            "unit": "second",
            "variant": "720p"
        }
    ],
    "reasoning_toggle": false,
    "sunset_at": null,
    "video_durations": [
        8
    ],
    "video_resolutions": [
        "720p"
    ]
}

{
    "endpoints": [
        "audio_transcription"
    ],
    "id": "whisper-large-v3-turbo",
    "modalities": {
        "input": [
            "audio"
        ],
        "output": [
            "text"
        ]
    },
    "name": "whisper-large-v3-turbo",
    "object": "model",
    "owned_by": "openai",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": false,
        "input": 0,
        "output": 0,
        "unit": "micro_idr_per_1m_tokens"
    },
    "pricing_lines": [
        {
            "billable": "input_audio",
            "endpoint": "audio_transcription",
            "micro_idr": 175000,
            "unit": "second",
            "variant": null
        }
    ],
    "reasoning_toggle": false,
    "sunset_at": null
}

{
    "context_length": 262144,
    "endpoints": [
        "chat"
    ],
    "id": "xing4-0-29b-a4b:free",
    "max_output_tokens": 235929,
    "modalities": {
        "input": [
            "text",
            "file"
        ],
        "output": [
            "text"
        ]
    },
    "name": "Xing4.0 29B A4B",
    "object": "model",
    "owned_by": "xingchen-agi",
    "pricing": {
        "cache_read": null,
        "cache_write": null,
        "currency": "IDR",
        "free": true,
        "input": null,
        "output": null,
        "unit": "micro_idr_per_1m_tokens"
    },
    "protocols": [
        "openai-chat",
        "openai-responses",
        "anthropic-messages"
    ],
    "reasoning": true,
    "reasoning_toggle": false,
    "sunset_at": null,
    "tool_call": true
}

{
    "id": "google/gemini-3.6-flash",
    "object": "model",
    "type": "model",
    "display_name": "Gemini 3.6 Flash",
    "created": 1,
    "owned_by": "google",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0.75,
        "output": 3.75,
        "cache_read": 0.07499999999999999722444243843710864894092082977294921875,
        "cache_write": 0.041667000000000002646327601496523129753768444061279296875
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "low",
            "medium",
            "high"
        ],
        "default": "medium"
    }
}

{
    "id": "openai/gpt-6.1-sol",
    "object": "model",
    "type": "model",
    "display_name": "GPT-6.1 Sol",
    "created": 1,
    "owned_by": "openai",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 2,
        "output": 10,
        "cache_read": 0.1000000000000000055511151231257827021181583404541015625,
        "cache_write": 2.5
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1050000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ],
        "default": "low"
    }
}

{
    "id": "x-ai/grok-4.5",
    "object": "model",
    "type": "model",
    "display_name": "Grok 4.5",
    "created": 1,
    "owned_by": "grok",
    "modality": "chat",
    "access_tier": "premium",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 1.3000000000000000444089209850062616169452667236328125,
        "output": 3.899999999999999911182158029987476766109466552734375,
        "cache_read": 0.195000000000000006661338147750939242541790008544921875
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 500000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "low",
            "medium",
            "high",
            "xhigh"
        ],
        "default": "high"
    }
}

{
    "id": "mistralai/ministral-14b",
    "object": "model",
    "type": "model",
    "display_name": "Ministral 3 14B",
    "created": 1,
    "owned_by": "mistral",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": false
    },
    "context_length": 256000,
    "max_output_tokens": 8192
}

{
    "id": "anthropic/claude-opus-4.8",
    "object": "model",
    "type": "model",
    "display_name": "Opus 4.8",
    "created": 1,
    "owned_by": "anthropic",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 5,
        "output": 25,
        "cache_read": 0.5,
        "cache_write": 6.25
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ],
        "default": "high"
    }
}

{
    "id": "x-ai/grok-4.7",
    "object": "model",
    "type": "model",
    "display_name": "Grok 4.7",
    "created": 1,
    "owned_by": "grok",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 2,
        "output": 6,
        "cache_read": 0.5
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 500000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "low",
            "medium",
            "high",
            "xhigh"
        ],
        "default": "high"
    }
}

{
    "id": "anthropic/claude-haiku-5.5",
    "object": "model",
    "type": "model",
    "display_name": "Haiku 5.5",
    "created": 1,
    "owned_by": "anthropic",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0.1000000000000000055511151231257827021181583404541015625,
        "output": 0.5,
        "cache_read": 0.01000000000000000020816681711721685132943093776702880859375,
        "cache_write": 0.125
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 128000,
    "reasoning_efforts": {
        "levels": [
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ],
        "default": "medium"
    }
}

{
    "id": "anthropic/claude-sonnet-5.5",
    "object": "model",
    "type": "model",
    "display_name": "Sonnet 5.5",
    "created": 1,
    "owned_by": "anthropic",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 2,
        "output": 10,
        "cache_read": 0.1000000000000000055511151231257827021181583404541015625,
        "cache_write": 2.5
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 128000,
    "reasoning_efforts": {
        "levels": [
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ],
        "default": "high"
    }
}

{
    "id": "anthropic/claude-opus-5",
    "object": "model",
    "type": "model",
    "display_name": "Opus 5",
    "created": 1,
    "owned_by": "anthropic",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 5,
        "output": 25,
        "cache_read": 0.5,
        "cache_write": 6.25
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ],
        "default": "high"
    }
}

{
    "id": "minimax/minimax-m3",
    "object": "model",
    "type": "model",
    "display_name": "MiniMax M3",
    "created": 1,
    "owned_by": "minimax",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0.299999999999999988897769753748434595763683319091796875,
        "output": 1.1999999999999999555910790149937383830547332763671875,
        "cache_read": 0.059999999999999997779553950749686919152736663818359375
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "adaptive",
            "disabled"
        ],
        "default": "disabled"
    }
}

{
    "id": "minimax/minimax-m2.7",
    "object": "model",
    "type": "model",
    "display_name": "MiniMax M2.7",
    "created": 1,
    "owned_by": "minimax",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0.299999999999999988897769753748434595763683319091796875,
        "output": 1.1999999999999999555910790149937383830547332763671875,
        "cache_read": 0.059999999999999997779553950749686919152736663818359375,
        "cache_write": 0.375
    },
    "capabilities": {
        "vision": false,
        "tools": true,
        "reasoning": true
    },
    "context_length": 204800,
    "max_output_tokens": 65536
}

{
    "id": "minimax/minimax-m2.7-highspeed",
    "object": "model",
    "type": "model",
    "display_name": "MiniMax M2.7 Highspeed",
    "created": 1,
    "owned_by": "minimax",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0.59999999999999997779553950749686919152736663818359375,
        "output": 2.399999999999999911182158029987476766109466552734375,
        "cache_read": 0.059999999999999997779553950749686919152736663818359375,
        "cache_write": 0.375
    },
    "capabilities": {
        "vision": false,
        "tools": true,
        "reasoning": true
    },
    "context_length": 204800,
    "max_output_tokens": 65536
}

{
    "id": "openai/gpt-6-astra",
    "object": "model",
    "type": "model",
    "display_name": "GPT-6 Astra",
    "created": 1,
    "owned_by": "openai",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 10,
        "output": 50,
        "cache_read": 1
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "min_plan_usd": 100,
    "min_plan_names": [
        "Ultra",
        "Power"
    ],
    "context_length": 1050000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ],
        "default": "medium"
    }
}

{
    "id": "openai/gpt-6-sol",
    "object": "model",
    "type": "model",
    "display_name": "GPT-6 Sol",
    "created": 1,
    "owned_by": "openai",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 2,
        "output": 10,
        "cache_read": 0.200000000000000011102230246251565404236316680908203125,
        "cache_write": 2.5
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1050000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ],
        "default": "medium"
    }
}

{
    "id": "anthropic/claude-opus-4.5",
    "object": "model",
    "type": "model",
    "display_name": "Opus 4.5",
    "created": 1,
    "owned_by": "anthropic",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 5,
        "output": 25,
        "cache_read": 0.5,
        "cache_write": 6.25
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 200000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "low",
            "medium",
            "high"
        ],
        "default": "low"
    }
}

{
    "id": "anthropic/claude-sonnet-4.6",
    "object": "model",
    "type": "model",
    "display_name": "Sonnet 4.6",
    "created": 1,
    "owned_by": "anthropic",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 3,
        "output": 15,
        "cache_read": 0.299999999999999988897769753748434595763683319091796875,
        "cache_write": 3.75
    },
    "capabilities": {
        "vision": false,
        "tools": false,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "low",
            "medium",
            "high",
            "max"
        ],
        "default": "low"
    }
}

{
    "id": "anthropic/claude-haiku-4.5",
    "object": "model",
    "type": "model",
    "display_name": "Haiku 4.5",
    "created": 1,
    "owned_by": "anthropic",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 1,
        "output": 5,
        "cache_read": 0.1000000000000000055511151231257827021181583404541015625,
        "cache_write": 1.25
    },
    "capabilities": {
        "vision": false,
        "tools": false,
        "reasoning": true
    },
    "context_length": 200000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "low",
            "medium",
            "high"
        ],
        "default": "low"
    }
}

{
    "id": "google/gemini-3.8-flash",
    "object": "model",
    "type": "model",
    "display_name": "Gemini 3.8 Flash",
    "created": 1,
    "owned_by": "google",
    "modality": "chat",
    "access_tier": "premium",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0.75,
        "output": 3.75,
        "cache_read": 0.07499999999999999722444243843710864894092082977294921875,
        "cache_write": 0.04170000000000000095479180117763462476432323455810546875
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "low",
            "medium",
            "high"
        ],
        "default": "medium"
    }
}

{
    "id": "moonshotai/kimi-k2.8-preview-agent",
    "object": "model",
    "type": "model",
    "display_name": "Kimi K2.8 Preview Agent",
    "created": 1,
    "owned_by": "kimi",
    "modality": "chat",
    "access_tier": "premium",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 1,
        "output": 4,
        "cache_read": 0.1600000000000000033306690738754696212708950042724609375
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 262144,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "none",
            "low",
            "medium",
            "high",
            "max"
        ],
        "default": "high"
    }
}

{
    "id": "qwen/qwen3-vl-plus:free",
    "object": "model",
    "type": "model",
    "display_name": "Qwen3 VL Plus (Free)",
    "created": 1,
    "owned_by": "qwen",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 262144,
    "max_output_tokens": 65536
}

{
    "id": "google/gemini-3.7-flash",
    "object": "model",
    "type": "model",
    "display_name": "Gemini 3.7 Flash",
    "created": 1,
    "owned_by": "google",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0.75,
        "output": 3.75,
        "cache_read": 0.07499999999999999722444243843710864894092082977294921875,
        "cache_write": 0.041667000000000002646327601496523129753768444061279296875
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "low",
            "medium",
            "high"
        ],
        "default": "medium"
    }
}

{
    "id": "x-ai/grok-4.6",
    "object": "model",
    "type": "model",
    "display_name": "Grok 4.6",
    "created": 1,
    "owned_by": "grok",
    "modality": "chat",
    "access_tier": "premium",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 2,
        "output": 6,
        "cache_read": 0.5
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 500000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "low",
            "medium",
            "high",
            "xhigh"
        ],
        "default": "high"
    }
}

{
    "id": "anthropic/claude-fable-5-1",
    "object": "model",
    "type": "model",
    "display_name": "Fable 5.1",
    "created": 1,
    "owned_by": "anthropic",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 10,
        "output": 50,
        "cache_read": 0.25,
        "cache_write": 12.5
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "min_plan_usd": 100,
    "min_plan_names": [
        "Ultra",
        "Power"
    ],
    "context_length": 1000000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ],
        "default": "high"
    }
}

{
    "id": "anthropic/claude-fable-5",
    "object": "model",
    "type": "model",
    "display_name": "Fable 5",
    "created": 1,
    "owned_by": "anthropic",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 10,
        "output": 50,
        "cache_read": 1,
        "cache_write": 12.5
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ],
        "default": "high"
    }
}

{
    "id": "cohere/north-mini-code",
    "object": "model",
    "type": "model",
    "display_name": "North Mini Code",
    "created": 1,
    "owned_by": "api",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": false,
        "tools": true,
        "reasoning": true
    },
    "context_length": 256000,
    "max_output_tokens": 64000,
    "reasoning_efforts": {
        "levels": [
            "none",
            "high"
        ],
        "default": "high"
    }
}

{
    "id": "cohere/command-r-08-2024",
    "object": "model",
    "type": "model",
    "display_name": "Command R (08-2024)",
    "created": 1,
    "owned_by": "api",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": false,
        "tools": true,
        "reasoning": false
    },
    "context_length": 128000,
    "max_output_tokens": 4096
}

{
    "id": "qwen/qwen-plus-2025-07-28:free",
    "object": "model",
    "type": "model",
    "display_name": "Qwen Plus 0728 (Free)",
    "created": 1,
    "owned_by": "qwen",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 131072,
    "max_output_tokens": 65536
}

{
    "id": "sensenova/sensenova-6.8-flash-lite",
    "object": "model",
    "type": "model",
    "display_name": "SenseNova 6.8 Flash-Lite",
    "created": 1,
    "owned_by": "api",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 262144,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "none",
            "low",
            "medium",
            "high"
        ],
        "default": "medium"
    }
}

{
    "id": "cohere/command-a",
    "object": "model",
    "type": "model",
    "display_name": "Command A",
    "created": 1,
    "owned_by": "api",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": false,
        "tools": true,
        "reasoning": false
    },
    "context_length": 288000,
    "max_output_tokens": 8192
}

{
    "id": "cohere/aya-vision-32b",
    "object": "model",
    "type": "model",
    "display_name": "Aya Vision 32B",
    "created": 1,
    "owned_by": "api",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": false,
        "tools": false,
        "reasoning": false
    },
    "context_length": 16384,
    "max_output_tokens": 4096
}

{
    "id": "mistralai/ministral-3b",
    "object": "model",
    "type": "model",
    "display_name": "Ministral 3 3B",
    "created": 1,
    "owned_by": "mistral",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": false
    },
    "context_length": 128000,
    "max_output_tokens": 8192
}

{
    "id": "anthropic/claude-sonnet-4",
    "object": "model",
    "type": "model",
    "display_name": "Sonnet 4",
    "created": 1,
    "owned_by": "anthropic",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 3,
        "output": 15,
        "cache_read": 0.299999999999999988897769753748434595763683319091796875,
        "cache_write": 3.75
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "low",
            "high"
        ],
        "default": "low"
    }
}

{
    "id": "cohere/tiny-aya-earth",
    "object": "model",
    "type": "model",
    "display_name": "Tiny Aya Earth",
    "created": 1,
    "owned_by": "api",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": false,
        "tools": true,
        "reasoning": false
    },
    "context_length": 8192,
    "max_output_tokens": 8192
}

{
    "id": "cohere/tiny-aya-global",
    "object": "model",
    "type": "model",
    "display_name": "Tiny Aya Global",
    "created": 1,
    "owned_by": "api",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": false,
        "tools": true,
        "reasoning": false
    },
    "context_length": 8192,
    "max_output_tokens": 8192
}

{
    "id": "cohere/command-r-plus-08-2024",
    "object": "model",
    "type": "model",
    "display_name": "Command R+ (08-2024)",
    "created": 1,
    "owned_by": "api",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": false,
        "tools": true,
        "reasoning": false
    },
    "context_length": 128000,
    "max_output_tokens": 4096
}

{
    "id": "cohere/aya-expanse-32b",
    "object": "model",
    "type": "model",
    "display_name": "Aya Expanse 32B",
    "created": 1,
    "owned_by": "api",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": false,
        "tools": false,
        "reasoning": false
    },
    "context_length": 128000,
    "max_output_tokens": 4096
}

{
    "id": "openai/gpt-5.6-terra",
    "object": "model",
    "type": "model",
    "display_name": "GPT-5.6 Terra",
    "created": 1,
    "owned_by": "openai",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 1,
        "output": 6,
        "cache_read": 0.125
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ],
        "default": "medium"
    }
}

{
    "id": "cohere/tiny-aya-fire",
    "object": "model",
    "type": "model",
    "display_name": "Tiny Aya Fire",
    "created": 1,
    "owned_by": "api",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": false,
        "tools": true,
        "reasoning": false
    },
    "context_length": 8192,
    "max_output_tokens": 8192
}

{
    "id": "minimax/minimax-m3.1-flash",
    "object": "model",
    "type": "model",
    "display_name": "MiniMax M3.1 Flash",
    "created": 1,
    "owned_by": "minimax",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0.1499999999999999944488848768742172978818416595458984375,
        "output": 0.59999999999999997779553950749686919152736663818359375,
        "cache_read": 0.01499999999999999944488848768742172978818416595458984375
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ],
        "default": "max"
    }
}

{
    "id": "cohere/command-a-plus",
    "object": "model",
    "type": "model",
    "display_name": "Command A+",
    "created": 1,
    "owned_by": "api",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 436000,
    "max_output_tokens": 64000,
    "reasoning_efforts": {
        "levels": [
            "high"
        ],
        "default": "high"
    }
}

{
    "id": "anthropic/claude-opus-4.6",
    "object": "model",
    "type": "model",
    "display_name": "Opus 4.6",
    "created": 1,
    "owned_by": "anthropic",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 5,
        "output": 25,
        "cache_read": 0.5,
        "cache_write": 6.25
    },
    "capabilities": {
        "vision": false,
        "tools": false,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "low",
            "medium",
            "high",
            "max"
        ],
        "default": "medium"
    }
}

{
    "id": "openai/gpt-6-luna",
    "object": "model",
    "type": "model",
    "display_name": "GPT-6 Luna",
    "created": 1,
    "owned_by": "openai",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0.1000000000000000055511151231257827021181583404541015625,
        "output": 0.5,
        "cache_read": 0.01000000000000000020816681711721685132943093776702880859375,
        "cache_write": 0.125
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1050000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ],
        "default": "medium"
    }
}

{
    "id": "google/gemini-3.5-flash",
    "object": "model",
    "type": "model",
    "display_name": "Gemini 3.5 Flash",
    "created": 1,
    "owned_by": "google",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 1.5,
        "output": 9,
        "cache_read": 0.1499999999999999944488848768742172978818416595458984375,
        "cache_write": 0.08329999999999999904520819882236537523567676544189453125
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "low",
            "medium",
            "high"
        ],
        "default": "medium"
    }
}

{
    "id": "anthropic/claude-sonnet-4.5",
    "object": "model",
    "type": "model",
    "display_name": "Sonnet 4.5",
    "created": 1,
    "owned_by": "anthropic",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 3,
        "output": 15,
        "cache_read": 0.299999999999999988897769753748434595763683319091796875,
        "cache_write": 3.75
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "low",
            "high"
        ],
        "default": "low"
    }
}

{
    "id": "google/gemini-3.1-pro",
    "object": "model",
    "type": "model",
    "display_name": "Gemini 3.1 Pro",
    "created": 1,
    "owned_by": "google",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 2,
        "output": 12,
        "cache_read": 0.200000000000000011102230246251565404236316680908203125
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "low",
            "medium",
            "high"
        ],
        "default": "medium"
    }
}

{
    "id": "openai/gpt-5.6-luna",
    "object": "model",
    "type": "model",
    "display_name": "GPT-5.6 Luna",
    "created": 1,
    "owned_by": "openai",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0.1000000000000000055511151231257827021181583404541015625,
        "output": 0.59999999999999997779553950749686919152736663818359375,
        "cache_read": 0.05000000000000000277555756156289135105907917022705078125
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ],
        "default": "medium"
    }
}

{
    "id": "anthropic/claude-sonnet-5",
    "object": "model",
    "type": "model",
    "display_name": "Sonnet 5",
    "created": 1,
    "owned_by": "anthropic",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 2,
        "output": 10,
        "cache_read": 0.200000000000000011102230246251565404236316680908203125,
        "cache_write": 2.5
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ],
        "default": "high"
    }
}

{
    "id": "google/gemini-2.5-flash",
    "object": "model",
    "type": "model",
    "display_name": "Gemini 2.5 Flash",
    "created": 1,
    "owned_by": "google",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0.299999999999999988897769753748434595763683319091796875,
        "output": 2.5,
        "cache_read": 0.0299999999999999988897769753748434595763683319091796875,
        "cache_write": 0.08329999999999999904520819882236537523567676544189453125
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "low",
            "high"
        ],
        "default": "low"
    }
}

{
    "id": "mistralai/mistral-large-4-0",
    "object": "model",
    "type": "model",
    "display_name": "Mistral Large 4",
    "created": 1,
    "owned_by": "mistral",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0.68000000000000004884981308350688777863979339599609375,
        "output": 2.089999999999999857891452847979962825775146484375,
        "cache_read": 0.070000000000000006661338147750939242541790008544921875
    },
    "capabilities": {
        "vision": false,
        "tools": false,
        "reasoning": true
    },
    "context_length": 256000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "none",
            "high"
        ],
        "default": "none"
    }
}

{
    "id": "moonshotai/kimi-k3-agent",
    "object": "model",
    "type": "model",
    "display_name": "Kimi K3 Agent",
    "created": 1,
    "owned_by": "kimi",
    "modality": "chat",
    "access_tier": "premium",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 3,
        "output": 15,
        "cache_read": 0.299999999999999988897769753748434595763683319091796875
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 262144,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "none",
            "low",
            "medium",
            "high",
            "max"
        ],
        "default": "high"
    }
}

{
    "id": "mistralai/mistral-large-2512",
    "object": "model",
    "type": "model",
    "display_name": "Mistral Large 3",
    "created": 1,
    "owned_by": "mistral",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": false
    },
    "context_length": 256000,
    "max_output_tokens": 16384
}

{
    "id": "mistralai/mistral-medium-3.5",
    "object": "model",
    "type": "model",
    "display_name": "Mistral Medium 3.5",
    "created": 1,
    "owned_by": "mistral",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 256000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "none",
            "high"
        ],
        "default": "none"
    }
}

{
    "id": "mistralai/mistral-small-2603",
    "object": "model",
    "type": "model",
    "display_name": "Mistral Small 4",
    "created": 1,
    "owned_by": "mistral",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 256000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "none",
            "high"
        ],
        "default": "none"
    }
}

{
    "id": "mistralai/devstral-medium",
    "object": "model",
    "type": "model",
    "display_name": "Devstral 2",
    "created": 1,
    "owned_by": "mistral",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": false,
        "tools": true,
        "reasoning": false
    },
    "context_length": 256000,
    "max_output_tokens": 16384
}

{
    "id": "anthropic/claude-opus-5.5",
    "object": "model",
    "type": "model",
    "display_name": "Opus 5.5",
    "created": 1,
    "owned_by": "anthropic",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 4,
        "output": 20,
        "cache_read": 0.200000000000000011102230246251565404236316680908203125,
        "cache_write": 5
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ],
        "default": "medium"
    }
}

{
    "id": "mistralai/codestral-2508",
    "object": "model",
    "type": "model",
    "display_name": "Codestral",
    "created": 1,
    "owned_by": "mistral",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": false,
        "tools": true,
        "reasoning": false
    },
    "context_length": 256000,
    "max_output_tokens": 16384
}

{
    "id": "cohere/command-a-translate",
    "object": "model",
    "type": "model",
    "display_name": "Command A Translate",
    "created": 1,
    "owned_by": "api",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": false,
        "tools": true,
        "reasoning": false
    },
    "context_length": 8992,
    "max_output_tokens": 8000
}

{
    "id": "google/gemini-3-flash",
    "object": "model",
    "type": "model",
    "display_name": "Gemini 3 Flash",
    "created": 1,
    "owned_by": "google",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0.75,
        "output": 3.75,
        "cache_read": 0.07499999999999999722444243843710864894092082977294921875
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 65536
}

{
    "id": "minimax/minimax-m2.5",
    "object": "model",
    "type": "model",
    "display_name": "MiniMax M2.5",
    "created": 1,
    "owned_by": "minimax",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0.299999999999999988897769753748434595763683319091796875,
        "output": 1.1999999999999999555910790149937383830547332763671875,
        "cache_read": 0.0299999999999999988897769753748434595763683319091796875,
        "cache_write": 0.375
    },
    "capabilities": {
        "vision": false,
        "tools": true,
        "reasoning": true
    },
    "context_length": 204800,
    "max_output_tokens": 65536
}

{
    "id": "minimax/minimax-m2.1",
    "object": "model",
    "type": "model",
    "display_name": "MiniMax M2.1",
    "created": 1,
    "owned_by": "minimax",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0.299999999999999988897769753748434595763683319091796875,
        "output": 1.1999999999999999555910790149937383830547332763671875,
        "cache_read": 0.0299999999999999988897769753748434595763683319091796875,
        "cache_write": 0.375
    },
    "capabilities": {
        "vision": false,
        "tools": true,
        "reasoning": true
    },
    "context_length": 204800,
    "max_output_tokens": 65536
}

{
    "id": "qwen/qwen3-omni-flash:free",
    "object": "model",
    "type": "model",
    "display_name": "Qwen3 Omni Flash (Free)",
    "created": 1,
    "owned_by": "qwen",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": false
    },
    "context_length": 262144,
    "max_output_tokens": 65536
}

{
    "id": "mistralai/ministral-8b",
    "object": "model",
    "type": "model",
    "display_name": "Ministral 3 8B",
    "created": 1,
    "owned_by": "mistral",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": false
    },
    "context_length": 256000,
    "max_output_tokens": 8192
}

{
    "id": "xiaomi/mimo-v2.6-pro",
    "object": "model",
    "type": "model",
    "display_name": "MiMo v2.6 Pro",
    "created": 1,
    "owned_by": "mimo",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0.434999999999999997779553950749686919152736663818359375,
        "output": 0.86999999999999999555910790149937383830547332763671875,
        "cache_read": 0.003599999999999999901467706564517357037402689456939697265625
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1048576,
    "max_output_tokens": 65536
}

{
    "id": "google/gemini-2.5-pro",
    "object": "model",
    "type": "model",
    "display_name": "Gemini 2.5 Pro",
    "created": 1,
    "owned_by": "google",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 1.25,
        "output": 10,
        "cache_read": 0.125,
        "cache_write": 0.375
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "low",
            "medium",
            "high"
        ],
        "default": "medium"
    }
}

{
    "id": "xiaomi/mimo-v2.6-flash",
    "object": "model",
    "type": "model",
    "display_name": "MiMo v2.6 Flash",
    "created": 1,
    "owned_by": "mimo",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0.14000000000000001332267629550187848508358001708984375,
        "output": 0.2800000000000000266453525910037569701671600341796875,
        "cache_read": 0.0027999999999999999715505349939803636516444385051727294921875
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1048576,
    "max_output_tokens": 65536
}

{
    "id": "anthropic/claude-opus-4.7",
    "object": "model",
    "type": "model",
    "display_name": "Opus 4.7",
    "created": 1,
    "owned_by": "anthropic",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 5,
        "output": 25,
        "cache_read": 0.5,
        "cache_write": 6.25
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ],
        "default": "xhigh"
    }
}

{
    "id": "minimax/minimax-m2.5-highspeed",
    "object": "model",
    "type": "model",
    "display_name": "MiniMax M2.5 Highspeed",
    "created": 1,
    "owned_by": "minimax",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0.59999999999999997779553950749686919152736663818359375,
        "output": 2.399999999999999911182158029987476766109466552734375,
        "cache_read": 0.0299999999999999988897769753748434595763683319091796875,
        "cache_write": 0.375
    },
    "capabilities": {
        "vision": false,
        "tools": true,
        "reasoning": true
    },
    "context_length": 204800,
    "max_output_tokens": 65536
}

{
    "id": "minimax/minimax-m2.1-highspeed",
    "object": "model",
    "type": "model",
    "display_name": "MiniMax M2.1 Highspeed",
    "created": 1,
    "owned_by": "minimax",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0.59999999999999997779553950749686919152736663818359375,
        "output": 2.399999999999999911182158029987476766109466552734375,
        "cache_read": 0.0299999999999999988897769753748434595763683319091796875,
        "cache_write": 0.375
    },
    "capabilities": {
        "vision": false,
        "tools": true,
        "reasoning": true
    },
    "context_length": 204800,
    "max_output_tokens": 65536
}

{
    "id": "minimax/minimax-m2",
    "object": "model",
    "type": "model",
    "display_name": "MiniMax M2",
    "created": 1,
    "owned_by": "minimax",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0.299999999999999988897769753748434595763683319091796875,
        "output": 1.1999999999999999555910790149937383830547332763671875,
        "cache_read": 0.0299999999999999988897769753748434595763683319091796875,
        "cache_write": 0.375
    },
    "capabilities": {
        "vision": false,
        "tools": true,
        "reasoning": true
    },
    "context_length": 204800,
    "max_output_tokens": 65536
}

{
    "id": "xiaomi/mimo-v2.5",
    "object": "model",
    "type": "model",
    "display_name": "MiMo v2.5",
    "created": 1,
    "owned_by": "mimo",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0.14000000000000001332267629550187848508358001708984375,
        "output": 0.2800000000000000266453525910037569701671600341796875,
        "cache_read": 0.0027999999999999999715505349939803636516444385051727294921875
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1050000,
    "max_output_tokens": 65536
}

{
    "id": "qwen/qwen3.6-plus:free",
    "object": "model",
    "type": "model",
    "display_name": "Qwen3.6 Plus (Free)",
    "created": 1,
    "owned_by": "qwen",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 65536
}

{
    "id": "qwen/qwen3.7-max:free",
    "object": "model",
    "type": "model",
    "display_name": "Qwen3.7 Max (Free)",
    "created": 1,
    "owned_by": "qwen",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": false,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 65536
}

{
    "id": "meituan/longcat-2.0",
    "object": "model",
    "type": "model",
    "display_name": "LongCat 2.0",
    "created": 1,
    "owned_by": "opencode-zen",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": false,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1048576,
    "max_output_tokens": 65536
}

{
    "id": "meituan/longcat-2.5-preview:free",
    "object": "model",
    "type": "model",
    "display_name": "LongCat 2.5 Preview (Free)",
    "created": 1,
    "owned_by": "opencode-zen",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": false,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 65536
}

{
    "id": "openai/gpt-5.6-sol",
    "object": "model",
    "type": "model",
    "display_name": "GPT-5.6 Sol",
    "created": 1,
    "owned_by": "openai",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 2,
        "output": 10,
        "cache_read": 0.200000000000000011102230246251565404236316680908203125,
        "cache_write": 2.5
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "low",
            "medium",
            "high",
            "xhigh",
            "max"
        ],
        "default": "medium"
    }
}

{
    "id": "qwen/qwen3.7-plus:free",
    "object": "model",
    "type": "model",
    "display_name": "Qwen3.7 Plus (Free)",
    "created": 1,
    "owned_by": "qwen",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 65536
}

{
    "id": "nvidia/nemotron-3-ultra",
    "object": "model",
    "type": "model",
    "display_name": "Nemotron 3 Ultra",
    "created": 1,
    "owned_by": "nvidia",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0.59999999999999997779553950749686919152736663818359375,
        "output": 2.399999999999999911182158029987476766109466552734375,
        "cache_read": 0.11999999999999999555910790149937383830547332763671875
    },
    "capabilities": {
        "vision": false,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "off",
            "on"
        ],
        "default": "on"
    }
}

{
    "id": "stealth/big-pickle",
    "object": "model",
    "type": "model",
    "display_name": "Big Pickle (Free)",
    "created": 1,
    "owned_by": "stealth",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": false,
        "tools": true,
        "reasoning": true
    },
    "context_length": 200000,
    "max_output_tokens": 65536
}

{
    "id": "qwen/qwen3.5-omni-flash:free",
    "object": "model",
    "type": "model",
    "display_name": "Qwen3.5 Omni Flash (Free)",
    "created": 1,
    "owned_by": "qwen",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": false
    },
    "context_length": 262144,
    "max_output_tokens": 65536
}

{
    "id": "cohere/command-r7b-12-2024",
    "object": "model",
    "type": "model",
    "display_name": "Command R7B (12-2024)",
    "created": 1,
    "owned_by": "api",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": false,
        "tools": true,
        "reasoning": false
    },
    "context_length": 132000,
    "max_output_tokens": 4096
}

{
    "id": "nvidia/nemotron-3-nano-omni",
    "object": "model",
    "type": "model",
    "display_name": "Nemotron 3 Nano Omni",
    "created": 1,
    "owned_by": "nvidia",
    "modality": "chat",
    "access_tier": "paid",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0.05000000000000000277555756156289135105907917022705078125,
        "output": 0.200000000000000011102230246251565404236316680908203125,
        "cache_read": 0.0299999999999999988897769753748434595763683319091796875
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 256000,
    "max_output_tokens": 65536,
    "reasoning_efforts": {
        "levels": [
            "off",
            "on"
        ],
        "default": "on"
    }
}

{
    "id": "qwen/qwen3.8-max:free",
    "object": "model",
    "type": "model",
    "display_name": "Qwen3.8 Max (Free)",
    "created": 1,
    "owned_by": "qwen",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 65536
}

{
    "id": "qwen/qwen3.8-omni-flash:free",
    "object": "model",
    "type": "model",
    "display_name": "Qwen3.8 Omni Flash (Free)",
    "created": 1,
    "owned_by": "qwen",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 65536
}

{
    "id": "qwen/qwen3.7-flash:free",
    "object": "model",
    "type": "model",
    "display_name": "Qwen3.7 Flash (Free)",
    "created": 1,
    "owned_by": "qwen",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 65536
}

{
    "id": "qwen/qwen3.6-max-preview:free",
    "object": "model",
    "type": "model",
    "display_name": "Qwen3.6 Max Preview (Free)",
    "created": 1,
    "owned_by": "qwen",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": false,
        "tools": true,
        "reasoning": true
    },
    "context_length": 262144,
    "max_output_tokens": 65536
}

{
    "id": "qwen/qwen3-coder-plus:free",
    "object": "model",
    "type": "model",
    "display_name": "Qwen3 Coder Plus (Free)",
    "created": 1,
    "owned_by": "qwen",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1048576,
    "max_output_tokens": 65536
}

{
    "id": "cohere/north-small-translate",
    "object": "model",
    "type": "model",
    "display_name": "North Small Translate",
    "created": 1,
    "owned_by": "api",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": false,
        "tools": false,
        "reasoning": false
    },
    "context_length": 32768,
    "max_output_tokens": 16384
}

{
    "id": "qwen/qwen3.6-27b:free",
    "object": "model",
    "type": "model",
    "display_name": "Qwen3.6 27B (Free)",
    "created": 1,
    "owned_by": "qwen",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 262144,
    "max_output_tokens": 65536
}

{
    "id": "qwen/qwen3.5-plus:free",
    "object": "model",
    "type": "model",
    "display_name": "Qwen3.5 Plus (Free)",
    "created": 1,
    "owned_by": "qwen",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 65536
}

{
    "id": "cohere/command-a-vision",
    "object": "model",
    "type": "model",
    "display_name": "Command A Vision",
    "created": 1,
    "owned_by": "api",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": true,
        "tools": false,
        "reasoning": false
    },
    "context_length": 128000,
    "max_output_tokens": 8192
}

{
    "id": "cohere/command-a-reasoning",
    "object": "model",
    "type": "model",
    "display_name": "Command A Reasoning",
    "created": 1,
    "owned_by": "api",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": false,
        "tools": true,
        "reasoning": true
    },
    "context_length": 288768,
    "max_output_tokens": 32768,
    "reasoning_efforts": {
        "levels": [
            "none",
            "high"
        ],
        "default": "high"
    }
}

{
    "id": "qwen/qwen3.5-omni-plus:free",
    "object": "model",
    "type": "model",
    "display_name": "Qwen3.5 Omni Plus (Free)",
    "created": 1,
    "owned_by": "qwen",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": false
    },
    "context_length": 262144,
    "max_output_tokens": 65536
}

{
    "id": "qwen/qwen3.6-35b-a3b:free",
    "object": "model",
    "type": "model",
    "display_name": "Qwen3.6 35B A3B (Free)",
    "created": 1,
    "owned_by": "qwen",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 262144,
    "max_output_tokens": 65536
}

{
    "id": "qwen/qwen3.5-flash:free",
    "object": "model",
    "type": "model",
    "display_name": "Qwen3.5 Flash (Free)",
    "created": 1,
    "owned_by": "qwen",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 1000000,
    "max_output_tokens": 65536
}

{
    "id": "cohere/tiny-aya-water",
    "object": "model",
    "type": "model",
    "display_name": "Tiny Aya Water",
    "created": 1,
    "owned_by": "api",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": false,
        "tools": true,
        "reasoning": false
    },
    "context_length": 8192,
    "max_output_tokens": 8192
}

{
    "id": "qwen/qwen3.5-397b-a17b:free",
    "object": "model",
    "type": "model",
    "display_name": "Qwen3.5 397B A17B (Free)",
    "created": 1,
    "owned_by": "qwen",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 262144,
    "max_output_tokens": 65536
}

{
    "id": "qwen/qwen3-max:free",
    "object": "model",
    "type": "model",
    "display_name": "Qwen3 Max (Free)",
    "created": 1,
    "owned_by": "qwen",
    "modality": "chat",
    "access_tier": "free",
    "pricing": {
        "currency": "USD",
        "unit": "per_1m_tokens",
        "input": 0,
        "output": 0
    },
    "capabilities": {
        "vision": true,
        "tools": true,
        "reasoning": true
    },
    "context_length": 262144,
    "max_output_tokens": 65536
}

{
    "api": "chat",
    "id": "moonshot/kimi-k3.1-pro",
    "object": "model",
    "created": 1792776805,
    "updated": 1792776805,
    "owned_by": "system",
    "input_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-6,
    "caching_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-6,
    "cached_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-7,
    "output_price": 1.0000000000000000818030539140313095458623138256371021270751953125e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-6,
            "caching_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-6,
            "cached_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-7,
            "output_price": 1.0000000000000000818030539140313095458623138256371021270751953125e-5
        }
    ],
    "max_output_tokens": 1048576,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Kimi K3.1 Pro is the first model in the K3.1 series and Kimi's most capable flagship to date, a 3T class model with native visual understanding and a 1M token context window. It brings substantial gains in coding, 3D creation, financial research and modeling, and suits software engineering, knowledge work and deep reasoning.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "open_weights": false,
    "model_lab": "moonshot",
    "model_canonical_name": "kimi-k3.1-pro"
}

{
    "api": "chat",
    "id": "moonshot/kimi-k3.1-pro-highspeed",
    "object": "model",
    "created": 1792776805,
    "updated": 1792776805,
    "owned_by": "system",
    "input_price": 3.9999999999999998189924473035450347424557548947632312774658203125e-6,
    "caching_price": 3.9999999999999998189924473035450347424557548947632312774658203125e-6,
    "cached_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-7,
    "output_price": 2.000000000000000163606107828062619091724627651274204254150390625e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 3.9999999999999998189924473035450347424557548947632312774658203125e-6,
            "caching_price": 3.9999999999999998189924473035450347424557548947632312774658203125e-6,
            "cached_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-7,
            "output_price": 2.000000000000000163606107828062619091724627651274204254150390625e-5
        }
    ],
    "max_output_tokens": 1048576,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Kimi K3.1 Pro Highspeed is the high speed variant of Kimi K3.1 Pro, with the same intelligence and 1M token context window at roughly 3x the output speed. Built for latency sensitive coding agents, interactive assistants and real time knowledge work.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "open_weights": false,
    "model_lab": "moonshot",
    "model_canonical_name": "kimi-k3.1-pro-highspeed"
}

{
    "api": "chat",
    "id": "melious/clef",
    "object": "model",
    "created": 1792594083,
    "updated": 1792594083,
    "owned_by": "system",
    "input_price": 2.3999999999999997855163499753394784619331403519026935100555419921875e-7,
    "output_price": 0,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 2.3999999999999997855163499753394784619331403519026935100555419921875e-7,
            "output_price": 0
        }
    ],
    "max_output_tokens": 0,
    "context_window": 0,
    "supports_caching": false,
    "supports_vision": false,
    "supports_computer_use": false,
    "supports_reasoning": false,
    "supports_image_generation": false,
    "supports_tool_calling": false,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": false,
    "supports_output_json_schema": false,
    "supports_system_mid_conversation": false,
    "description": "",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "",
    "geolocation": "eu",
    "hugging_face_id": "Cloudflare/clef",
    "open_weights": true,
    "model_lab": "cloudflare",
    "model_canonical_name": "clef"
}

{
    "api": "chat",
    "id": "melious/clef-flash",
    "object": "model",
    "created": 1792594083,
    "updated": 1792594083,
    "owned_by": "system",
    "input_price": 8.99999999999999985743080244994518412937622997560538351535797119140625e-8,
    "output_price": 0,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 8.99999999999999985743080244994518412937622997560538351535797119140625e-8,
            "output_price": 0
        }
    ],
    "max_output_tokens": 0,
    "context_window": 0,
    "supports_caching": false,
    "supports_vision": false,
    "supports_computer_use": false,
    "supports_reasoning": false,
    "supports_image_generation": false,
    "supports_tool_calling": false,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": false,
    "supports_output_json_schema": false,
    "supports_system_mid_conversation": false,
    "description": "",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "",
    "geolocation": "eu",
    "hugging_face_id": "Cloudflare/clef-flash",
    "open_weights": true,
    "model_lab": "cloudflare",
    "model_canonical_name": "clef-flash"
}

{
    "api": "chat",
    "id": "minimaxi/minimax-m3.1-flash",
    "object": "model",
    "created": 1792425600,
    "updated": 1792428930,
    "owned_by": "system",
    "input_price": 1.4999999999999999321221677388293880284209080855362117290496826171875e-7,
    "cached_price": 1.4999999999999998659477187345871740387082127199391834437847137451171875e-8,
    "output_price": 5.99999999999999972848867095531755211368363234214484691619873046875e-7,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.4999999999999999321221677388293880284209080855362117290496826171875e-7,
            "cached_price": 1.4999999999999998659477187345871740387082127199391834437847137451171875e-8,
            "output_price": 5.99999999999999972848867095531755211368363234214484691619873046875e-7
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "MiniMax M3.1 Flash is a fast multimodal model in the MiniMax M3 family, built for agentic cowork automation, coding and visual tasks. It scores 72.5% on AutomationBench AA (best among open models), 73.67% on DeepSWE, 91.0 on BabyVision with tools, 82.5 on CharXiv RQ, 56% on AA Omniscience and 48% on HLE. Supports image input, tool calling, structured JSON output, reasoning and prompt caching. Ideal for multi step workflows, coding agents, frontend and presentation generation, and professional analysis at low cost.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "https://platform.minimax.io/docs/guides/text-generation",
    "geolocation": "global",
    "open_weights": false,
    "model_lab": "minimax",
    "model_canonical_name": "minimax-m3.1-flash"
}

{
    "api": "chat",
    "id": "tensorx/minimax-m3.1-flash",
    "object": "model",
    "created": 1792425600,
    "updated": 1792922068,
    "owned_by": "system",
    "input_price": 2.999999999999999864244335477658776056841816171072423458099365234375e-7,
    "cached_price": 7.00000000000000047733017083211037867584991545299999415874481201171875e-8,
    "output_price": 1.19999999999999994569773419106351042273672646842896938323974609375e-6,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 2.999999999999999864244335477658776056841816171072423458099365234375e-7,
            "cached_price": 7.00000000000000047733017083211037867584991545299999415874481201171875e-8,
            "output_price": 1.19999999999999994569773419106351042273672646842896938323974609375e-6
        }
    ],
    "max_output_tokens": 1048576,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "MiniMax M3.1 Flash is a fast multimodal model in the MiniMax M3 family, built for agentic cowork automation, coding and visual tasks. It scores 72.5% on AutomationBench AA (best among open models), 73.67% on DeepSWE, 91.0 on BabyVision with tools, 82.5 on CharXiv RQ, 56% on AA Omniscience and 48% on HLE. Supports image input, tool calling, structured JSON output, reasoning and prompt caching. Ideal for multi step workflows, coding agents, frontend and presentation generation, and professional analysis at low cost.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "No training on user data",
    "geolocation": "eu",
    "open_weights": false,
    "model_lab": "minimax",
    "model_canonical_name": "minimax-m3.1-flash"
}

{
    "api": "chat",
    "id": "deepinfra/deepseek-v4.1-flash-1017",
    "object": "model",
    "created": 1792195200,
    "updated": 1792266280,
    "owned_by": "system",
    "input_price": 9.800000000000000403564443147985674187339100171811878681182861328125e-8,
    "cached_price": 2.9400000000000001872437819486379162459144254171405918896198272705078125e-9,
    "output_price": 2.9400000000000001210693329443957022562017300515435636043548583984375e-7,
    "discount_percentage": 51,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 9.800000000000000403564443147985674187339100171811878681182861328125e-8,
            "cached_price": 2.9400000000000001872437819486379162459144254171405918896198272705078125e-9,
            "output_price": 2.9400000000000001210693329443957022562017300515435636043548583984375e-7
        }
    ],
    "max_output_tokens": 0,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "DeepSeek V4.1 Flash 1017 is a minor update to DeepSeek V4.1 Flash with substantial gains in reasoning, coding, agentic tasks and visual benchmarks, plus shorter outputs and faster task completion. 552B parameter Mixture of Experts with native vision, 1M token context, thinking and non thinking modes, tool calling, structured JSON output and prompt caching. Served on DeepInfra in FP8 with zero retention. Open weights on Hugging Face.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "quantization": "fp8",
    "hugging_face_id": "deepseek-ai/DeepSeek-V4.1-Flash-1017",
    "open_weights": true,
    "model_lab": "deepseek",
    "model_canonical_name": "deepseek-v4.1-flash-1017"
}

{
    "api": "chat",
    "id": "deepinfra/deepseek-v4.1-flash-1017:priority",
    "object": "model",
    "created": 1792195200,
    "updated": 1792311466,
    "owned_by": "system",
    "input_price": 1.47000000000000006053466647219785112810086502577178180217742919921875e-7,
    "cached_price": 4.41000000000000028086567292295687436887163812571088783442974090576171875e-9,
    "output_price": 4.409999999999999916906203399624697425451813614927232265472412109375e-7,
    "discount_percentage": 51,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.47000000000000006053466647219785112810086502577178180217742919921875e-7,
            "cached_price": 4.41000000000000028086567292295687436887163812571088783442974090576171875e-9,
            "output_price": 4.409999999999999916906203399624697425451813614927232265472412109375e-7
        }
    ],
    "max_output_tokens": 0,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "DeepSeek V4.1 Flash 1017 is a minor update to DeepSeek V4.1 Flash with substantial gains in reasoning, coding, agentic tasks and visual benchmarks, plus shorter outputs and faster task completion. 552B parameter Mixture of Experts with native vision, 1M token context, thinking and non thinking modes, tool calling, structured JSON output and prompt caching. Served on DeepInfra in FP8 with zero retention. Open weights on Hugging Face. Priority service tier at 1.5x standard pricing.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "quantization": "fp8",
    "hugging_face_id": "deepseek-ai/DeepSeek-V4.1-Flash-1017",
    "open_weights": true,
    "model_lab": "deepseek",
    "model_canonical_name": "deepseek-v4.1-flash-1017"
}

{
    "api": "chat",
    "id": "deepseek/deepseek-v4.1-flash-1017",
    "object": "model",
    "created": 1792195200,
    "updated": 1792229020,
    "owned_by": "system",
    "input_price": 2.999999999999999864244335477658776056841816171072423458099365234375e-7,
    "cached_price": 5.99999999999999996009924247016530107767806612173444591462612152099609375e-9,
    "output_price": 1.19999999999999994569773419106351042273672646842896938323974609375e-6,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 2.999999999999999864244335477658776056841816171072423458099365234375e-7,
            "cached_price": 5.99999999999999996009924247016530107767806612173444591462612152099609375e-9,
            "output_price": 1.19999999999999994569773419106351042273672646842896938323974609375e-6
        }
    ],
    "max_output_tokens": 384000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": true,
    "supports_output_json_object": true,
    "supports_output_json_schema": false,
    "supports_system_mid_conversation": true,
    "description": "DeepSeek V4.1 Flash 1017 is the October 2026 refresh of DeepSeek V4.1 Flash, a 552B parameter Mixture of Experts model with native vision. 1M token context, 384K max output, thinking and non thinking modes, tool calling, JSON output, prompt caching and web search. Off peak pricing at half the peak rate (peak 01:00 to 04:00 and 06:00 to 10:00 UTC, Monday to Friday). Open weights on Hugging Face.",
    "data_retention": true,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "No online information",
    "geolocation": "global",
    "hugging_face_id": "deepseek-ai/DeepSeek-V4.1-Flash-1017",
    "open_weights": true,
    "model_lab": "deepseek",
    "model_canonical_name": "deepseek-v4.1-flash-1017"
}

{
    "api": "chat",
    "id": "fireworks/deepseek-v4.1-flash-1017",
    "object": "model",
    "created": 1792195200,
    "updated": 1792311228,
    "owned_by": "system",
    "input_price": 2.999999999999999864244335477658776056841816171072423458099365234375e-7,
    "cached_price": 5.99999999999999996009924247016530107767806612173444591462612152099609375e-9,
    "output_price": 1.19999999999999994569773419106351042273672646842896938323974609375e-6,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 2.999999999999999864244335477658776056841816171072423458099365234375e-7,
            "cached_price": 5.99999999999999996009924247016530107767806612173444591462612152099609375e-9,
            "output_price": 1.19999999999999994569773419106351042273672646842896938323974609375e-6
        }
    ],
    "max_output_tokens": 131072,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "DeepSeek V4.1 Flash 1017 is a minor update to DeepSeek V4.1 Flash with substantial gains in reasoning, coding, agentic tasks and visual benchmarks, plus shorter outputs and faster task completion. Mixture of Experts with native vision, 1M token context, tool calling and structured outputs. Served serverless on Fireworks.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "hugging_face_id": "deepseek-ai/DeepSeek-V4.1-Flash-1017",
    "open_weights": true,
    "model_lab": "deepseek",
    "model_canonical_name": "deepseek-v4.1-flash-1017"
}

{
    "api": "chat",
    "id": "melious/deepseek-v4.1-flash-1017",
    "object": "model",
    "created": 1792195200,
    "updated": 1792413840,
    "owned_by": "system",
    "input_price": 2.29999999999999994886021640293216616868221535696648061275482177734375e-7,
    "cached_price": 2.000000000000000041845121660256945350653268178575672209262847900390625e-8,
    "output_price": 1.1400000000000000966436132510128942385563277639448642730712890625e-6,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 2.29999999999999994886021640293216616868221535696648061275482177734375e-7,
            "cached_price": 2.000000000000000041845121660256945350653268178575672209262847900390625e-8,
            "output_price": 1.1400000000000000966436132510128942385563277639448642730712890625e-6
        }
    ],
    "max_output_tokens": 384000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": false,
    "supports_system_mid_conversation": false,
    "description": "DeepSeek V4.1 Flash is a 552B MoE hybrid reasoning model with image input and a 1M token context, suited for agentic coding and long context work. Served from the EU by Melious.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "EU only inference (Finland, Ireland), no prompt or response logging, no training on customer data.",
    "geolocation": "eu",
    "hugging_face_id": "deepseek-ai/DeepSeek-V4.1-Flash-1017",
    "open_weights": true,
    "model_lab": "deepseek",
    "model_canonical_name": "deepseek-v4.1-flash-1017"
}

{
    "api": "chat",
    "id": "runware/deepseek-v4.1-flash-1017",
    "object": "model",
    "created": 1792195200,
    "updated": 1792592720,
    "owned_by": "system",
    "input_price": 1.4999999999999999321221677388293880284209080855362117290496826171875e-7,
    "cached_price": 1.0000000000000000209225608301284726753266340892878361046314239501953125e-8,
    "output_price": 5.99999999999999972848867095531755211368363234214484691619873046875e-7,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.4999999999999999321221677388293880284209080855362117290496826171875e-7,
            "cached_price": 1.0000000000000000209225608301284726753266340892878361046314239501953125e-8,
            "output_price": 5.99999999999999972848867095531755211368363234214484691619873046875e-7
        }
    ],
    "max_output_tokens": 384000,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "DeepSeek V4.1 Flash 1017 is the October 2026 checkpoint of DeepSeek V4.1 Flash, a multimodal mixture of experts model for coding, reasoning, visual understanding and tool using agents. It reads text and images, writes text, and combines a 1M token context window with adjustable reasoning effort and tool calls. Suited for large codebase work, document analysis, research and long running agentic tasks.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "hugging_face_id": "deepseek-ai/DeepSeek-V4.1-Flash-1017",
    "open_weights": true,
    "model_lab": "deepseek",
    "model_canonical_name": "deepseek-v4.1-flash-1017"
}

{
    "api": "chat",
    "id": "sference/deepseek-v4.1-flash-1017",
    "object": "model",
    "created": 1792195200,
    "updated": 1792240911,
    "owned_by": "system",
    "input_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-7,
    "cached_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-8,
    "output_price": 1.5000000000000000380012861456169304119612206704914569854736328125e-6,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-7,
            "cached_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-8,
            "output_price": 1.5000000000000000380012861456169304119612206704914569854736328125e-6
        }
    ],
    "max_output_tokens": 393216,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "DeepSeek V4.1 Flash 1017 is the October 2026 refresh of DeepSeek V4.1 Flash, a 552B parameter Mixture of Experts model with native vision. 1M token context window, 384K max output, thinking and non thinking modes, tool calling, structured JSON output and prompt caching. Served in the EU via Sference at $0.50 input, $0.05 cache read and $1.50 output per 1M tokens, with no data retention and no training on user data. Open weights on Hugging Face.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "No training on user data",
    "geolocation": "eu",
    "hugging_face_id": "deepseek-ai/DeepSeek-V4.1-Flash-1017",
    "open_weights": true,
    "model_lab": "deepseek",
    "model_canonical_name": "deepseek-v4.1-flash-1017"
}

{
    "api": "chat",
    "id": "tensorx/deepseek-v4.1-flash-1017",
    "object": "model",
    "created": 1792195200,
    "updated": 1792266064,
    "owned_by": "system",
    "input_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-7,
    "cached_price": 1.29999999999999999411210457704590748306827663327567279338836669921875e-7,
    "output_price": 1.5000000000000000380012861456169304119612206704914569854736328125e-6,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-7,
            "cached_price": 1.29999999999999999411210457704590748306827663327567279338836669921875e-7,
            "output_price": 1.5000000000000000380012861456169304119612206704914569854736328125e-6
        }
    ],
    "max_output_tokens": 65536,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "DeepSeek V4.1 Flash 1017 is the October 2026 refresh of DeepSeek V4.1 Flash, a 552B parameter Mixture of Experts model with native vision. 1M token context window, 64K max output, thinking and non thinking modes, tool calling, structured JSON output and prompt caching. Served in the EU via TensorX on NVIDIA B300s at $0.50 input, $0.13 cache read and $1.50 output per 1M tokens, with zero data retention and no training on user data. Open weights on Hugging Face.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "No training on user data",
    "geolocation": "eu",
    "hugging_face_id": "deepseek-ai/DeepSeek-V4.1-Flash-1017",
    "open_weights": true,
    "model_lab": "deepseek",
    "model_canonical_name": "deepseek-v4.1-flash-1017"
}

{
    "api": "chat",
    "id": "together/deepseek-v4.1-flash-1017",
    "object": "model",
    "created": 1792195200,
    "updated": 1792408811,
    "owned_by": "system",
    "input_price": 2.999999999999999864244335477658776056841816171072423458099365234375e-7,
    "cached_price": 5.99999999999999996009924247016530107767806612173444591462612152099609375e-9,
    "output_price": 1.19999999999999994569773419106351042273672646842896938323974609375e-6,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 2.999999999999999864244335477658776056841816171072423458099365234375e-7,
            "cached_price": 5.99999999999999996009924247016530107767806612173444591462612152099609375e-9,
            "output_price": 1.19999999999999994569773419106351042273672646842896938323974609375e-6
        }
    ],
    "max_output_tokens": 0,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "DeepSeek V4.1 Flash 1017 is a minor update to DeepSeek V4.1 Flash with substantial gains in reasoning, coding, agentic tasks and visual benchmarks, plus shorter outputs and faster task completion. 552B parameter Mixture of Experts with native vision, 1M token context, thinking and non thinking modes, tool calling, structured JSON output and prompt caching. Served on DeepInfra in FP8 with zero retention. Open weights on Hugging Face.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "hugging_face_id": "deepseek-ai/DeepSeek-V4.1-Flash-1017",
    "open_weights": true,
    "model_lab": "deepseek",
    "model_canonical_name": "deepseek-v4.1-flash-1017"
}

{
    "api": "chat",
    "id": "fireworks/muse-spark-open",
    "object": "model",
    "created": 1792022400,
    "updated": 1792090822,
    "owned_by": "system",
    "input_price": 1.250000000000000102253817392539136932327892282046377658843994140625e-6,
    "cached_price": 1.4999999999999999321221677388293880284209080855362117290496826171875e-7,
    "output_price": 4.249999999999999966498152870197912989169708453118801116943359375e-6,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.250000000000000102253817392539136932327892282046377658843994140625e-6,
            "cached_price": 1.4999999999999999321221677388293880284209080855362117290496826171875e-7,
            "output_price": 4.249999999999999966498152870197912989169708453118801116943359375e-6
        }
    ],
    "max_output_tokens": 131072,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": false,
    "supports_system_mid_conversation": true,
    "description": "Muse Spark Open is an open weights reasoning model from Meta optimized for agentic coding, with reliable tool calling, deep codebase understanding and native image understanding. Sparse MoE with 816B total and 42B active parameters, 1M token context.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "hugging_face_id": "meta-models/Muse-Spark-Open-816B-A42B",
    "open_weights": true,
    "model_lab": "meta",
    "model_canonical_name": "muse-spark-open"
}

{
    "api": "chat",
    "id": "together/muse-spark-open",
    "object": "model",
    "created": 1792022400,
    "updated": 1792090822,
    "owned_by": "system",
    "input_price": 1.250000000000000102253817392539136932327892282046377658843994140625e-6,
    "cached_price": 1.4999999999999999321221677388293880284209080855362117290496826171875e-7,
    "output_price": 4.249999999999999966498152870197912989169708453118801116943359375e-6,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.250000000000000102253817392539136932327892282046377658843994140625e-6,
            "cached_price": 1.4999999999999999321221677388293880284209080855362117290496826171875e-7,
            "output_price": 4.249999999999999966498152870197912989169708453118801116943359375e-6
        }
    ],
    "max_output_tokens": 131072,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": false,
    "supports_system_mid_conversation": true,
    "description": "Muse Spark Open is an open weights reasoning model from Meta optimized for agentic coding, with reliable tool calling, deep codebase understanding and native image understanding. Sparse MoE with 816B total and 42B active parameters, 1M token context.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "hugging_face_id": "meta-models/Muse-Spark-Open-816B-A42B",
    "open_weights": true,
    "model_lab": "meta",
    "model_canonical_name": "muse-spark-open"
}

{
    "api": "chat",
    "id": "typesafe/jev-1.14.0",
    "object": "model",
    "created": 1792016361,
    "updated": 1792016361,
    "owned_by": "system",
    "input_price": 4.199999999999999889351408473812943267233777078217826783657073974609375e-8,
    "output_price": 0,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 4.199999999999999889351408473812943267233777078217826783657073974609375e-8,
            "output_price": 0
        }
    ],
    "max_output_tokens": 1024,
    "context_window": 64000,
    "supports_caching": false,
    "supports_vision": false,
    "supports_computer_use": false,
    "supports_reasoning": false,
    "supports_image_generation": false,
    "supports_tool_calling": false,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": false,
    "supports_output_json_schema": false,
    "supports_system_mid_conversation": true,
    "description": "Jev is TypeSafe’s flagship model and the first System One model.",
    "data_retention": true,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "Data retention period is not specified",
    "geolocation": "global",
    "open_weights": false,
    "model_lab": "typesafe",
    "model_canonical_name": "jev"
}

{
    "api": "chat",
    "id": "vertex/gemini-4-argon",
    "object": "model",
    "created": 1791849600,
    "updated": 1791908436,
    "owned_by": "system",
    "input_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-6,
    "cached_price": 9.99999999999999954748111825886258685613938723690807819366455078125e-8,
    "output_price": 1.0000000000000000818030539140313095458623138256371021270751953125e-5,
    "discount_percentage": 50,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-6,
            "cached_price": 9.99999999999999954748111825886258685613938723690807819366455078125e-8,
            "output_price": 1.0000000000000000818030539140313095458623138256371021270751953125e-5
        }
    ],
    "max_output_tokens": 65536,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": true,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Gemini 4 Argon is Google's frontier model for deep work on complex, real world tasks across coding, finance, legal, cybersecurity and science. It sustains long multi step workflows with strong reasoning and multimodal understanding over a 1M token context.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "open_weights": false,
    "model_lab": "google",
    "model_canonical_name": "gemini-4-argon"
}

{
    "api": "chat",
    "id": "vertex/gemini-4-argon@eu",
    "object": "model",
    "created": 1791849600,
    "updated": 1791908436,
    "owned_by": "system",
    "input_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-6,
    "cached_price": 1.10000000000000005610204141526242693771564518101513385772705078125e-7,
    "output_price": 1.099999999999999971398746689832393030883395113050937652587890625e-5,
    "discount_percentage": 50,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-6,
            "cached_price": 1.10000000000000005610204141526242693771564518101513385772705078125e-7,
            "output_price": 1.099999999999999971398746689832393030883395113050937652587890625e-5
        }
    ],
    "max_output_tokens": 65536,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": true,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Gemini 4 Argon is Google's frontier model for deep work on complex, real world tasks across coding, finance, legal, cybersecurity and science. It sustains long multi step workflows with strong reasoning and multimodal understanding over a 1M token context.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "eu",
    "open_weights": false,
    "model_lab": "google",
    "model_canonical_name": "gemini-4-argon"
}

{
    "api": "chat",
    "id": "meta/muse-spark-1.3",
    "object": "model",
    "created": 1791763200,
    "updated": 1791885044,
    "owned_by": "system",
    "input_price": 1.250000000000000102253817392539136932327892282046377658843994140625e-6,
    "cached_price": 1.4999999999999999321221677388293880284209080855362117290496826171875e-7,
    "output_price": 4.249999999999999966498152870197912989169708453118801116943359375e-6,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.250000000000000102253817392539136932327892282046377658843994140625e-6,
            "cached_price": 1.4999999999999999321221677388293880284209080855362117290496826171875e-7,
            "output_price": 4.249999999999999966498152870197912989169708453118801116943359375e-6
        }
    ],
    "max_output_tokens": 943718,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": true,
    "supports_web_search": true,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Muse Spark 1.3 is a reasoning model from Meta built for long horizon coding and multi step agentic work, with improved tool, browser and computer use, native tool calling and MCP support, and fewer tokens than 1.2. It accepts text, images, video and PDF documents with a 1M token context and returns text.",
    "data_retention": true,
    "data_retention_days": 30,
    "data_used_for_training": false,
    "privacy_comments": "Meta Model API Terms of Service apply.",
    "geolocation": "global",
    "open_weights": false,
    "model_lab": "meta",
    "model_canonical_name": "muse-spark-1.3"
}

{
    "api": "chat",
    "id": "meta/muse-wonder-1.0",
    "object": "model",
    "created": 1791763200,
    "updated": 1791885044,
    "owned_by": "system",
    "input_price": 3.9999999999999998189924473035450347424557548947632312774658203125e-6,
    "cached_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-7,
    "output_price": 2.000000000000000163606107828062619091724627651274204254150390625e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 3.9999999999999998189924473035450347424557548947632312774658203125e-6,
            "cached_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-7,
            "output_price": 2.000000000000000163606107828062619091724627651274204254150390625e-5
        }
    ],
    "max_output_tokens": 943718,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": true,
    "supports_web_search": true,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Muse Wonder is a frontier reasoning model from Meta, built for complex personal and professional agentic tasks such as coding, research, legal, finance and health work. It accepts text, images, video, audio and PDF documents with a 1M token context and returns text.",
    "data_retention": true,
    "data_retention_days": 30,
    "data_used_for_training": false,
    "privacy_comments": "Meta Model API Terms of Service apply.",
    "geolocation": "global",
    "open_weights": false,
    "model_lab": "meta",
    "model_canonical_name": "muse-wonder-1.0"
}

{
    "api": "chat",
    "id": "azure/decision-1",
    "object": "model",
    "created": 1791504000,
    "updated": 1791708608,
    "owned_by": "system",
    "input_price": 4.199999999999999889351408473812943267233777078217826783657073974609375e-8,
    "cached_price": 0,
    "output_price": 0,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 4.199999999999999889351408473812943267233777078217826783657073974609375e-8,
            "cached_price": 0,
            "output_price": 0
        }
    ],
    "max_output_tokens": 1024,
    "context_window": 32768,
    "supports_caching": false,
    "supports_vision": false,
    "supports_computer_use": false,
    "supports_reasoning": false,
    "supports_image_generation": false,
    "supports_tool_calling": false,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": false,
    "supports_output_json_schema": false,
    "supports_system_mid_conversation": true,
    "description": "Microsoft-Decision-1 is a small decision model post trained from Qwen3.5-9B. Instead of generating text it reads the provided state and returns a calibrated probability for each fixed answer option, for classification, routing, prioritization, verification, agent guardrails and AI judging.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "us",
    "open_weights": false,
    "model_lab": "microsoft",
    "model_canonical_name": "microsoft-decision-1"
}

{
    "api": "chat",
    "id": "azure/decision-1@francecentral",
    "object": "model",
    "created": 1791504000,
    "updated": 1791708737,
    "owned_by": "system",
    "input_price": 4.199999999999999889351408473812943267233777078217826783657073974609375e-8,
    "cached_price": 0,
    "output_price": 0,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 4.199999999999999889351408473812943267233777078217826783657073974609375e-8,
            "cached_price": 0,
            "output_price": 0
        }
    ],
    "max_output_tokens": 1024,
    "context_window": 32768,
    "supports_caching": false,
    "supports_vision": false,
    "supports_computer_use": false,
    "supports_reasoning": false,
    "supports_image_generation": false,
    "supports_tool_calling": false,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": false,
    "supports_output_json_schema": false,
    "supports_system_mid_conversation": true,
    "description": "Microsoft-Decision-1 is a small decision model post trained from Qwen3.5-9B. Instead of generating text it reads the provided state and returns a calibrated probability for each fixed answer option, for classification, routing, prioritization, verification, agent guardrails and AI judging.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "eu",
    "open_weights": false,
    "model_lab": "microsoft",
    "model_canonical_name": "microsoft-decision-1"
}

{
    "api": "chat",
    "id": "azure/decision-1@swedencentral",
    "object": "model",
    "created": 1791504000,
    "updated": 1791708737,
    "owned_by": "system",
    "input_price": 4.199999999999999889351408473812943267233777078217826783657073974609375e-8,
    "cached_price": 0,
    "output_price": 0,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 4.199999999999999889351408473812943267233777078217826783657073974609375e-8,
            "cached_price": 0,
            "output_price": 0
        }
    ],
    "max_output_tokens": 1024,
    "context_window": 32768,
    "supports_caching": false,
    "supports_vision": false,
    "supports_computer_use": false,
    "supports_reasoning": false,
    "supports_image_generation": false,
    "supports_tool_calling": false,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": false,
    "supports_output_json_schema": false,
    "supports_system_mid_conversation": true,
    "description": "Microsoft-Decision-1 is a small decision model post trained from Qwen3.5-9B. Instead of generating text it reads the provided state and returns a calibrated probability for each fixed answer option, for classification, routing, prioritization, verification, agent guardrails and AI judging.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "eu",
    "open_weights": false,
    "model_lab": "microsoft",
    "model_canonical_name": "microsoft-decision-1"
}

{
    "api": "chat",
    "id": "deepinfra/step-5-preview",
    "object": "model",
    "created": 1791417600,
    "updated": 1792140707,
    "owned_by": "system",
    "input_price": 9.99999999999999954748111825886258685613938723690807819366455078125e-7,
    "cached_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-8,
    "output_price": 2.69999999999999998369902033668044083469794713892042636871337890625e-6,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 9.99999999999999954748111825886258685613938723690807819366455078125e-7,
            "cached_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-8,
            "output_price": 2.69999999999999998369902033668044083469794713892042636871337890625e-6
        }
    ],
    "max_output_tokens": 65536,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Step 5 Preview is StepFun's flagship model for agentic work, a sparse Mixture-of-Experts model with 600B total and 27B active parameters, a 1M token context window, and text and image input. It is built for software engineering, long horizon agentic execution with repeated tool calls, and professional knowledge work, with particular strength in finance.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "quantization": "fp8",
    "hugging_face_id": "stepfun-ai/Step-5-Preview",
    "open_weights": true,
    "model_lab": "stepfun",
    "model_canonical_name": "step-5-preview"
}

{
    "api": "chat",
    "id": "anthropic/claude-haiku-5-5",
    "object": "model",
    "created": 1791331200,
    "updated": 1791391588,
    "owned_by": "system",
    "input_price": 9.99999999999999954748111825886258685613938723690807819366455078125e-8,
    "caching_price": 1.29999999999999999411210457704590748306827663327567279338836669921875e-7,
    "cached_price": 1.0000000000000000209225608301284726753266340892878361046314239501953125e-8,
    "output_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-7,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 9.99999999999999954748111825886258685613938723690807819366455078125e-8,
            "caching_price": 1.29999999999999999411210457704590748306827663327567279338836669921875e-7,
            "caching_5m_price": 1.29999999999999999411210457704590748306827663327567279338836669921875e-7,
            "caching_1h_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-7,
            "cached_price": 1.0000000000000000209225608301284726753266340892878361046314239501953125e-8,
            "output_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-7
        },
        {
            "prompt_tokens_threshold": 100000,
            "input_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-7,
            "caching_price": 6.300000000000000032550459723446056869988751714117825031280517578125e-7,
            "caching_5m_price": 6.300000000000000032550459723446056869988751714117825031280517578125e-7,
            "caching_1h_price": 9.99999999999999954748111825886258685613938723690807819366455078125e-7,
            "cached_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-8,
            "output_price": 2.50000000000000020450763478507827386465578456409275531768798828125e-6
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": true,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Claude Haiku 5.5 is the fastest model in the Claude 5.5 family, built for high volume, speed sensitive workloads. It is much stronger than Haiku 4.5 and is the first Haiku with effort levels to control how much it thinks.",
    "data_retention": true,
    "data_retention_days": 30,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "open_weights": false,
    "model_lab": "anthropic",
    "model_canonical_name": "claude-haiku-5-5"
}

{
    "api": "chat",
    "id": "bedrock/claude-haiku-5-5",
    "object": "model",
    "created": 1791331200,
    "updated": 1791391588,
    "owned_by": "system",
    "input_price": 9.99999999999999954748111825886258685613938723690807819366455078125e-8,
    "caching_price": 1.29999999999999999411210457704590748306827663327567279338836669921875e-7,
    "cached_price": 1.0000000000000000209225608301284726753266340892878361046314239501953125e-8,
    "output_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-7,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 9.99999999999999954748111825886258685613938723690807819366455078125e-8,
            "caching_price": 1.29999999999999999411210457704590748306827663327567279338836669921875e-7,
            "caching_5m_price": 1.29999999999999999411210457704590748306827663327567279338836669921875e-7,
            "caching_1h_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-7,
            "cached_price": 1.0000000000000000209225608301284726753266340892878361046314239501953125e-8,
            "output_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-7
        },
        {
            "prompt_tokens_threshold": 100000,
            "input_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-7,
            "caching_price": 6.300000000000000032550459723446056869988751714117825031280517578125e-7,
            "caching_5m_price": 6.300000000000000032550459723446056869988751714117825031280517578125e-7,
            "caching_1h_price": 9.99999999999999954748111825886258685613938723690807819366455078125e-7,
            "cached_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-8,
            "output_price": 2.50000000000000020450763478507827386465578456409275531768798828125e-6
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Claude Haiku 5.5 is the fastest model in the Claude 5.5 family, built for high volume, speed sensitive workloads. It is much stronger than Haiku 4.5 and is the first Haiku with effort levels to control how much it thinks.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html",
    "geolocation": "global",
    "open_weights": false,
    "model_lab": "anthropic",
    "model_canonical_name": "claude-haiku-5-5"
}

{
    "api": "chat",
    "id": "bedrock/claude-haiku-5-5@eu-central-1",
    "object": "model",
    "created": 1791331200,
    "updated": 1791410369,
    "owned_by": "system",
    "input_price": 1.10000000000000005610204141526242693771564518101513385772705078125e-7,
    "caching_price": 1.40000000000000009546603416642207573516998309059999883174896240234375e-7,
    "cached_price": 2.000000000000000041845121660256945350653268178575672209262847900390625e-8,
    "output_price": 5.50000000000000028051020707631213468857822590507566928863525390625e-7,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.10000000000000005610204141526242693771564518101513385772705078125e-7,
            "caching_price": 1.40000000000000009546603416642207573516998309059999883174896240234375e-7,
            "caching_5m_price": 1.40000000000000009546603416642207573516998309059999883174896240234375e-7,
            "caching_1h_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
            "cached_price": 2.000000000000000041845121660256945350653268178575672209262847900390625e-8,
            "output_price": 5.50000000000000028051020707631213468857822590507566928863525390625e-7
        },
        {
            "prompt_tokens_threshold": 100000,
            "input_price": 5.50000000000000028051020707631213468857822590507566928863525390625e-7,
            "caching_price": 6.89999999999999958188285319182764254719586460851132869720458984375e-7,
            "caching_5m_price": 6.89999999999999958188285319182764254719586460851132869720458984375e-7,
            "caching_1h_price": 1.10000000000000005610204141526242693771564518101513385772705078125e-6,
            "cached_price": 5.99999999999999946379087493834869615483285087975673377513885498046875e-8,
            "output_price": 2.7499999999999999284968667245809825772084877826273441314697265625e-6
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Claude Haiku 5.5 is the fastest model in the Claude 5.5 family, built for high volume, speed sensitive workloads. It is much stronger than Haiku 4.5 and is the first Haiku with effort levels to control how much it thinks.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html",
    "geolocation": "eu",
    "open_weights": false,
    "model_lab": "anthropic",
    "model_canonical_name": "claude-haiku-5-5"
}

{
    "api": "chat",
    "id": "bedrock/claude-haiku-5-5@eu-north-1",
    "object": "model",
    "created": 1791331200,
    "updated": 1791410369,
    "owned_by": "system",
    "input_price": 1.10000000000000005610204141526242693771564518101513385772705078125e-7,
    "caching_price": 1.40000000000000009546603416642207573516998309059999883174896240234375e-7,
    "cached_price": 2.000000000000000041845121660256945350653268178575672209262847900390625e-8,
    "output_price": 5.50000000000000028051020707631213468857822590507566928863525390625e-7,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.10000000000000005610204141526242693771564518101513385772705078125e-7,
            "caching_price": 1.40000000000000009546603416642207573516998309059999883174896240234375e-7,
            "caching_5m_price": 1.40000000000000009546603416642207573516998309059999883174896240234375e-7,
            "caching_1h_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
            "cached_price": 2.000000000000000041845121660256945350653268178575672209262847900390625e-8,
            "output_price": 5.50000000000000028051020707631213468857822590507566928863525390625e-7
        },
        {
            "prompt_tokens_threshold": 100000,
            "input_price": 5.50000000000000028051020707631213468857822590507566928863525390625e-7,
            "caching_price": 6.89999999999999958188285319182764254719586460851132869720458984375e-7,
            "caching_5m_price": 6.89999999999999958188285319182764254719586460851132869720458984375e-7,
            "caching_1h_price": 1.10000000000000005610204141526242693771564518101513385772705078125e-6,
            "cached_price": 5.99999999999999946379087493834869615483285087975673377513885498046875e-8,
            "output_price": 2.7499999999999999284968667245809825772084877826273441314697265625e-6
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Claude Haiku 5.5 is the fastest model in the Claude 5.5 family, built for high volume, speed sensitive workloads. It is much stronger than Haiku 4.5 and is the first Haiku with effort levels to control how much it thinks.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html",
    "geolocation": "eu",
    "open_weights": false,
    "model_lab": "anthropic",
    "model_canonical_name": "claude-haiku-5-5"
}

{
    "api": "chat",
    "id": "bedrock/claude-haiku-5-5@eu-west-1",
    "object": "model",
    "created": 1791331200,
    "updated": 1791410369,
    "owned_by": "system",
    "input_price": 1.10000000000000005610204141526242693771564518101513385772705078125e-7,
    "caching_price": 1.40000000000000009546603416642207573516998309059999883174896240234375e-7,
    "cached_price": 2.000000000000000041845121660256945350653268178575672209262847900390625e-8,
    "output_price": 5.50000000000000028051020707631213468857822590507566928863525390625e-7,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.10000000000000005610204141526242693771564518101513385772705078125e-7,
            "caching_price": 1.40000000000000009546603416642207573516998309059999883174896240234375e-7,
            "caching_5m_price": 1.40000000000000009546603416642207573516998309059999883174896240234375e-7,
            "caching_1h_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
            "cached_price": 2.000000000000000041845121660256945350653268178575672209262847900390625e-8,
            "output_price": 5.50000000000000028051020707631213468857822590507566928863525390625e-7
        },
        {
            "prompt_tokens_threshold": 100000,
            "input_price": 5.50000000000000028051020707631213468857822590507566928863525390625e-7,
            "caching_price": 6.89999999999999958188285319182764254719586460851132869720458984375e-7,
            "caching_5m_price": 6.89999999999999958188285319182764254719586460851132869720458984375e-7,
            "caching_1h_price": 1.10000000000000005610204141526242693771564518101513385772705078125e-6,
            "cached_price": 5.99999999999999946379087493834869615483285087975673377513885498046875e-8,
            "output_price": 2.7499999999999999284968667245809825772084877826273441314697265625e-6
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Claude Haiku 5.5 is the fastest model in the Claude 5.5 family, built for high volume, speed sensitive workloads. It is much stronger than Haiku 4.5 and is the first Haiku with effort levels to control how much it thinks.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html",
    "geolocation": "eu",
    "open_weights": false,
    "model_lab": "anthropic",
    "model_canonical_name": "claude-haiku-5-5"
}

{
    "api": "chat",
    "id": "bedrock/claude-haiku-5-5@eu-west-3",
    "object": "model",
    "created": 1791331200,
    "updated": 1791410369,
    "owned_by": "system",
    "input_price": 1.10000000000000005610204141526242693771564518101513385772705078125e-7,
    "caching_price": 1.40000000000000009546603416642207573516998309059999883174896240234375e-7,
    "cached_price": 2.000000000000000041845121660256945350653268178575672209262847900390625e-8,
    "output_price": 5.50000000000000028051020707631213468857822590507566928863525390625e-7,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.10000000000000005610204141526242693771564518101513385772705078125e-7,
            "caching_price": 1.40000000000000009546603416642207573516998309059999883174896240234375e-7,
            "caching_5m_price": 1.40000000000000009546603416642207573516998309059999883174896240234375e-7,
            "caching_1h_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
            "cached_price": 2.000000000000000041845121660256945350653268178575672209262847900390625e-8,
            "output_price": 5.50000000000000028051020707631213468857822590507566928863525390625e-7
        },
        {
            "prompt_tokens_threshold": 100000,
            "input_price": 5.50000000000000028051020707631213468857822590507566928863525390625e-7,
            "caching_price": 6.89999999999999958188285319182764254719586460851132869720458984375e-7,
            "caching_5m_price": 6.89999999999999958188285319182764254719586460851132869720458984375e-7,
            "caching_1h_price": 1.10000000000000005610204141526242693771564518101513385772705078125e-6,
            "cached_price": 5.99999999999999946379087493834869615483285087975673377513885498046875e-8,
            "output_price": 2.7499999999999999284968667245809825772084877826273441314697265625e-6
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Claude Haiku 5.5 is the fastest model in the Claude 5.5 family, built for high volume, speed sensitive workloads. It is much stronger than Haiku 4.5 and is the first Haiku with effort levels to control how much it thinks.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html",
    "geolocation": "eu",
    "open_weights": false,
    "model_lab": "anthropic",
    "model_canonical_name": "claude-haiku-5-5"
}

{
    "api": "chat",
    "id": "vertex/claude-haiku-5-5@eu",
    "object": "model",
    "created": 1791331200,
    "updated": 1791410369,
    "owned_by": "system",
    "input_price": 1.10000000000000005610204141526242693771564518101513385772705078125e-7,
    "caching_price": 1.40000000000000009546603416642207573516998309059999883174896240234375e-7,
    "cached_price": 2.000000000000000041845121660256945350653268178575672209262847900390625e-8,
    "output_price": 5.50000000000000028051020707631213468857822590507566928863525390625e-7,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.10000000000000005610204141526242693771564518101513385772705078125e-7,
            "caching_price": 1.40000000000000009546603416642207573516998309059999883174896240234375e-7,
            "caching_5m_price": 1.40000000000000009546603416642207573516998309059999883174896240234375e-7,
            "caching_1h_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
            "cached_price": 2.000000000000000041845121660256945350653268178575672209262847900390625e-8,
            "output_price": 5.50000000000000028051020707631213468857822590507566928863525390625e-7
        },
        {
            "prompt_tokens_threshold": 100000,
            "input_price": 5.50000000000000028051020707631213468857822590507566928863525390625e-7,
            "caching_price": 6.89999999999999958188285319182764254719586460851132869720458984375e-7,
            "caching_5m_price": 6.89999999999999958188285319182764254719586460851132869720458984375e-7,
            "caching_1h_price": 1.10000000000000005610204141526242693771564518101513385772705078125e-6,
            "cached_price": 5.99999999999999946379087493834869615483285087975673377513885498046875e-8,
            "output_price": 2.7499999999999999284968667245809825772084877826273441314697265625e-6
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": true,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Claude Haiku 5.5 is the fastest model in the Claude 5.5 family, built for high volume, speed sensitive workloads. It is much stronger than Haiku 4.5 and is the first Haiku with effort levels to control how much it thinks.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "eu",
    "open_weights": false,
    "model_lab": "anthropic",
    "model_canonical_name": "claude-haiku-5-5"
}

{
    "api": "chat",
    "id": "mistral/mistral-large-4",
    "object": "model",
    "created": 1791244800,
    "updated": 1791292899,
    "owned_by": "system",
    "input_price": 6.799999999999999480528923602451474295094158151187002658843994140625e-7,
    "cached_price": 7.00000000000000047733017083211037867584991545299999415874481201171875e-8,
    "output_price": 2.08999999999999989483564187542352641457910067401826381683349609375e-6,
    "discount_percentage": 50,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 6.799999999999999480528923602451474295094158151187002658843994140625e-7,
            "cached_price": 7.00000000000000047733017083211037867584991545299999415874481201171875e-8,
            "output_price": 2.08999999999999989483564187542352641457910067401826381683349609375e-6
        }
    ],
    "max_output_tokens": 0,
    "context_window": 524288,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": false,
    "description": "Mistral Large 4 is a state-of-the-art, open-weight, general-purpose multimodal model with a granular Mixture-of-Experts architecture. It features 49B active parameters and 1.05T total parameters, and a 1.6B vision encoder. Public preview, 1M context.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "eu",
    "open_weights": false,
    "model_lab": "mistral",
    "model_canonical_name": "mistral-large-4"
}

{
    "api": "chat",
    "id": "sference/clef",
    "object": "model",
    "created": 1791232124,
    "updated": 1791474259,
    "owned_by": "system",
    "input_price": 2.3999999999999997855163499753394784619331403519026935100555419921875e-7,
    "caching_price": 0,
    "cached_price": 0,
    "output_price": 0,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 2.3999999999999997855163499753394784619331403519026935100555419921875e-7,
            "caching_price": 0,
            "cached_price": 0,
            "output_price": 0
        }
    ],
    "max_output_tokens": 0,
    "context_window": 65536,
    "supports_caching": false,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": false,
    "supports_image_generation": false,
    "supports_tool_calling": false,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": false,
    "supports_output_json_schema": false,
    "supports_system_mid_conversation": false,
    "description": "Clef is a 27B multimodal decision model that turns a state and a schema of typed questions into decisions. It reads the state as text, JSON, images, or video, and returns a probability for every allowed option of every question.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "No training on user data",
    "geolocation": "eu",
    "hugging_face_id": "Cloudflare/clef",
    "open_weights": true,
    "model_lab": "cloudflare",
    "model_canonical_name": "clef"
}

{
    "api": "chat",
    "id": "cloudflare/clef-flash",
    "object": "model",
    "created": 1791216346,
    "updated": 1791474259,
    "owned_by": "system",
    "input_price": 8.99999999999999985743080244994518412937622997560538351535797119140625e-8,
    "caching_price": 0,
    "cached_price": 0,
    "output_price": 0,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 8.99999999999999985743080244994518412937622997560538351535797119140625e-8,
            "caching_price": 0,
            "cached_price": 0,
            "output_price": 0
        }
    ],
    "max_output_tokens": 0,
    "context_window": 65536,
    "supports_caching": false,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": false,
    "supports_image_generation": false,
    "supports_tool_calling": false,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": false,
    "supports_output_json_schema": false,
    "supports_system_mid_conversation": false,
    "description": "Clef-flash is a fast 9B multimodal decision model that turns a state and a schema of typed questions into decisions. It reads the state as text, JSON, images, or video, and returns a probability for every allowed option of every question.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "hugging_face_id": "Cloudflare/clef-flash",
    "open_weights": true,
    "model_lab": "cloudflare",
    "model_canonical_name": "clef-flash"
}

{
    "api": "chat",
    "id": "cloudflare/clef",
    "object": "model",
    "created": 1791213419,
    "updated": 1791474259,
    "owned_by": "system",
    "input_price": 2.3999999999999997855163499753394784619331403519026935100555419921875e-7,
    "caching_price": 0,
    "cached_price": 0,
    "output_price": 0,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 2.3999999999999997855163499753394784619331403519026935100555419921875e-7,
            "caching_price": 0,
            "cached_price": 0,
            "output_price": 0
        }
    ],
    "max_output_tokens": 0,
    "context_window": 65536,
    "supports_caching": false,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": false,
    "supports_image_generation": false,
    "supports_tool_calling": false,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": false,
    "supports_output_json_schema": false,
    "supports_system_mid_conversation": false,
    "description": "Clef is a 27B multimodal decision model that turns a state and a schema of typed questions into decisions. It reads the state as text, JSON, images, or video, and returns a probability for every allowed option of every question.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "hugging_face_id": "Cloudflare/clef",
    "open_weights": true,
    "model_lab": "cloudflare",
    "model_canonical_name": "clef"
}

{
    "api": "chat",
    "id": "perplexity/pplx-decider-v1-27b",
    "object": "model",
    "created": 1790726400,
    "updated": 1791211188,
    "owned_by": "system",
    "input_price": 4.00000000000000008369024332051389070130653635715134441852569580078125e-8,
    "output_price": 0,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 4.00000000000000008369024332051389070130653635715134441852569580078125e-8,
            "output_price": 0
        }
    ],
    "max_output_tokens": 1024,
    "context_window": 262144,
    "supports_caching": false,
    "supports_vision": false,
    "supports_computer_use": false,
    "supports_reasoning": false,
    "supports_image_generation": false,
    "supports_tool_calling": false,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": false,
    "supports_output_json_schema": false,
    "supports_system_mid_conversation": true,
    "description": "Perplexity decision model. Answers typed questions (noul, choice, score) about the provided state with probabilities instead of text.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "open_weights": false,
    "model_lab": "perplexity",
    "model_canonical_name": "pplx-decider-v1-27b"
}

{
    "api": "chat",
    "id": "openai/gpt-6.1-sol",
    "object": "model",
    "created": 1790703300,
    "updated": 1790847020,
    "owned_by": "system",
    "input_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-6,
    "caching_price": 2.50000000000000020450763478507827386465578456409275531768798828125e-6,
    "cached_price": 9.99999999999999954748111825886258685613938723690807819366455078125e-8,
    "output_price": 1.0000000000000000818030539140313095458623138256371021270751953125e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-6,
            "caching_price": 2.50000000000000020450763478507827386465578456409275531768798828125e-6,
            "cached_price": 9.99999999999999954748111825886258685613938723690807819366455078125e-8,
            "output_price": 1.0000000000000000818030539140313095458623138256371021270751953125e-5
        },
        {
            "prompt_tokens_threshold": 272000,
            "input_price": 3.9999999999999998189924473035450347424557548947632312774658203125e-6,
            "caching_price": 5.0000000000000004090152695701565477293115691281855106353759765625e-6,
            "cached_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-7,
            "output_price": 1.5000000000000000380012861456169304119612206704914569854736328125e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1050000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": true,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "GPT-6.1 Sol delivers near-Astra performance at a lower cost for complex coding, computer use, and professional work. It succeeds GPT-6 Sol with the same 1M context and 128K output, cheaper cached input, and reasoning effort from low to max.",
    "data_retention": true,
    "data_retention_days": 30,
    "data_used_for_training": false,
    "privacy_comments": "No training on customer data. Data retained for 30 days.",
    "geolocation": "global",
    "open_weights": false,
    "model_lab": "openai",
    "model_canonical_name": "gpt-6.1-sol"
}

{
    "api": "chat",
    "id": "openai/gpt-6.1-sol:flex",
    "object": "model",
    "created": 1790703300,
    "updated": 1790847020,
    "owned_by": "system",
    "input_price": 9.99999999999999954748111825886258685613938723690807819366455078125e-7,
    "caching_price": 1.250000000000000102253817392539136932327892282046377658843994140625e-6,
    "cached_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-8,
    "output_price": 5.0000000000000004090152695701565477293115691281855106353759765625e-6,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 9.99999999999999954748111825886258685613938723690807819366455078125e-7,
            "caching_price": 1.250000000000000102253817392539136932327892282046377658843994140625e-6,
            "cached_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-8,
            "output_price": 5.0000000000000004090152695701565477293115691281855106353759765625e-6
        },
        {
            "prompt_tokens_threshold": 272000,
            "input_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-6,
            "caching_price": 2.50000000000000020450763478507827386465578456409275531768798828125e-6,
            "cached_price": 9.99999999999999954748111825886258685613938723690807819366455078125e-8,
            "output_price": 7.5000000000000001900064307280846520598061033524572849273681640625e-6
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1050000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": true,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "GPT-6.1 Sol delivers near-Astra performance at a lower cost for complex coding, computer use, and professional work. It succeeds GPT-6 Sol with the same 1M context and 128K output, cheaper cached input, and reasoning effort from low to max.",
    "data_retention": true,
    "data_retention_days": 30,
    "data_used_for_training": false,
    "privacy_comments": "No training on customer data. Data retained for 30 days.",
    "geolocation": "global",
    "open_weights": false,
    "model_lab": "openai",
    "model_canonical_name": "gpt-6.1-sol"
}

{
    "api": "chat",
    "id": "azure/gpt-6.1-sol@eastus2",
    "object": "model",
    "created": 1790640000,
    "updated": 1790845773,
    "owned_by": "system",
    "input_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-6,
    "caching_price": 2.50000000000000020450763478507827386465578456409275531768798828125e-6,
    "cached_price": 9.99999999999999954748111825886258685613938723690807819366455078125e-8,
    "output_price": 1.0000000000000000818030539140313095458623138256371021270751953125e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-6,
            "caching_price": 2.50000000000000020450763478507827386465578456409275531768798828125e-6,
            "cached_price": 9.99999999999999954748111825886258685613938723690807819366455078125e-8,
            "output_price": 1.0000000000000000818030539140313095458623138256371021270751953125e-5
        },
        {
            "prompt_tokens_threshold": 272000,
            "input_price": 3.9999999999999998189924473035450347424557548947632312774658203125e-6,
            "caching_price": 5.0000000000000004090152695701565477293115691281855106353759765625e-6,
            "cached_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-7,
            "output_price": 1.5000000000000000380012861456169304119612206704914569854736328125e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1050000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": true,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "GPT-6.1 Sol delivers near-Astra performance at a lower cost for complex coding, computer use, and professional work. It succeeds GPT-6 Sol with the same 1M context and 128K output, cheaper cached input, and reasoning effort from low to max.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "us",
    "open_weights": false,
    "model_lab": "openai",
    "model_canonical_name": "gpt-6.1-sol"
}

{
    "api": "chat",
    "id": "azure/gpt-6.1-sol@francecentral",
    "object": "model",
    "created": 1790640000,
    "updated": 1790845774,
    "owned_by": "system",
    "input_price": 2.3999999999999998913954683821270208454734529368579387664794921875e-6,
    "caching_price": 3.000000000000000076002572291233860823922441340982913970947265625e-6,
    "cached_price": 1.19999999999999989275817498766973923096657017595134675502777099609375e-7,
    "output_price": 1.20000000000000003040102891649354432956897653639316558837890625e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 2.3999999999999998913954683821270208454734529368579387664794921875e-6,
            "caching_price": 3.000000000000000076002572291233860823922441340982913970947265625e-6,
            "cached_price": 1.19999999999999989275817498766973923096657017595134675502777099609375e-7,
            "output_price": 1.20000000000000003040102891649354432956897653639316558837890625e-5
        },
        {
            "prompt_tokens_threshold": 272000,
            "input_price": 4.799999999999999782790936764254041690946905873715877532958984375e-6,
            "caching_price": 6.00000000000000015200514458246772164784488268196582794189453125e-6,
            "cached_price": 2.3999999999999997855163499753394784619331403519026935100555419921875e-7,
            "output_price": 1.800000000000000045601543374740316494353464804589748382568359375e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1050000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": true,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "GPT-6.1 Sol delivers near-Astra performance at a lower cost for complex coding, computer use, and professional work. It succeeds GPT-6 Sol with the same 1M context and 128K output, cheaper cached input, and reasoning effort from low to max.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "eu",
    "open_weights": false,
    "model_lab": "openai",
    "model_canonical_name": "gpt-6.1-sol"
}

{
    "api": "chat",
    "id": "azure/gpt-6.1-sol@germanywestcentral",
    "object": "model",
    "created": 1790640000,
    "updated": 1790845776,
    "owned_by": "system",
    "input_price": 2.3999999999999998913954683821270208454734529368579387664794921875e-6,
    "caching_price": 3.000000000000000076002572291233860823922441340982913970947265625e-6,
    "cached_price": 1.19999999999999989275817498766973923096657017595134675502777099609375e-7,
    "output_price": 1.20000000000000003040102891649354432956897653639316558837890625e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 2.3999999999999998913954683821270208454734529368579387664794921875e-6,
            "caching_price": 3.000000000000000076002572291233860823922441340982913970947265625e-6,
            "cached_price": 1.19999999999999989275817498766973923096657017595134675502777099609375e-7,
            "output_price": 1.20000000000000003040102891649354432956897653639316558837890625e-5
        },
        {
            "prompt_tokens_threshold": 272000,
            "input_price": 4.799999999999999782790936764254041690946905873715877532958984375e-6,
            "caching_price": 6.00000000000000015200514458246772164784488268196582794189453125e-6,
            "cached_price": 2.3999999999999997855163499753394784619331403519026935100555419921875e-7,
            "output_price": 1.800000000000000045601543374740316494353464804589748382568359375e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1050000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": true,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "GPT-6.1 Sol delivers near-Astra performance at a lower cost for complex coding, computer use, and professional work. It succeeds GPT-6 Sol with the same 1M context and 128K output, cheaper cached input, and reasoning effort from low to max.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "eu",
    "open_weights": false,
    "model_lab": "openai",
    "model_canonical_name": "gpt-6.1-sol"
}

{
    "api": "chat",
    "id": "azure/gpt-6.1-sol@swedencentral",
    "object": "model",
    "created": 1790640000,
    "updated": 1790845778,
    "owned_by": "system",
    "input_price": 2.3999999999999998913954683821270208454734529368579387664794921875e-6,
    "caching_price": 3.000000000000000076002572291233860823922441340982913970947265625e-6,
    "cached_price": 1.19999999999999989275817498766973923096657017595134675502777099609375e-7,
    "output_price": 1.20000000000000003040102891649354432956897653639316558837890625e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 2.3999999999999998913954683821270208454734529368579387664794921875e-6,
            "caching_price": 3.000000000000000076002572291233860823922441340982913970947265625e-6,
            "cached_price": 1.19999999999999989275817498766973923096657017595134675502777099609375e-7,
            "output_price": 1.20000000000000003040102891649354432956897653639316558837890625e-5
        },
        {
            "prompt_tokens_threshold": 272000,
            "input_price": 4.799999999999999782790936764254041690946905873715877532958984375e-6,
            "caching_price": 6.00000000000000015200514458246772164784488268196582794189453125e-6,
            "cached_price": 2.3999999999999997855163499753394784619331403519026935100555419921875e-7,
            "output_price": 1.800000000000000045601543374740316494353464804589748382568359375e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1050000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": true,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "GPT-6.1 Sol delivers near-Astra performance at a lower cost for complex coding, computer use, and professional work. It succeeds GPT-6 Sol with the same 1M context and 128K output, cheaper cached input, and reasoning effort from low to max.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "eu",
    "open_weights": false,
    "model_lab": "openai",
    "model_canonical_name": "gpt-6.1-sol"
}

{
    "api": "chat",
    "id": "azure/gpt-6.1-sol@westeurope",
    "object": "model",
    "created": 1790640000,
    "updated": 1790845777,
    "owned_by": "system",
    "input_price": 2.3999999999999998913954683821270208454734529368579387664794921875e-6,
    "caching_price": 3.000000000000000076002572291233860823922441340982913970947265625e-6,
    "cached_price": 1.19999999999999989275817498766973923096657017595134675502777099609375e-7,
    "output_price": 1.20000000000000003040102891649354432956897653639316558837890625e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 2.3999999999999998913954683821270208454734529368579387664794921875e-6,
            "caching_price": 3.000000000000000076002572291233860823922441340982913970947265625e-6,
            "cached_price": 1.19999999999999989275817498766973923096657017595134675502777099609375e-7,
            "output_price": 1.20000000000000003040102891649354432956897653639316558837890625e-5
        },
        {
            "prompt_tokens_threshold": 272000,
            "input_price": 4.799999999999999782790936764254041690946905873715877532958984375e-6,
            "caching_price": 6.00000000000000015200514458246772164784488268196582794189453125e-6,
            "cached_price": 2.3999999999999997855163499753394784619331403519026935100555419921875e-7,
            "output_price": 1.800000000000000045601543374740316494353464804589748382568359375e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1050000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": true,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "GPT-6.1 Sol delivers near-Astra performance at a lower cost for complex coding, computer use, and professional work. It succeeds GPT-6 Sol with the same 1M context and 128K output, cheaper cached input, and reasoning effort from low to max.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "eu",
    "open_weights": false,
    "model_lab": "openai",
    "model_canonical_name": "gpt-6.1-sol"
}

{
    "api": "chat",
    "id": "bedrock/claude-sonnet-5-5",
    "object": "model",
    "created": 1790620530,
    "updated": 1790620530,
    "owned_by": "system",
    "input_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-6,
    "caching_price": 2.50000000000000020450763478507827386465578456409275531768798828125e-6,
    "cached_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-7,
    "output_price": 1.0000000000000000818030539140313095458623138256371021270751953125e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-6,
            "caching_price": 2.50000000000000020450763478507827386465578456409275531768798828125e-6,
            "caching_5m_price": 2.50000000000000020450763478507827386465578456409275531768798828125e-6,
            "caching_1h_price": 3.9999999999999998189924473035450347424557548947632312774658203125e-6,
            "cached_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-7,
            "output_price": 1.0000000000000000818030539140313095458623138256371021270751953125e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Claude Sonnet 5.5 is a step-change improvement over Sonnet 5. It performs great with well-scoped everyday tasks like building features, fixing bugs, and creating polished documents, slides, and spreadsheets. Sonnet 5.5 also improves on communication and writes more clearly than Sonnet 5.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html",
    "geolocation": "global",
    "open_weights": false,
    "model_lab": "anthropic",
    "model_canonical_name": "claude-sonnet-5-5"
}

{
    "api": "chat",
    "id": "bedrock/claude-sonnet-5-5@eu-central-1",
    "object": "model",
    "created": 1790620530,
    "updated": 1791457283,
    "owned_by": "system",
    "input_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-6,
    "caching_price": 2.7499999999999999284968667245809825772084877826273441314697265625e-6,
    "cached_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
    "output_price": 1.099999999999999971398746689832393030883395113050937652587890625e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-6,
            "caching_price": 2.7499999999999999284968667245809825772084877826273441314697265625e-6,
            "caching_5m_price": 2.7499999999999999284968667245809825772084877826273441314697265625e-6,
            "caching_1h_price": 4.400000000000000224408165661049707750862580724060535430908203125e-6,
            "cached_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
            "output_price": 1.099999999999999971398746689832393030883395113050937652587890625e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Claude Sonnet 5.5 is a step-change improvement over Sonnet 5. It performs great with well-scoped everyday tasks like building features, fixing bugs, and creating polished documents, slides, and spreadsheets. Sonnet 5.5 also improves on communication and writes more clearly than Sonnet 5.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html",
    "geolocation": "eu",
    "open_weights": false,
    "model_lab": "anthropic",
    "model_canonical_name": "claude-sonnet-5-5"
}

{
    "api": "chat",
    "id": "bedrock/claude-sonnet-5-5@eu-north-1",
    "object": "model",
    "created": 1790620530,
    "updated": 1791457283,
    "owned_by": "system",
    "input_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-6,
    "caching_price": 2.7499999999999999284968667245809825772084877826273441314697265625e-6,
    "cached_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
    "output_price": 1.099999999999999971398746689832393030883395113050937652587890625e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-6,
            "caching_price": 2.7499999999999999284968667245809825772084877826273441314697265625e-6,
            "caching_5m_price": 2.7499999999999999284968667245809825772084877826273441314697265625e-6,
            "caching_1h_price": 4.400000000000000224408165661049707750862580724060535430908203125e-6,
            "cached_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
            "output_price": 1.099999999999999971398746689832393030883395113050937652587890625e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Claude Sonnet 5.5 is a step-change improvement over Sonnet 5. It performs great with well-scoped everyday tasks like building features, fixing bugs, and creating polished documents, slides, and spreadsheets. Sonnet 5.5 also improves on communication and writes more clearly than Sonnet 5.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html",
    "geolocation": "eu",
    "open_weights": false,
    "model_lab": "anthropic",
    "model_canonical_name": "claude-sonnet-5-5"
}

{
    "api": "chat",
    "id": "bedrock/claude-sonnet-5-5@eu-west-1",
    "object": "model",
    "created": 1790620530,
    "updated": 1791457283,
    "owned_by": "system",
    "input_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-6,
    "caching_price": 2.7499999999999999284968667245809825772084877826273441314697265625e-6,
    "cached_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
    "output_price": 1.099999999999999971398746689832393030883395113050937652587890625e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-6,
            "caching_price": 2.7499999999999999284968667245809825772084877826273441314697265625e-6,
            "caching_5m_price": 2.7499999999999999284968667245809825772084877826273441314697265625e-6,
            "caching_1h_price": 4.400000000000000224408165661049707750862580724060535430908203125e-6,
            "cached_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
            "output_price": 1.099999999999999971398746689832393030883395113050937652587890625e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Claude Sonnet 5.5 is a step-change improvement over Sonnet 5. It performs great with well-scoped everyday tasks like building features, fixing bugs, and creating polished documents, slides, and spreadsheets. Sonnet 5.5 also improves on communication and writes more clearly than Sonnet 5.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html",
    "geolocation": "eu",
    "open_weights": false,
    "model_lab": "anthropic",
    "model_canonical_name": "claude-sonnet-5-5"
}

{
    "api": "chat",
    "id": "bedrock/claude-sonnet-5-5@eu-west-3",
    "object": "model",
    "created": 1790620530,
    "updated": 1791457283,
    "owned_by": "system",
    "input_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-6,
    "caching_price": 2.7499999999999999284968667245809825772084877826273441314697265625e-6,
    "cached_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
    "output_price": 1.099999999999999971398746689832393030883395113050937652587890625e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-6,
            "caching_price": 2.7499999999999999284968667245809825772084877826273441314697265625e-6,
            "caching_5m_price": 2.7499999999999999284968667245809825772084877826273441314697265625e-6,
            "caching_1h_price": 4.400000000000000224408165661049707750862580724060535430908203125e-6,
            "cached_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
            "output_price": 1.099999999999999971398746689832393030883395113050937652587890625e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Claude Sonnet 5.5 is a step-change improvement over Sonnet 5. It performs great with well-scoped everyday tasks like building features, fixing bugs, and creating polished documents, slides, and spreadsheets. Sonnet 5.5 also improves on communication and writes more clearly than Sonnet 5.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html",
    "geolocation": "eu",
    "open_weights": false,
    "model_lab": "anthropic",
    "model_canonical_name": "claude-sonnet-5-5"
}

{
    "api": "chat",
    "id": "anthropic/claude-sonnet-5-5",
    "object": "model",
    "created": 1790616534,
    "updated": 1790616534,
    "owned_by": "system",
    "input_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-6,
    "caching_price": 2.50000000000000020450763478507827386465578456409275531768798828125e-6,
    "cached_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-7,
    "output_price": 1.0000000000000000818030539140313095458623138256371021270751953125e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-6,
            "caching_price": 2.50000000000000020450763478507827386465578456409275531768798828125e-6,
            "caching_5m_price": 2.50000000000000020450763478507827386465578456409275531768798828125e-6,
            "caching_1h_price": 3.9999999999999998189924473035450347424557548947632312774658203125e-6,
            "cached_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-7,
            "output_price": 1.0000000000000000818030539140313095458623138256371021270751953125e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": true,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Claude Sonnet 5.5 is a step-change improvement over Sonnet 5. It performs great with well-scoped everyday tasks like building features, fixing bugs, and creating polished documents, slides, and spreadsheets. Sonnet 5.5 also improves on communication and writes more clearly than Sonnet 5.",
    "data_retention": true,
    "data_retention_days": 30,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "open_weights": false,
    "model_lab": "anthropic",
    "model_canonical_name": "claude-sonnet-5-5"
}

{
    "api": "chat",
    "id": "novita/ling-3.1-flash",
    "object": "model",
    "created": 1790553600,
    "updated": 1791193805,
    "owned_by": "system",
    "input_price": 0,
    "cached_price": 0,
    "output_price": 0,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 0,
            "cached_price": 0,
            "output_price": 0
        }
    ],
    "max_output_tokens": 32768,
    "context_window": 262144,
    "supports_caching": true,
    "supports_vision": false,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": false,
    "supports_output_json_schema": false,
    "supports_system_mid_conversation": false,
    "description": "Ling 3.1 Flash is a hybrid reasoning MoE model from inclusionAI with 560B total and 25B active parameters. Served by Novita with a 256K context window and 32K max output, supporting reasoning and function calling. Free tier.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "open_weights": true,
    "model_lab": "inclusionai",
    "model_canonical_name": "ling-3.1-flash"
}

{
    "api": "chat",
    "id": "vertex/claude-sonnet-5-5",
    "object": "model",
    "created": 1790553600,
    "updated": 1790668471,
    "owned_by": "system",
    "input_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-6,
    "caching_price": 2.50000000000000020450763478507827386465578456409275531768798828125e-6,
    "cached_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-7,
    "output_price": 1.0000000000000000818030539140313095458623138256371021270751953125e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-6,
            "caching_price": 2.50000000000000020450763478507827386465578456409275531768798828125e-6,
            "caching_5m_price": 2.50000000000000020450763478507827386465578456409275531768798828125e-6,
            "caching_1h_price": 3.9999999999999998189924473035450347424557548947632312774658203125e-6,
            "cached_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-7,
            "output_price": 1.0000000000000000818030539140313095458623138256371021270751953125e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": true,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Claude Sonnet 5.5 is a step-change improvement over Sonnet 5. It performs great with well-scoped everyday tasks like building features, fixing bugs, and creating polished documents, slides, and spreadsheets. Sonnet 5.5 also improves on communication and writes more clearly than Sonnet 5.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "open_weights": false,
    "model_lab": "anthropic",
    "model_canonical_name": "claude-sonnet-5-5"
}

{
    "api": "chat",
    "id": "vertex/claude-sonnet-5-5@eu",
    "object": "model",
    "created": 1790553600,
    "updated": 1790668471,
    "owned_by": "system",
    "input_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-6,
    "caching_price": 2.7499999999999999284968667245809825772084877826273441314697265625e-6,
    "cached_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
    "output_price": 1.099999999999999971398746689832393030883395113050937652587890625e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-6,
            "caching_price": 2.7499999999999999284968667245809825772084877826273441314697265625e-6,
            "caching_5m_price": 2.7499999999999999284968667245809825772084877826273441314697265625e-6,
            "caching_1h_price": 4.400000000000000224408165661049707750862580724060535430908203125e-6,
            "cached_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
            "output_price": 1.099999999999999971398746689832393030883395113050937652587890625e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": true,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Claude Sonnet 5.5 is a step-change improvement over Sonnet 5. It performs great with well-scoped everyday tasks like building features, fixing bugs, and creating polished documents, slides, and spreadsheets. Sonnet 5.5 also improves on communication and writes more clearly than Sonnet 5.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "eu",
    "open_weights": false,
    "model_lab": "anthropic",
    "model_canonical_name": "claude-sonnet-5-5"
}

{
    "api": "chat",
    "id": "vertex/claude-sonnet-5-5@us",
    "object": "model",
    "created": 1790553600,
    "updated": 1790668471,
    "owned_by": "system",
    "input_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-6,
    "caching_price": 2.7499999999999999284968667245809825772084877826273441314697265625e-6,
    "cached_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
    "output_price": 1.099999999999999971398746689832393030883395113050937652587890625e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-6,
            "caching_price": 2.7499999999999999284968667245809825772084877826273441314697265625e-6,
            "caching_5m_price": 2.7499999999999999284968667245809825772084877826273441314697265625e-6,
            "caching_1h_price": 4.400000000000000224408165661049707750862580724060535430908203125e-6,
            "cached_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
            "output_price": 1.099999999999999971398746689832393030883395113050937652587890625e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": true,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Claude Sonnet 5.5 is a step-change improvement over Sonnet 5. It performs great with well-scoped everyday tasks like building features, fixing bugs, and creating polished documents, slides, and spreadsheets. Sonnet 5.5 also improves on communication and writes more clearly than Sonnet 5.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "us",
    "open_weights": false,
    "model_lab": "anthropic",
    "model_canonical_name": "claude-sonnet-5-5"
}

{
    "api": "chat",
    "id": "deepinfra/mimo-v2.6-flash",
    "object": "model",
    "created": 1790520673,
    "updated": 1791474259,
    "owned_by": "system",
    "input_price": 1.40000000000000009546603416642207573516998309059999883174896240234375e-7,
    "cached_price": 2.70000000000000018883981224983130420280730277227121405303478240966796875e-9,
    "output_price": 2.8000000000000001909320683328441514703399661811999976634979248046875e-7,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.40000000000000009546603416642207573516998309059999883174896240234375e-7,
            "cached_price": 2.70000000000000018883981224983130420280730277227121405303478240966796875e-9,
            "output_price": 2.8000000000000001909320683328441514703399661811999976634979248046875e-7
        }
    ],
    "max_output_tokens": 131072,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "MiMo-V2.6-Flash is the efficiency-balanced model in Xiaomi's MiMo-V2.6 series: a sparse Mixture-of-Experts model with 309B total and 15B activated parameters, natively omnimodal across text, image, video and audio, with a 1M-token context window. Trained with large-scale mixed reinforcement learning across coding, general agents, visual and cybersecurity tasks, it is built for agentic workloads such as long-horizon coding, tool use and computer use.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "quantization": "fp8",
    "hugging_face_id": "XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "open_weights": true,
    "model_lab": "xiaomi",
    "model_canonical_name": "mimo-v2.6-flash"
}

{
    "api": "chat",
    "id": "deepinfra/mimo-v2.6-pro",
    "object": "model",
    "created": 1790520673,
    "updated": 1791474259,
    "owned_by": "system",
    "input_price": 4.300000000000000123054236071673539498760874266736209392547607421875e-7,
    "cached_price": 3.59999999999999997605954548209918064660683967304066754877567291259765625e-9,
    "output_price": 8.700000000000000347462401732723247249623454990796744823455810546875e-7,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 4.300000000000000123054236071673539498760874266736209392547607421875e-7,
            "cached_price": 3.59999999999999997605954548209918064660683967304066754877567291259765625e-9,
            "output_price": 8.700000000000000347462401732723247249623454990796744823455810546875e-7
        }
    ],
    "max_output_tokens": 131072,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "MiMo-V2.6-Pro is the flagship of Xiaomi's MiMo-V2.6 series: a sparse Mixture-of-Experts model with 1.02T total and 42B activated parameters, natively omnimodal across text, image, video and audio, with a 1M-token context window. Trained with large-scale mixed reinforcement learning and groupwise agentic grading, it is built for demanding agentic work including long-horizon coding, multi-tool agents and cybersecurity tasks.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "quantization": "fp8",
    "hugging_face_id": "XiaomiMiMo/MiMo-V2.6-Pro-RL",
    "open_weights": true,
    "model_lab": "xiaomi",
    "model_canonical_name": "mimo-v2.6-pro"
}

{
    "api": "chat",
    "id": "azure/gpt-6-luna@eastus2",
    "object": "model",
    "created": 1790140750,
    "updated": 1790845759,
    "owned_by": "system",
    "input_price": 9.99999999999999954748111825886258685613938723690807819366455078125e-8,
    "caching_price": 1.24999999999999994343513978235782335701742340461350977420806884765625e-7,
    "cached_price": 1.0000000000000000209225608301284726753266340892878361046314239501953125e-8,
    "output_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-7,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 9.99999999999999954748111825886258685613938723690807819366455078125e-8,
            "caching_price": 1.24999999999999994343513978235782335701742340461350977420806884765625e-7,
            "cached_price": 1.0000000000000000209225608301284726753266340892878361046314239501953125e-8,
            "output_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-7
        },
        {
            "prompt_tokens_threshold": 272000,
            "input_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-7,
            "caching_price": 2.4999999999999998868702795647156467140348468092270195484161376953125e-7,
            "cached_price": 2.000000000000000041845121660256945350653268178575672209262847900390625e-8,
            "output_price": 7.5000000000000001900064307280846520598061033524572849273681640625e-7
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1050000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": true,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reasoning effort it can take on complex software engineering and computer-use tasks that previously called for a Sol-tier model.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "us",
    "open_weights": false,
    "model_lab": "openai",
    "model_canonical_name": "gpt-6-luna"
}

{
    "api": "chat",
    "id": "azure/gpt-6-sol@eastus2",
    "object": "model",
    "created": 1790140750,
    "updated": 1790845766,
    "owned_by": "system",
    "input_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-6,
    "caching_price": 2.50000000000000020450763478507827386465578456409275531768798828125e-6,
    "cached_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-7,
    "output_price": 1.0000000000000000818030539140313095458623138256371021270751953125e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-6,
            "caching_price": 2.50000000000000020450763478507827386465578456409275531768798828125e-6,
            "cached_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-7,
            "output_price": 1.0000000000000000818030539140313095458623138256371021270751953125e-5
        },
        {
            "prompt_tokens_threshold": 272000,
            "input_price": 3.9999999999999998189924473035450347424557548947632312774658203125e-6,
            "caching_price": 5.0000000000000004090152695701565477293115691281855106353759765625e-6,
            "cached_price": 3.9999999999999998189924473035450347424557548947632312774658203125e-7,
            "output_price": 1.5000000000000000380012861456169304119612206704914569854736328125e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1050000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": true,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, agentic coding, business workflow automation, and computer use, and is particularly strong at long-horizon software engineering tasks in real codebases. It approaches Astra-level factual reliability at a much lower cost.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "us",
    "open_weights": false,
    "model_lab": "openai",
    "model_canonical_name": "gpt-6-sol"
}

{
    "api": "chat",
    "id": "azure/gpt-6-luna@francecentral",
    "object": "model",
    "created": 1790109419,
    "updated": 1790845761,
    "owned_by": "system",
    "input_price": 1.19999999999999989275817498766973923096657017595134675502777099609375e-7,
    "caching_price": 1.4999999999999999321221677388293880284209080855362117290496826171875e-7,
    "cached_price": 1.19999999999999999201984849403306021553561322434688918292522430419921875e-8,
    "output_price": 5.99999999999999972848867095531755211368363234214484691619873046875e-7,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.19999999999999989275817498766973923096657017595134675502777099609375e-7,
            "caching_price": 1.4999999999999999321221677388293880284209080855362117290496826171875e-7,
            "cached_price": 1.19999999999999999201984849403306021553561322434688918292522430419921875e-8,
            "output_price": 5.99999999999999972848867095531755211368363234214484691619873046875e-7
        },
        {
            "prompt_tokens_threshold": 272000,
            "input_price": 2.3999999999999997855163499753394784619331403519026935100555419921875e-7,
            "caching_price": 2.999999999999999864244335477658776056841816171072423458099365234375e-7,
            "cached_price": 2.3999999999999999840396969880661204310712264486937783658504486083984375e-8,
            "output_price": 8.999999999999999592733006432976328170525448513217270374298095703125e-7
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1050000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": true,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reasoning effort it can take on complex software engineering and computer-use tasks that previously called for a Sol-tier model.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "eu",
    "open_weights": false,
    "model_lab": "openai",
    "model_canonical_name": "gpt-6-luna"
}

{
    "api": "chat",
    "id": "azure/gpt-6-luna@germanywestcentral",
    "object": "model",
    "created": 1790109419,
    "updated": 1790845762,
    "owned_by": "system",
    "input_price": 1.19999999999999989275817498766973923096657017595134675502777099609375e-7,
    "caching_price": 1.4999999999999999321221677388293880284209080855362117290496826171875e-7,
    "cached_price": 1.19999999999999999201984849403306021553561322434688918292522430419921875e-8,
    "output_price": 5.99999999999999972848867095531755211368363234214484691619873046875e-7,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.19999999999999989275817498766973923096657017595134675502777099609375e-7,
            "caching_price": 1.4999999999999999321221677388293880284209080855362117290496826171875e-7,
            "cached_price": 1.19999999999999999201984849403306021553561322434688918292522430419921875e-8,
            "output_price": 5.99999999999999972848867095531755211368363234214484691619873046875e-7
        },
        {
            "prompt_tokens_threshold": 272000,
            "input_price": 2.3999999999999997855163499753394784619331403519026935100555419921875e-7,
            "caching_price": 2.999999999999999864244335477658776056841816171072423458099365234375e-7,
            "cached_price": 2.3999999999999999840396969880661204310712264486937783658504486083984375e-8,
            "output_price": 8.999999999999999592733006432976328170525448513217270374298095703125e-7
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1050000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": true,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reasoning effort it can take on complex software engineering and computer-use tasks that previously called for a Sol-tier model.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "eu",
    "open_weights": false,
    "model_lab": "openai",
    "model_canonical_name": "gpt-6-luna"
}

{
    "api": "chat",
    "id": "azure/gpt-6-luna@swedencentral",
    "object": "model",
    "created": 1790109419,
    "updated": 1790845765,
    "owned_by": "system",
    "input_price": 1.19999999999999989275817498766973923096657017595134675502777099609375e-7,
    "caching_price": 1.4999999999999999321221677388293880284209080855362117290496826171875e-7,
    "cached_price": 1.19999999999999999201984849403306021553561322434688918292522430419921875e-8,
    "output_price": 5.99999999999999972848867095531755211368363234214484691619873046875e-7,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.19999999999999989275817498766973923096657017595134675502777099609375e-7,
            "caching_price": 1.4999999999999999321221677388293880284209080855362117290496826171875e-7,
            "cached_price": 1.19999999999999999201984849403306021553561322434688918292522430419921875e-8,
            "output_price": 5.99999999999999972848867095531755211368363234214484691619873046875e-7
        },
        {
            "prompt_tokens_threshold": 272000,
            "input_price": 2.3999999999999997855163499753394784619331403519026935100555419921875e-7,
            "caching_price": 2.999999999999999864244335477658776056841816171072423458099365234375e-7,
            "cached_price": 2.3999999999999999840396969880661204310712264486937783658504486083984375e-8,
            "output_price": 8.999999999999999592733006432976328170525448513217270374298095703125e-7
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1050000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": true,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reasoning effort it can take on complex software engineering and computer-use tasks that previously called for a Sol-tier model.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "eu",
    "open_weights": false,
    "model_lab": "openai",
    "model_canonical_name": "gpt-6-luna"
}

{
    "api": "chat",
    "id": "azure/gpt-6-luna@westeurope",
    "object": "model",
    "created": 1790109419,
    "updated": 1790845763,
    "owned_by": "system",
    "input_price": 1.19999999999999989275817498766973923096657017595134675502777099609375e-7,
    "caching_price": 1.4999999999999999321221677388293880284209080855362117290496826171875e-7,
    "cached_price": 1.19999999999999999201984849403306021553561322434688918292522430419921875e-8,
    "output_price": 5.99999999999999972848867095531755211368363234214484691619873046875e-7,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.19999999999999989275817498766973923096657017595134675502777099609375e-7,
            "caching_price": 1.4999999999999999321221677388293880284209080855362117290496826171875e-7,
            "cached_price": 1.19999999999999999201984849403306021553561322434688918292522430419921875e-8,
            "output_price": 5.99999999999999972848867095531755211368363234214484691619873046875e-7
        },
        {
            "prompt_tokens_threshold": 272000,
            "input_price": 2.3999999999999997855163499753394784619331403519026935100555419921875e-7,
            "caching_price": 2.999999999999999864244335477658776056841816171072423458099365234375e-7,
            "cached_price": 2.3999999999999999840396969880661204310712264486937783658504486083984375e-8,
            "output_price": 8.999999999999999592733006432976328170525448513217270374298095703125e-7
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1050000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": true,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reasoning effort it can take on complex software engineering and computer-use tasks that previously called for a Sol-tier model.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "eu",
    "open_weights": false,
    "model_lab": "openai",
    "model_canonical_name": "gpt-6-luna"
}

{
    "api": "chat",
    "id": "azure/gpt-6-sol@francecentral",
    "object": "model",
    "created": 1790109419,
    "updated": 1790845768,
    "owned_by": "system",
    "input_price": 2.3999999999999998913954683821270208454734529368579387664794921875e-6,
    "caching_price": 3.000000000000000076002572291233860823922441340982913970947265625e-6,
    "cached_price": 2.3999999999999997855163499753394784619331403519026935100555419921875e-7,
    "output_price": 1.20000000000000003040102891649354432956897653639316558837890625e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 2.3999999999999998913954683821270208454734529368579387664794921875e-6,
            "caching_price": 3.000000000000000076002572291233860823922441340982913970947265625e-6,
            "cached_price": 2.3999999999999997855163499753394784619331403519026935100555419921875e-7,
            "output_price": 1.20000000000000003040102891649354432956897653639316558837890625e-5
        },
        {
            "prompt_tokens_threshold": 272000,
            "input_price": 4.799999999999999782790936764254041690946905873715877532958984375e-6,
            "caching_price": 6.00000000000000015200514458246772164784488268196582794189453125e-6,
            "cached_price": 4.799999999999999571032699950678956923866280703805387020111083984375e-7,
            "output_price": 1.800000000000000045601543374740316494353464804589748382568359375e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1050000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": true,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, agentic coding, business workflow automation, and computer use, and is particularly strong at long-horizon software engineering tasks in real codebases. It approaches Astra-level factual reliability at a much lower cost.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "eu",
    "open_weights": false,
    "model_lab": "openai",
    "model_canonical_name": "gpt-6-sol"
}

{
    "api": "chat",
    "id": "azure/gpt-6-sol@germanywestcentral",
    "object": "model",
    "created": 1790109419,
    "updated": 1790845769,
    "owned_by": "system",
    "input_price": 2.3999999999999998913954683821270208454734529368579387664794921875e-6,
    "caching_price": 3.000000000000000076002572291233860823922441340982913970947265625e-6,
    "cached_price": 2.3999999999999997855163499753394784619331403519026935100555419921875e-7,
    "output_price": 1.20000000000000003040102891649354432956897653639316558837890625e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 2.3999999999999998913954683821270208454734529368579387664794921875e-6,
            "caching_price": 3.000000000000000076002572291233860823922441340982913970947265625e-6,
            "cached_price": 2.3999999999999997855163499753394784619331403519026935100555419921875e-7,
            "output_price": 1.20000000000000003040102891649354432956897653639316558837890625e-5
        },
        {
            "prompt_tokens_threshold": 272000,
            "input_price": 4.799999999999999782790936764254041690946905873715877532958984375e-6,
            "caching_price": 6.00000000000000015200514458246772164784488268196582794189453125e-6,
            "cached_price": 4.799999999999999571032699950678956923866280703805387020111083984375e-7,
            "output_price": 1.800000000000000045601543374740316494353464804589748382568359375e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1050000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": true,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, agentic coding, business workflow automation, and computer use, and is particularly strong at long-horizon software engineering tasks in real codebases. It approaches Astra-level factual reliability at a much lower cost.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "eu",
    "open_weights": false,
    "model_lab": "openai",
    "model_canonical_name": "gpt-6-sol"
}

{
    "api": "chat",
    "id": "azure/gpt-6-sol@swedencentral",
    "object": "model",
    "created": 1790109419,
    "updated": 1790845772,
    "owned_by": "system",
    "input_price": 2.3999999999999998913954683821270208454734529368579387664794921875e-6,
    "caching_price": 3.000000000000000076002572291233860823922441340982913970947265625e-6,
    "cached_price": 2.3999999999999997855163499753394784619331403519026935100555419921875e-7,
    "output_price": 1.20000000000000003040102891649354432956897653639316558837890625e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 2.3999999999999998913954683821270208454734529368579387664794921875e-6,
            "caching_price": 3.000000000000000076002572291233860823922441340982913970947265625e-6,
            "cached_price": 2.3999999999999997855163499753394784619331403519026935100555419921875e-7,
            "output_price": 1.20000000000000003040102891649354432956897653639316558837890625e-5
        },
        {
            "prompt_tokens_threshold": 272000,
            "input_price": 4.799999999999999782790936764254041690946905873715877532958984375e-6,
            "caching_price": 6.00000000000000015200514458246772164784488268196582794189453125e-6,
            "cached_price": 4.799999999999999571032699950678956923866280703805387020111083984375e-7,
            "output_price": 1.800000000000000045601543374740316494353464804589748382568359375e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1050000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": true,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, agentic coding, business workflow automation, and computer use, and is particularly strong at long-horizon software engineering tasks in real codebases. It approaches Astra-level factual reliability at a much lower cost.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "eu",
    "open_weights": false,
    "model_lab": "openai",
    "model_canonical_name": "gpt-6-sol"
}

{
    "api": "chat",
    "id": "azure/gpt-6-sol@westeurope",
    "object": "model",
    "created": 1790109419,
    "updated": 1790845771,
    "owned_by": "system",
    "input_price": 2.3999999999999998913954683821270208454734529368579387664794921875e-6,
    "caching_price": 3.000000000000000076002572291233860823922441340982913970947265625e-6,
    "cached_price": 2.3999999999999997855163499753394784619331403519026935100555419921875e-7,
    "output_price": 1.20000000000000003040102891649354432956897653639316558837890625e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 2.3999999999999998913954683821270208454734529368579387664794921875e-6,
            "caching_price": 3.000000000000000076002572291233860823922441340982913970947265625e-6,
            "cached_price": 2.3999999999999997855163499753394784619331403519026935100555419921875e-7,
            "output_price": 1.20000000000000003040102891649354432956897653639316558837890625e-5
        },
        {
            "prompt_tokens_threshold": 272000,
            "input_price": 4.799999999999999782790936764254041690946905873715877532958984375e-6,
            "caching_price": 6.00000000000000015200514458246772164784488268196582794189453125e-6,
            "cached_price": 4.799999999999999571032699950678956923866280703805387020111083984375e-7,
            "output_price": 1.800000000000000045601543374740316494353464804589748382568359375e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1050000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": true,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, agentic coding, business workflow automation, and computer use, and is particularly strong at long-horizon software engineering tasks in real codebases. It approaches Astra-level factual reliability at a much lower cost.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "eu",
    "open_weights": false,
    "model_lab": "openai",
    "model_canonical_name": "gpt-6-sol"
}

{
    "api": "chat",
    "id": "openai/gpt-6-luna:flex",
    "object": "model",
    "created": 1790102585,
    "updated": 1790847020,
    "owned_by": "system",
    "input_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-8,
    "caching_price": 6.24999999999999971717569891178911678508711702306754887104034423828125e-8,
    "cached_price": 5.0000000000000001046128041506423633766331704464391805231571197509765625e-9,
    "output_price": 2.4999999999999998868702795647156467140348468092270195484161376953125e-7,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-8,
            "caching_price": 6.24999999999999971717569891178911678508711702306754887104034423828125e-8,
            "cached_price": 5.0000000000000001046128041506423633766331704464391805231571197509765625e-9,
            "output_price": 2.4999999999999998868702795647156467140348468092270195484161376953125e-7
        },
        {
            "prompt_tokens_threshold": 272000,
            "input_price": 9.99999999999999954748111825886258685613938723690807819366455078125e-8,
            "caching_price": 1.24999999999999994343513978235782335701742340461350977420806884765625e-7,
            "cached_price": 1.0000000000000000209225608301284726753266340892878361046314239501953125e-8,
            "output_price": 3.75000000000000009500321536404232602990305167622864246368408203125e-7
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1050000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": true,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reasoning effort it can take on complex software engineering and computer-use tasks that previously called for a Sol-tier model.",
    "data_retention": true,
    "data_retention_days": 30,
    "data_used_for_training": false,
    "privacy_comments": "No training on customer data. Data retained for 30 days.",
    "geolocation": "global",
    "open_weights": false,
    "model_lab": "openai",
    "model_canonical_name": "gpt-6-luna"
}

{
    "api": "chat",
    "id": "openai/gpt-6-luna",
    "object": "model",
    "created": 1790102582,
    "updated": 1790847020,
    "owned_by": "system",
    "input_price": 9.99999999999999954748111825886258685613938723690807819366455078125e-8,
    "caching_price": 1.24999999999999994343513978235782335701742340461350977420806884765625e-7,
    "cached_price": 1.0000000000000000209225608301284726753266340892878361046314239501953125e-8,
    "output_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-7,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 9.99999999999999954748111825886258685613938723690807819366455078125e-8,
            "caching_price": 1.24999999999999994343513978235782335701742340461350977420806884765625e-7,
            "cached_price": 1.0000000000000000209225608301284726753266340892878361046314239501953125e-8,
            "output_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-7
        },
        {
            "prompt_tokens_threshold": 272000,
            "input_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-7,
            "caching_price": 2.4999999999999998868702795647156467140348468092270195484161376953125e-7,
            "cached_price": 2.000000000000000041845121660256945350653268178575672209262847900390625e-8,
            "output_price": 7.5000000000000001900064307280846520598061033524572849273681640625e-7
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1050000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": true,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reasoning effort it can take on complex software engineering and computer-use tasks that previously called for a Sol-tier model.",
    "data_retention": true,
    "data_retention_days": 30,
    "data_used_for_training": false,
    "privacy_comments": "No training on customer data. Data retained for 30 days.",
    "geolocation": "global",
    "open_weights": false,
    "model_lab": "openai",
    "model_canonical_name": "gpt-6-luna"
}

{
    "api": "chat",
    "id": "openai/gpt-6-sol:flex",
    "object": "model",
    "created": 1790102579,
    "updated": 1790847020,
    "owned_by": "system",
    "input_price": 9.99999999999999954748111825886258685613938723690807819366455078125e-7,
    "caching_price": 1.250000000000000102253817392539136932327892282046377658843994140625e-6,
    "cached_price": 9.99999999999999954748111825886258685613938723690807819366455078125e-8,
    "output_price": 5.0000000000000004090152695701565477293115691281855106353759765625e-6,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 9.99999999999999954748111825886258685613938723690807819366455078125e-7,
            "caching_price": 1.250000000000000102253817392539136932327892282046377658843994140625e-6,
            "cached_price": 9.99999999999999954748111825886258685613938723690807819366455078125e-8,
            "output_price": 5.0000000000000004090152695701565477293115691281855106353759765625e-6
        },
        {
            "prompt_tokens_threshold": 272000,
            "input_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-6,
            "caching_price": 2.50000000000000020450763478507827386465578456409275531768798828125e-6,
            "cached_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-7,
            "output_price": 7.5000000000000001900064307280846520598061033524572849273681640625e-6
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1050000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": true,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, agentic coding, business workflow automation, and computer use, and is particularly strong at long-horizon software engineering tasks in real codebases. It approaches Astra-level factual reliability at a much lower cost.",
    "data_retention": true,
    "data_retention_days": 30,
    "data_used_for_training": false,
    "privacy_comments": "No training on customer data. Data retained for 30 days.",
    "geolocation": "global",
    "open_weights": false,
    "model_lab": "openai",
    "model_canonical_name": "gpt-6-sol"
}

{
    "api": "chat",
    "id": "openai/gpt-6-sol",
    "object": "model",
    "created": 1790102552,
    "updated": 1790847020,
    "owned_by": "system",
    "input_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-6,
    "caching_price": 2.50000000000000020450763478507827386465578456409275531768798828125e-6,
    "cached_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-7,
    "output_price": 1.0000000000000000818030539140313095458623138256371021270751953125e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-6,
            "caching_price": 2.50000000000000020450763478507827386465578456409275531768798828125e-6,
            "cached_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-7,
            "output_price": 1.0000000000000000818030539140313095458623138256371021270751953125e-5
        },
        {
            "prompt_tokens_threshold": 272000,
            "input_price": 3.9999999999999998189924473035450347424557548947632312774658203125e-6,
            "caching_price": 5.0000000000000004090152695701565477293115691281855106353759765625e-6,
            "cached_price": 3.9999999999999998189924473035450347424557548947632312774658203125e-7,
            "output_price": 1.5000000000000000380012861456169304119612206704914569854736328125e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1050000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": true,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, agentic coding, business workflow automation, and computer use, and is particularly strong at long-horizon software engineering tasks in real codebases. It approaches Astra-level factual reliability at a much lower cost.",
    "data_retention": true,
    "data_retention_days": 30,
    "data_used_for_training": false,
    "privacy_comments": "No training on customer data. Data retained for 30 days.",
    "geolocation": "global",
    "open_weights": false,
    "model_lab": "openai",
    "model_canonical_name": "gpt-6-sol"
}

{
    "api": "chat",
    "id": "anthropic/claude-opus-5-5",
    "object": "model",
    "created": 1790098200,
    "updated": 1790098200,
    "owned_by": "system",
    "input_price": 3.9999999999999998189924473035450347424557548947632312774658203125e-6,
    "caching_price": 5.0000000000000004090152695701565477293115691281855106353759765625e-6,
    "cached_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-7,
    "output_price": 2.000000000000000163606107828062619091724627651274204254150390625e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 3.9999999999999998189924473035450347424557548947632312774658203125e-6,
            "caching_price": 5.0000000000000004090152695701565477293115691281855106353759765625e-6,
            "caching_5m_price": 5.0000000000000004090152695701565477293115691281855106353759765625e-6,
            "caching_1h_price": 7.999999999999999637984894607090069484911509789526462554931640625e-6,
            "cached_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-7,
            "output_price": 2.000000000000000163606107828062619091724627651274204254150390625e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": true,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Claude Opus 5.5 is a step-change improvement over Opus 5, with the biggest gains in agentic coding, long-running agentic tasks, and knowledge work. It is also a much better collaborator on long-running work. It reports back in plain language on what it did, what it found, and what it needs next.",
    "data_retention": true,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "open_weights": false,
    "model_lab": "anthropic",
    "model_canonical_name": "claude-opus-5-5"
}

{
    "api": "chat",
    "id": "vertex/claude-opus-5-5",
    "object": "model",
    "created": 1790098200,
    "updated": 1790668360,
    "owned_by": "system",
    "input_price": 3.9999999999999998189924473035450347424557548947632312774658203125e-6,
    "caching_price": 5.0000000000000004090152695701565477293115691281855106353759765625e-6,
    "cached_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-7,
    "output_price": 2.000000000000000163606107828062619091724627651274204254150390625e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 3.9999999999999998189924473035450347424557548947632312774658203125e-6,
            "caching_price": 5.0000000000000004090152695701565477293115691281855106353759765625e-6,
            "caching_5m_price": 5.0000000000000004090152695701565477293115691281855106353759765625e-6,
            "caching_1h_price": 7.999999999999999637984894607090069484911509789526462554931640625e-6,
            "cached_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-7,
            "output_price": 2.000000000000000163606107828062619091724627651274204254150390625e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": true,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Claude Opus 5.5 is the first model in Anthropic's Claude 5.5 family and the most capable Opus to date, built for long running autonomous agents, large scale coding, and frontier knowledge work. It improves on Opus 5 in planning, sustained multi step execution, and judgment across extended sessions, at a lower price than Opus 5.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "open_weights": false,
    "model_lab": "anthropic",
    "model_canonical_name": "claude-opus-5-5"
}

{
    "api": "chat",
    "id": "vertex/claude-opus-5-5@eu",
    "object": "model",
    "created": 1790098200,
    "updated": 1790668360,
    "owned_by": "system",
    "input_price": 4.400000000000000224408165661049707750862580724060535430908203125e-6,
    "caching_price": 5.499999999999999856993733449161965154416975565254688262939453125e-6,
    "cached_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
    "output_price": 2.19999999999999994279749337966478606176679022610187530517578125e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 4.400000000000000224408165661049707750862580724060535430908203125e-6,
            "caching_price": 5.499999999999999856993733449161965154416975565254688262939453125e-6,
            "caching_5m_price": 5.499999999999999856993733449161965154416975565254688262939453125e-6,
            "caching_1h_price": 8.80000000000000044881633132209941550172516144812107086181640625e-6,
            "cached_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
            "output_price": 2.19999999999999994279749337966478606176679022610187530517578125e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": true,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Claude Opus 5.5 is the first model in Anthropic's Claude 5.5 family and the most capable Opus to date, built for long running autonomous agents, large scale coding, and frontier knowledge work. It improves on Opus 5 in planning, sustained multi step execution, and judgment across extended sessions, at a lower price than Opus 5.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "eu",
    "open_weights": false,
    "model_lab": "anthropic",
    "model_canonical_name": "claude-opus-5-5"
}

{
    "api": "chat",
    "id": "vertex/claude-opus-5-5@us",
    "object": "model",
    "created": 1790098200,
    "updated": 1790668360,
    "owned_by": "system",
    "input_price": 4.400000000000000224408165661049707750862580724060535430908203125e-6,
    "caching_price": 5.499999999999999856993733449161965154416975565254688262939453125e-6,
    "cached_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
    "output_price": 2.19999999999999994279749337966478606176679022610187530517578125e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 4.400000000000000224408165661049707750862580724060535430908203125e-6,
            "caching_price": 5.499999999999999856993733449161965154416975565254688262939453125e-6,
            "caching_5m_price": 5.499999999999999856993733449161965154416975565254688262939453125e-6,
            "caching_1h_price": 8.80000000000000044881633132209941550172516144812107086181640625e-6,
            "cached_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
            "output_price": 2.19999999999999994279749337966478606176679022610187530517578125e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": true,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Claude Opus 5.5 is the first model in Anthropic's Claude 5.5 family and the most capable Opus to date, built for long running autonomous agents, large scale coding, and frontier knowledge work. It improves on Opus 5 in planning, sustained multi step execution, and judgment across extended sessions, at a lower price than Opus 5.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "us",
    "open_weights": false,
    "model_lab": "anthropic",
    "model_canonical_name": "claude-opus-5-5"
}

{
    "api": "chat",
    "id": "bedrock/claude-opus-5-5",
    "object": "model",
    "created": 1790095744,
    "updated": 1790095744,
    "owned_by": "system",
    "input_price": 3.9999999999999998189924473035450347424557548947632312774658203125e-6,
    "caching_price": 5.0000000000000004090152695701565477293115691281855106353759765625e-6,
    "cached_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-7,
    "output_price": 2.000000000000000163606107828062619091724627651274204254150390625e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 3.9999999999999998189924473035450347424557548947632312774658203125e-6,
            "caching_price": 5.0000000000000004090152695701565477293115691281855106353759765625e-6,
            "caching_5m_price": 5.0000000000000004090152695701565477293115691281855106353759765625e-6,
            "caching_1h_price": 7.999999999999999637984894607090069484911509789526462554931640625e-6,
            "cached_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-7,
            "output_price": 2.000000000000000163606107828062619091724627651274204254150390625e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Claude Opus 5.5 is a step-change improvement over Opus 5, with the biggest gains in agentic coding, long-running agentic tasks, and knowledge work. It is also a much better collaborator on long-running work. It reports back in plain language on what it did, what it found, and what it needs next.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html",
    "geolocation": "global",
    "open_weights": false,
    "model_lab": "anthropic",
    "model_canonical_name": "claude-opus-5-5"
}

{
    "api": "chat",
    "id": "bedrock/claude-opus-5-5@eu-central-1",
    "object": "model",
    "created": 1790095261,
    "updated": 1790095261,
    "owned_by": "system",
    "input_price": 4.400000000000000224408165661049707750862580724060535430908203125e-6,
    "caching_price": 5.499999999999999856993733449161965154416975565254688262939453125e-6,
    "cached_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
    "output_price": 2.19999999999999994279749337966478606176679022610187530517578125e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 4.400000000000000224408165661049707750862580724060535430908203125e-6,
            "caching_price": 5.499999999999999856993733449161965154416975565254688262939453125e-6,
            "caching_5m_price": 5.499999999999999856993733449161965154416975565254688262939453125e-6,
            "caching_1h_price": 8.80000000000000044881633132209941550172516144812107086181640625e-6,
            "cached_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
            "output_price": 2.19999999999999994279749337966478606176679022610187530517578125e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Claude Opus 5.5 is a step-change improvement over Opus 5, with the biggest gains in agentic coding, long-running agentic tasks, and knowledge work. It is also a much better collaborator on long-running work. It reports back in plain language on what it did, what it found, and what it needs next.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html",
    "geolocation": "eu",
    "open_weights": false,
    "model_lab": "anthropic",
    "model_canonical_name": "claude-opus-5-5"
}

{
    "api": "chat",
    "id": "bedrock/claude-opus-5-5@eu-north-1",
    "object": "model",
    "created": 1790095261,
    "updated": 1790095261,
    "owned_by": "system",
    "input_price": 4.400000000000000224408165661049707750862580724060535430908203125e-6,
    "caching_price": 5.499999999999999856993733449161965154416975565254688262939453125e-6,
    "cached_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
    "output_price": 2.19999999999999994279749337966478606176679022610187530517578125e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 4.400000000000000224408165661049707750862580724060535430908203125e-6,
            "caching_price": 5.499999999999999856993733449161965154416975565254688262939453125e-6,
            "caching_5m_price": 5.499999999999999856993733449161965154416975565254688262939453125e-6,
            "caching_1h_price": 8.80000000000000044881633132209941550172516144812107086181640625e-6,
            "cached_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
            "output_price": 2.19999999999999994279749337966478606176679022610187530517578125e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Claude Opus 5.5 is a step-change improvement over Opus 5, with the biggest gains in agentic coding, long-running agentic tasks, and knowledge work. It is also a much better collaborator on long-running work. It reports back in plain language on what it did, what it found, and what it needs next.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html",
    "geolocation": "eu",
    "open_weights": false,
    "model_lab": "anthropic",
    "model_canonical_name": "claude-opus-5-5"
}

{
    "api": "chat",
    "id": "bedrock/claude-opus-5-5@eu-west-1",
    "object": "model",
    "created": 1790095261,
    "updated": 1790095261,
    "owned_by": "system",
    "input_price": 4.400000000000000224408165661049707750862580724060535430908203125e-6,
    "caching_price": 5.499999999999999856993733449161965154416975565254688262939453125e-6,
    "cached_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
    "output_price": 2.19999999999999994279749337966478606176679022610187530517578125e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 4.400000000000000224408165661049707750862580724060535430908203125e-6,
            "caching_price": 5.499999999999999856993733449161965154416975565254688262939453125e-6,
            "caching_5m_price": 5.499999999999999856993733449161965154416975565254688262939453125e-6,
            "caching_1h_price": 8.80000000000000044881633132209941550172516144812107086181640625e-6,
            "cached_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
            "output_price": 2.19999999999999994279749337966478606176679022610187530517578125e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Claude Opus 5.5 is a step-change improvement over Opus 5, with the biggest gains in agentic coding, long-running agentic tasks, and knowledge work. It is also a much better collaborator on long-running work. It reports back in plain language on what it did, what it found, and what it needs next.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html",
    "geolocation": "eu",
    "open_weights": false,
    "model_lab": "anthropic",
    "model_canonical_name": "claude-opus-5-5"
}

{
    "api": "chat",
    "id": "bedrock/claude-opus-5-5@eu-west-3",
    "object": "model",
    "created": 1790095261,
    "updated": 1790095261,
    "owned_by": "system",
    "input_price": 4.400000000000000224408165661049707750862580724060535430908203125e-6,
    "caching_price": 5.499999999999999856993733449161965154416975565254688262939453125e-6,
    "cached_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
    "output_price": 2.19999999999999994279749337966478606176679022610187530517578125e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 4.400000000000000224408165661049707750862580724060535430908203125e-6,
            "caching_price": 5.499999999999999856993733449161965154416975565254688262939453125e-6,
            "caching_5m_price": 5.499999999999999856993733449161965154416975565254688262939453125e-6,
            "caching_1h_price": 8.80000000000000044881633132209941550172516144812107086181640625e-6,
            "cached_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
            "output_price": 2.19999999999999994279749337966478606176679022610187530517578125e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Claude Opus 5.5 is a step-change improvement over Opus 5, with the biggest gains in agentic coding, long-running agentic tasks, and knowledge work. It is also a much better collaborator on long-running work. It reports back in plain language on what it did, what it found, and what it needs next.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html",
    "geolocation": "eu",
    "open_weights": false,
    "model_lab": "anthropic",
    "model_canonical_name": "claude-opus-5-5"
}

{
    "api": "chat",
    "id": "xiaomi/mimo-v2.6-pro",
    "object": "model",
    "created": 1790075519,
    "updated": 1791474259,
    "owned_by": "system",
    "input_price": 4.3500000000000001737312008663616236248117274953983724117279052734375e-7,
    "cached_price": 3.59999999999999997605954548209918064660683967304066754877567291259765625e-9,
    "output_price": 8.700000000000000347462401732723247249623454990796744823455810546875e-7,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 4.3500000000000001737312008663616236248117274953983724117279052734375e-7,
            "cached_price": 3.59999999999999997605954548209918064660683967304066754877567291259765625e-9,
            "output_price": 8.700000000000000347462401732723247249623454990796744823455810546875e-7
        }
    ],
    "max_output_tokens": 131072,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Xiaomi MiMo V2.6 Pro. Flagship 1T+ parameter MoE, native omni-modal input (text, image, video, audio), text output. 1M token context window, 128K max output. OpenAI-compatible.",
    "data_retention": true,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "quantization": "fp8",
    "hugging_face_id": "XiaomiMiMo/MiMo-V2.6-Pro-RL",
    "open_weights": true,
    "model_lab": "xiaomi",
    "model_canonical_name": "mimo-v2.6-pro"
}

{
    "api": "chat",
    "id": "xiaomi/mimo-v2.6-flash",
    "object": "model",
    "created": 1790075515,
    "updated": 1791474259,
    "owned_by": "system",
    "input_price": 1.40000000000000009546603416642207573516998309059999883174896240234375e-7,
    "cached_price": 2.799999999999999843516211060572528024348315511815599165856838226318359375e-9,
    "output_price": 2.8000000000000001909320683328441514703399661811999976634979248046875e-7,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.40000000000000009546603416642207573516998309059999883174896240234375e-7,
            "cached_price": 2.799999999999999843516211060572528024348315511815599165856838226318359375e-9,
            "output_price": 2.8000000000000001909320683328441514703399661811999976634979248046875e-7
        }
    ],
    "max_output_tokens": 131072,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Xiaomi MiMo V2.6 Flash. 309B total / 15B active MoE with hybrid attention, native omni-modal input (text, image, video, audio), text output. 1M token context window, 128K max output. OpenAI-compatible.",
    "data_retention": true,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "quantization": "fp8",
    "hugging_face_id": "XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "open_weights": true,
    "model_lab": "xiaomi",
    "model_canonical_name": "mimo-v2.6-flash"
}

{
    "api": "chat",
    "id": "xiaomi/mimo-v2.6-pro-ultraspeed",
    "object": "model",
    "created": 1790075438,
    "updated": 1791474259,
    "owned_by": "system",
    "input_price": 4.3499999999999998560938456459989964741907897405326366424560546875e-6,
    "cached_price": 3.599999999999999810623422971493645672325101259048096835613250732421875e-8,
    "output_price": 8.699999999999999712187691291997992948381579481065273284912109375e-6,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 4.3499999999999998560938456459989964741907897405326366424560546875e-6,
            "cached_price": 3.599999999999999810623422971493645672325101259048096835613250732421875e-8,
            "output_price": 8.699999999999999712187691291997992948381579481065273284912109375e-6
        }
    ],
    "max_output_tokens": 131072,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Xiaomi MiMo V2.6 Pro UltraSpeed. Same 1T+ MiMo V2.6 Pro checkpoint served at roughly 10x output speed for latency sensitive workloads. Omni-modal input (text, image, video, audio), text output. 1M token context window, 128K max output. OpenAI-compatible.",
    "data_retention": true,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "quantization": "fp8",
    "hugging_face_id": "XiaomiMiMo/MiMo-V2.6-Pro-RL",
    "open_weights": true,
    "model_lab": "xiaomi",
    "model_canonical_name": "mimo-v2.6-pro-ultraspeed"
}

{
    "api": "chat",
    "id": "bedrock/claude-opus-5-5@ap-northeast-1",
    "object": "model",
    "created": 1790035200,
    "updated": 1791362458,
    "owned_by": "system",
    "input_price": 4.400000000000000224408165661049707750862580724060535430908203125e-6,
    "caching_price": 5.499999999999999856993733449161965154416975565254688262939453125e-6,
    "cached_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
    "output_price": 2.19999999999999994279749337966478606176679022610187530517578125e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 4.400000000000000224408165661049707750862580724060535430908203125e-6,
            "caching_price": 5.499999999999999856993733449161965154416975565254688262939453125e-6,
            "caching_5m_price": 5.499999999999999856993733449161965154416975565254688262939453125e-6,
            "caching_1h_price": 8.80000000000000044881633132209941550172516144812107086181640625e-6,
            "cached_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
            "output_price": 2.19999999999999994279749337966478606176679022610187530517578125e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Claude Opus 5.5 is a step-change improvement over Opus 5, with the biggest gains in agentic coding, long-running agentic tasks, and knowledge work. It is also a much better collaborator on long-running work. It reports back in plain language on what it did, what it found, and what it needs next.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html",
    "geolocation": "ap",
    "open_weights": false,
    "model_lab": "anthropic",
    "model_canonical_name": "claude-opus-5-5"
}

{
    "api": "chat",
    "id": "bedrock/claude-opus-5-5@ap-northeast-3",
    "object": "model",
    "created": 1790035200,
    "updated": 1791362458,
    "owned_by": "system",
    "input_price": 4.400000000000000224408165661049707750862580724060535430908203125e-6,
    "caching_price": 5.499999999999999856993733449161965154416975565254688262939453125e-6,
    "cached_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
    "output_price": 2.19999999999999994279749337966478606176679022610187530517578125e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 4.400000000000000224408165661049707750862580724060535430908203125e-6,
            "caching_price": 5.499999999999999856993733449161965154416975565254688262939453125e-6,
            "caching_5m_price": 5.499999999999999856993733449161965154416975565254688262939453125e-6,
            "caching_1h_price": 8.80000000000000044881633132209941550172516144812107086181640625e-6,
            "cached_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
            "output_price": 2.19999999999999994279749337966478606176679022610187530517578125e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Claude Opus 5.5 is a step-change improvement over Opus 5, with the biggest gains in agentic coding, long-running agentic tasks, and knowledge work. It is also a much better collaborator on long-running work. It reports back in plain language on what it did, what it found, and what it needs next.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html",
    "geolocation": "ap",
    "open_weights": false,
    "model_lab": "anthropic",
    "model_canonical_name": "claude-opus-5-5"
}

{
    "api": "chat",
    "id": "bedrock/claude-opus-5-5@ap-southeast-2",
    "object": "model",
    "created": 1790035200,
    "updated": 1791362458,
    "owned_by": "system",
    "input_price": 4.400000000000000224408165661049707750862580724060535430908203125e-6,
    "caching_price": 5.499999999999999856993733449161965154416975565254688262939453125e-6,
    "cached_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
    "output_price": 2.19999999999999994279749337966478606176679022610187530517578125e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 4.400000000000000224408165661049707750862580724060535430908203125e-6,
            "caching_price": 5.499999999999999856993733449161965154416975565254688262939453125e-6,
            "caching_5m_price": 5.499999999999999856993733449161965154416975565254688262939453125e-6,
            "caching_1h_price": 8.80000000000000044881633132209941550172516144812107086181640625e-6,
            "cached_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
            "output_price": 2.19999999999999994279749337966478606176679022610187530517578125e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Claude Opus 5.5 is a step-change improvement over Opus 5, with the biggest gains in agentic coding, long-running agentic tasks, and knowledge work. It is also a much better collaborator on long-running work. It reports back in plain language on what it did, what it found, and what it needs next.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html",
    "geolocation": "ap",
    "open_weights": false,
    "model_lab": "anthropic",
    "model_canonical_name": "claude-opus-5-5"
}

{
    "api": "chat",
    "id": "tencent/mimo-v2.6-flash",
    "object": "model",
    "created": 1790035200,
    "updated": 1791474259,
    "owned_by": "system",
    "input_price": 1.40000000000000009546603416642207573516998309059999883174896240234375e-7,
    "cached_price": 2.799999999999999843516211060572528024348315511815599165856838226318359375e-9,
    "output_price": 2.8000000000000001909320683328441514703399661811999976634979248046875e-7,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.40000000000000009546603416642207573516998309059999883174896240234375e-7,
            "cached_price": 2.799999999999999843516211060572528024348315511815599165856838226318359375e-9,
            "output_price": 2.8000000000000001909320683328441514703399661811999976634979248046875e-7
        }
    ],
    "max_output_tokens": 131072,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "MiMo-V2.6-Flash is Xiaomi's fast, cost-efficient multimodal model with a 1M token context window, supporting text, image and video input, deep thinking, function calling and structured output.",
    "data_retention": true,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "sg",
    "hugging_face_id": "XiaomiMiMo/MiMo-V2.6-Flash-RL",
    "open_weights": true,
    "model_lab": "xiaomi",
    "model_canonical_name": "mimo-v2.6-flash"
}

{
    "api": "chat",
    "id": "tencent/mimo-v2.6-pro",
    "object": "model",
    "created": 1790035200,
    "updated": 1791474259,
    "owned_by": "system",
    "input_price": 4.3500000000000001737312008663616236248117274953983724117279052734375e-7,
    "cached_price": 3.59999999999999997605954548209918064660683967304066754877567291259765625e-9,
    "output_price": 8.700000000000000347462401732723247249623454990796744823455810546875e-7,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 4.3500000000000001737312008663616236248117274953983724117279052734375e-7,
            "cached_price": 3.59999999999999997605954548209918064660683967304066754877567291259765625e-9,
            "output_price": 8.700000000000000347462401732723247249623454990796744823455810546875e-7
        }
    ],
    "max_output_tokens": 131072,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "MiMo-V2.6-Pro is Xiaomi's flagship multimodal model with a 1M token context window, supporting text, image and video input, deep thinking, function calling and structured output.",
    "data_retention": true,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "sg",
    "hugging_face_id": "XiaomiMiMo/MiMo-V2.6-Pro-RL",
    "open_weights": true,
    "model_lab": "xiaomi",
    "model_canonical_name": "mimo-v2.6-pro"
}

{
    "api": "chat",
    "id": "xai/grok-4.7",
    "object": "model",
    "created": 1790008976,
    "updated": 1790008976,
    "owned_by": "system",
    "input_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-6,
    "caching_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-6,
    "cached_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-7,
    "output_price": 6.00000000000000015200514458246772164784488268196582794189453125e-6,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-6,
            "caching_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-6,
            "cached_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-7,
            "output_price": 6.00000000000000015200514458246772164784488268196582794189453125e-6
        }
    ],
    "max_output_tokens": 0,
    "context_window": 500000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": true,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and managing long context, and it improves on its predecessor at professional knowledge work such as drafting documents and presentations.\n\nThe model was trained with a longer reinforcement learning run weighted toward problems that take many hours to complete, and natively understands the Grok Bot harness for conversational tasks. It ships with a new safeguard stack that pairs strong jailbreak resistance with low refusal rates for legitimate cybersecurity and biology work. SpaceXAI's reported benchmark results use the xhigh reasoning effort.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "open_weights": false,
    "model_lab": "xai",
    "model_canonical_name": "grok-4.7"
}

{
    "api": "chat",
    "id": "typesafe/jev-1.13.0",
    "object": "model",
    "created": 1789746304,
    "updated": 1789746304,
    "owned_by": "system",
    "input_price": 4.199999999999999889351408473812943267233777078217826783657073974609375e-8,
    "output_price": 0,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 4.199999999999999889351408473812943267233777078217826783657073974609375e-8,
            "output_price": 0
        }
    ],
    "max_output_tokens": 1024,
    "context_window": 64000,
    "supports_caching": false,
    "supports_vision": false,
    "supports_computer_use": false,
    "supports_reasoning": false,
    "supports_image_generation": false,
    "supports_tool_calling": false,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": false,
    "supports_output_json_schema": false,
    "supports_system_mid_conversation": true,
    "description": "Jev is TypeSafe’s flagship model and the first System One model.",
    "data_retention": true,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "Data retention period is not specified",
    "geolocation": "global",
    "open_weights": false,
    "model_lab": "typesafe",
    "model_canonical_name": "jev"
}

{
    "api": "chat",
    "id": "tencent/glm-5.3-flashx",
    "object": "model",
    "created": 1789689600,
    "updated": 1790594486,
    "owned_by": "system",
    "input_price": 3.7000000000000000443262505693542419038521984475664794445037841796875e-7,
    "cached_price": 7.4999999999999996606108386941469401421045404276810586452484130859375e-8,
    "output_price": 1.250000000000000102253817392539136932327892282046377658843994140625e-6,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 3.7000000000000000443262505693542419038521984475664794445037841796875e-7,
            "cached_price": 7.4999999999999996606108386941469401421045404276810586452484130859375e-8,
            "output_price": 1.250000000000000102253817392539136932327892282046377658843994140625e-6
        }
    ],
    "max_output_tokens": 131072,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": false,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "GLM-5.3-FlashX is the enhanced, high-speed (~200 tokens/s) variant of GLM-5.3-Flash with a 1M token context window and image, video and file understanding.",
    "data_retention": true,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "sg",
    "open_weights": true,
    "model_lab": "zai",
    "model_canonical_name": "glm-5.3-flashx"
}

{
    "api": "chat",
    "id": "runware/deepseek-v4.1-flash",
    "object": "model",
    "created": 1789487766,
    "updated": 1791474259,
    "owned_by": "system",
    "input_price": 1.4999999999999999321221677388293880284209080855362117290496826171875e-7,
    "cached_price": 1.0000000000000000209225608301284726753266340892878361046314239501953125e-8,
    "output_price": 5.99999999999999972848867095531755211368363234214484691619873046875e-7,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.4999999999999999321221677388293880284209080855362117290496826171875e-7,
            "cached_price": 1.0000000000000000209225608301284726753266340892878361046314239501953125e-8,
            "output_price": 5.99999999999999972848867095531755211368363234214484691619873046875e-7
        }
    ],
    "max_output_tokens": 384000,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start of pre-training rather than added afterward as in the earlier experimental V4 Flash Vision Exp.\n\nIt is suited for coding, terminal, and computer-use agents, along with long-horizon tasks that must run to completion across many steps and long-context analysis. Compressed KV caching cuts cache memory to roughly a quarter of the previous Flash generation, significantly reducing costs on agentic workloads. DeepSeek positions it as the cost-efficient tier of the V4.1 family and reports that it exceeds V4 Pro on performance, speed, and task completion time.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "hugging_face_id": "deepseek-ai/DeepSeek-V4.1-Flash",
    "open_weights": true,
    "model_lab": "deepseek",
    "model_canonical_name": "deepseek-v4.1-flash"
}

{
    "api": "chat",
    "id": "mistral/glm-5-3",
    "object": "model",
    "created": 1789430400,
    "updated": 1791971563,
    "owned_by": "system",
    "input_price": 1.54000000000000007854285798136739771280190325342118740081787109375e-6,
    "cached_price": 1.6000000000000000334760973282055562805226145428605377674102783203125e-7,
    "output_price": 4.8400000000000002468489822271546785259488387964665889739990234375e-6,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.54000000000000007854285798136739771280190325342118740081787109375e-6,
            "cached_price": 1.6000000000000000334760973282055562805226145428605377674102783203125e-7,
            "output_price": 4.8400000000000002468489822271546785259488387964665889739990234375e-6
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": false,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "GLM 5.3 by Z.ai is an open weights model served by Mistral on EU infrastructure with no Mistral modifications. 1M token context window, 128K max output. Text only. Supports reasoning, function calling, structured outputs, predicted outputs and prefix. Built for long context coding and agentic workflows.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "eu",
    "hugging_face_id": "zai-org/GLM-5.3",
    "open_weights": true,
    "model_lab": "zai",
    "model_canonical_name": "glm-5.3"
}

{
    "api": "chat",
    "id": "sference/deepseek-v4.1-flash",
    "object": "model",
    "created": 1789201097,
    "updated": 1791474259,
    "owned_by": "system",
    "input_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-7,
    "cached_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-8,
    "output_price": 1.5000000000000000380012861456169304119612206704914569854736328125e-6,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-7,
            "cached_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-8,
            "output_price": 1.5000000000000000380012861456169304119612206704914569854736328125e-6
        }
    ],
    "max_output_tokens": 393216,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "DeepSeek V4.1 Flash is a 552B parameter Mixture of Experts model built on a new Causal Encoder Decoder architecture that activates only 8B parameters for input and 16B for output, giving frontier level intelligence at a fraction of the cost. It is the smallest model in the new DeepSeek architecture family and the first Flash with native vision and multimodal understanding. V4.1 Flash beats DeepSeek V4 Pro on performance, cost, speed and task completion time and scores 88.1 on CyberGym. Its KV cache is compressed to 890 bytes per token, four times smaller than V4 Flash and over 400 times smaller than V1, cutting the cache hit costs that dominate agent workloads. 1M token context window, 384K max output, thinking and non thinking modes, tool calling, structured JSON output and prompt caching. Served in the EU via Sference at $0.50 input, $0.05 cache read and $1.50 output per 1M tokens, with no data retention and no training on user data. Open weights are published on Hugging Face. Ideal for EU hosted coding agents, long context RAG, high throughput batch processing and multimodal assistants.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "No training on user data",
    "geolocation": "eu",
    "hugging_face_id": "deepseek-ai/DeepSeek-V4.1-Flash",
    "open_weights": true,
    "model_lab": "deepseek",
    "model_canonical_name": "deepseek-v4.1-flash"
}

{
    "api": "chat",
    "id": "tensorx/deepseek-v4.1-flash",
    "object": "model",
    "created": 1789201097,
    "updated": 1791474259,
    "owned_by": "system",
    "input_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-7,
    "cached_price": 1.29999999999999999411210457704590748306827663327567279338836669921875e-7,
    "output_price": 1.5000000000000000380012861456169304119612206704914569854736328125e-6,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-7,
            "cached_price": 1.29999999999999999411210457704590748306827663327567279338836669921875e-7,
            "output_price": 1.5000000000000000380012861456169304119612206704914569854736328125e-6
        }
    ],
    "max_output_tokens": 393216,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "DeepSeek V4.1 Flash is a 552B parameter Mixture of Experts model built on a new Causal Encoder Decoder architecture that activates only 8B parameters for input and 16B for output, giving frontier level intelligence at a fraction of the cost. It is the smallest model in the new DeepSeek architecture family and the first Flash with native vision and multimodal understanding. V4.1 Flash beats DeepSeek V4 Pro on performance, cost, speed and task completion time. 1M token context window, 384K max output, thinking and non thinking modes, tool calling, structured JSON output and prompt caching. Served in the EU via TensorX at $0.50 input, $0.13 cache read and $1.50 output per 1M tokens, with no data retention and no training on user data. Open weights are published on Hugging Face.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "No training on user data",
    "geolocation": "eu",
    "hugging_face_id": "deepseek-ai/DeepSeek-V4.1-Flash",
    "open_weights": true,
    "model_lab": "deepseek",
    "model_canonical_name": "deepseek-v4.1-flash"
}

{
    "api": "chat",
    "id": "fireworks/deepseek-v4.1-flash",
    "object": "model",
    "created": 1789116795,
    "updated": 1791474259,
    "owned_by": "system",
    "input_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
    "cached_price": 6.999999999999999815585680789688238778722961797029711306095123291015625e-9,
    "output_price": 6.6000000000000003366122484915745616262938710860908031463623046875e-7,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
            "cached_price": 6.999999999999999815585680789688238778722961797029711306095123291015625e-9,
            "output_price": 6.6000000000000003366122484915745616262938710860908031463623046875e-7
        }
    ],
    "max_output_tokens": 393216,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "DeepSeek V4.1 Flash is a 552B parameter Mixture of Experts model built on a new Causal Encoder Decoder architecture that activates only 8B parameters for input and 16B for output, giving frontier level intelligence at a fraction of the cost. It is the smallest model in the new DeepSeek architecture family and the first Flash with native vision and multimodal understanding. V4.1 Flash beats DeepSeek V4 Pro on performance, cost, speed and task completion time and scores 88.1 on CyberGym. Its KV cache is compressed to 890 bytes per token, four times smaller than V4 Flash and over 400 times smaller than V1, cutting the cache hit costs that dominate agent workloads. 1M token context window, 384K max output, thinking and non thinking modes, tool calling, structured JSON output and prompt caching. Served on Fireworks at $0.22 input, $0.007 cache read and $0.66 output per 1M tokens. Open weights are published on Hugging Face. Ideal for coding agents, long context RAG, high throughput batch processing and multimodal assistants.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "hugging_face_id": "deepseek-ai/DeepSeek-V4.1-Flash",
    "open_weights": true,
    "model_lab": "deepseek",
    "model_canonical_name": "deepseek-v4.1-flash"
}

{
    "api": "chat",
    "id": "novita/deepseek-v4.1-flash",
    "object": "model",
    "created": 1789037733,
    "updated": 1791474259,
    "owned_by": "system",
    "input_price": 2.999999999999999864244335477658776056841816171072423458099365234375e-7,
    "cached_price": 5.99999999999999996009924247016530107767806612173444591462612152099609375e-9,
    "output_price": 1.19999999999999994569773419106351042273672646842896938323974609375e-6,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 2.999999999999999864244335477658776056841816171072423458099365234375e-7,
            "cached_price": 5.99999999999999996009924247016530107767806612173444591462612152099609375e-9,
            "output_price": 1.19999999999999994569773419106351042273672646842896938323974609375e-6
        }
    ],
    "max_output_tokens": 393216,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "DeepSeek V4.1 Flash is a 552B parameter Mixture of Experts model built on a new Causal Encoder Decoder architecture that activates only 8B parameters for input and 16B for output, giving frontier level intelligence at a fraction of the cost. It is the smallest model in the new DeepSeek architecture family and the first Flash with native vision and multimodal understanding. V4.1 Flash beats DeepSeek V4 Pro on performance, cost, speed and task completion time and scores 88.1 on CyberGym. Its KV cache is compressed to 890 bytes per token, four times smaller than V4 Flash and over 400 times smaller than V1, cutting the cache hit costs that dominate agent workloads. 1M token context window, 384K max output, thinking and non thinking modes, tool calling, structured JSON output and prompt caching. Served on Novita at $0.30 input, $0.006 cache read and $1.20 output per 1M tokens. Open weights are published on Hugging Face. Ideal for coding agents, long context RAG, high throughput batch processing and multimodal assistants.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "quantization": "fp8",
    "hugging_face_id": "deepseek-ai/DeepSeek-V4.1-Flash",
    "open_weights": true,
    "model_lab": "deepseek",
    "model_canonical_name": "deepseek-v4.1-flash"
}

{
    "api": "chat",
    "id": "deepseek/deepseek-v4.1-flash",
    "object": "model",
    "created": 1789010266,
    "updated": 1792229063,
    "owned_by": "system",
    "input_price": 2.999999999999999864244335477658776056841816171072423458099365234375e-7,
    "cached_price": 5.99999999999999996009924247016530107767806612173444591462612152099609375e-9,
    "output_price": 1.19999999999999994569773419106351042273672646842896938323974609375e-6,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 2.999999999999999864244335477658776056841816171072423458099365234375e-7,
            "cached_price": 5.99999999999999996009924247016530107767806612173444591462612152099609375e-9,
            "output_price": 1.19999999999999994569773419106351042273672646842896938323974609375e-6
        }
    ],
    "max_output_tokens": 384000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": true,
    "supports_output_json_object": true,
    "supports_output_json_schema": false,
    "supports_system_mid_conversation": true,
    "description": "DeepSeek V4.1 Flash is a 552B parameter Mixture of Experts model built on a new Causal Encoder Decoder architecture that activates only 8B parameters for input and 16B for output, giving frontier level intelligence at a fraction of the cost. It is the smallest model in the new DeepSeek architecture family and the first Flash with native vision and multimodal understanding. V4.1 Flash beats DeepSeek V4 Pro on performance, cost, speed and task completion time and scores 88.1 on CyberGym. Its KV cache is compressed to 890 bytes per token, four times smaller than V4 Flash and over 400 times smaller than V1, cutting the cache hit costs that dominate agent workloads. 1M token context window, 384K max output, thinking and non thinking modes, tool calling, JSON output and prompt caching. Pricing per 1M tokens starts at $0.003 for cache hits, $0.15 input and $0.60 output off peak, with peak rates at double (01:00 to 04:00 and 06:00 to 10:00 UTC, Monday to Friday). Open weights are published on Hugging Face. Ideal for coding agents, long context RAG, high throughput batch processing and multimodal assistants. Replaces deepseek-v4-flash and deepseek-v4-flash-vision-exp, both still accepted as aliases.",
    "data_retention": true,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "No online information",
    "geolocation": "global",
    "hugging_face_id": "deepseek-ai/DeepSeek-V4.1-Flash",
    "open_weights": true,
    "model_lab": "deepseek",
    "model_canonical_name": "deepseek-v4.1-flash"
}

{
    "api": "chat",
    "id": "melious/deepseek-v4.1-flash",
    "object": "model",
    "created": 1788998400,
    "updated": 1791474259,
    "owned_by": "system",
    "input_price": 2.29999999999999994886021640293216616868221535696648061275482177734375e-7,
    "cached_price": 2.000000000000000041845121660256945350653268178575672209262847900390625e-8,
    "output_price": 1.1400000000000000966436132510128942385563277639448642730712890625e-6,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 2.29999999999999994886021640293216616868221535696648061275482177734375e-7,
            "cached_price": 2.000000000000000041845121660256945350653268178575672209262847900390625e-8,
            "output_price": 1.1400000000000000966436132510128942385563277639448642730712890625e-6
        }
    ],
    "max_output_tokens": 384000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": false,
    "supports_system_mid_conversation": false,
    "description": "DeepSeek V4.1 Flash is a 552B MoE hybrid reasoning model with image input and a 1M token context, suited for agentic coding and long context work. Served from the EU by Melious.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "EU only inference (Finland, Ireland), no prompt or response logging, no training on customer data.",
    "geolocation": "eu",
    "hugging_face_id": "deepseek-ai/DeepSeek-V4.1-Flash",
    "open_weights": true,
    "model_lab": "deepseek",
    "model_canonical_name": "deepseek-v4.1-flash"
}

{
    "api": "chat",
    "id": "tencent/deepseek-v4.1-flash",
    "object": "model",
    "created": 1788998400,
    "updated": 1791474259,
    "owned_by": "system",
    "input_price": 2.999999999999999864244335477658776056841816171072423458099365234375e-7,
    "cached_price": 5.99999999999999996009924247016530107767806612173444591462612152099609375e-9,
    "output_price": 1.19999999999999994569773419106351042273672646842896938323974609375e-6,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 2.999999999999999864244335477658776056841816171072423458099365234375e-7,
            "cached_price": 5.99999999999999996009924247016530107767806612173444591462612152099609375e-9,
            "output_price": 1.19999999999999994569773419106351042273672646842896938323974609375e-6
        }
    ],
    "max_output_tokens": 393216,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": false,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": false,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "DeepSeek-V4.1-Flash is DeepSeek's efficient production model with a 1M token context window, configurable thinking mode and strong tool calling for high-concurrency, low-latency workloads.",
    "data_retention": true,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "sg",
    "hugging_face_id": "deepseek-ai/DeepSeek-V4.1-Flash",
    "open_weights": true,
    "model_lab": "deepseek",
    "model_canonical_name": "deepseek-v4.1-flash"
}

{
    "api": "chat",
    "id": "deepinfra/deepseek-v4.1-flash",
    "object": "model",
    "created": 1788912000,
    "updated": 1791474259,
    "owned_by": "system",
    "input_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-7,
    "cached_price": 5.99999999999999996009924247016530107767806612173444591462612152099609375e-9,
    "output_price": 5.99999999999999972848867095531755211368363234214484691619873046875e-7,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-7,
            "cached_price": 5.99999999999999996009924247016530107767806612173444591462612152099609375e-9,
            "output_price": 5.99999999999999972848867095531755211368363234214484691619873046875e-7
        }
    ],
    "max_output_tokens": 0,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "DeepSeek V4.1 Flash is a 552B parameter Mixture of Experts model built on a new Causal Encoder Decoder architecture that activates only 8B parameters for input and 16B for output, giving frontier level intelligence at a fraction of the cost. It is the smallest model in the new DeepSeek architecture family and the first Flash with native vision and multimodal understanding. V4.1 Flash beats DeepSeek V4 Pro on performance, cost, speed and task completion time and scores 88.1 on CyberGym. Its KV cache is compressed to 890 bytes per token, four times smaller than V4 Flash and over 400 times smaller than V1, cutting the cache hit costs that dominate agent workloads. 1M token context window, 384K max output, thinking and non thinking modes, tool calling, structured JSON output and prompt caching. Served on DeepInfra in FP8 at $0.20 input, $0.006 cache read and $0.60 output per 1M tokens, with a flex tier at 0.8x. Open weights are published on Hugging Face. Ideal for coding agents, long context RAG, high throughput batch processing and multimodal assistants.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "quantization": "fp8",
    "hugging_face_id": "deepseek-ai/DeepSeek-V4.1-Flash",
    "open_weights": true,
    "model_lab": "deepseek",
    "model_canonical_name": "deepseek-v4.1-flash"
}

{
    "api": "chat",
    "id": "deepinfra/deepseek-v4.1-flash:flex",
    "object": "model",
    "created": 1788912000,
    "updated": 1791474259,
    "owned_by": "system",
    "input_price": 1.6000000000000000334760973282055562805226145428605377674102783203125e-7,
    "cached_price": 4.799999999999999968079393976132240862142452897387556731700897216796875e-9,
    "output_price": 4.799999999999999571032699950678956923866280703805387020111083984375e-7,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.6000000000000000334760973282055562805226145428605377674102783203125e-7,
            "cached_price": 4.799999999999999968079393976132240862142452897387556731700897216796875e-9,
            "output_price": 4.799999999999999571032699950678956923866280703805387020111083984375e-7
        }
    ],
    "max_output_tokens": 0,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "DeepSeek V4.1 Flash is a 552B parameter Mixture of Experts model built on a new Causal Encoder Decoder architecture that activates only 8B parameters for input and 16B for output, giving frontier level intelligence at a fraction of the cost. It is the smallest model in the new DeepSeek architecture family and the first Flash with native vision and multimodal understanding. V4.1 Flash beats DeepSeek V4 Pro on performance, cost, speed and task completion time and scores 88.1 on CyberGym. Its KV cache is compressed to 890 bytes per token, four times smaller than V4 Flash and over 400 times smaller than V1, cutting the cache hit costs that dominate agent workloads. 1M token context window, 384K max output, thinking and non thinking modes, tool calling, structured JSON output and prompt caching. Served on DeepInfra in FP8 at $0.20 input, $0.006 cache read and $0.60 output per 1M tokens, with a flex tier at 0.8x. Open weights are published on Hugging Face. Ideal for coding agents, long context RAG, high throughput batch processing and multimodal assistants.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "quantization": "fp8",
    "hugging_face_id": "deepseek-ai/DeepSeek-V4.1-Flash",
    "open_weights": true,
    "model_lab": "deepseek",
    "model_canonical_name": "deepseek-v4.1-flash"
}

{
    "api": "chat",
    "id": "together/deepseek-v4.1-flash",
    "object": "model",
    "created": 1788912000,
    "updated": 1791974914,
    "owned_by": "system",
    "input_price": 2.999999999999999864244335477658776056841816171072423458099365234375e-7,
    "cached_price": 1.0000000000000000209225608301284726753266340892878361046314239501953125e-8,
    "output_price": 1.19999999999999994569773419106351042273672646842896938323974609375e-6,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 2.999999999999999864244335477658776056841816171072423458099365234375e-7,
            "cached_price": 1.0000000000000000209225608301284726753266340892878361046314239501953125e-8,
            "output_price": 1.19999999999999994569773419106351042273672646842896938323974609375e-6
        }
    ],
    "max_output_tokens": 0,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "DeepSeek V4.1 Flash is a 552B parameter Mixture of Experts model built on a new Causal Encoder Decoder architecture that activates only 8B parameters for input and 16B for output, giving frontier level intelligence at a fraction of the cost. It is the smallest model in the new DeepSeek architecture family and the first Flash with native vision and multimodal understanding. V4.1 Flash beats DeepSeek V4 Pro on performance, cost, speed and task completion time and scores 88.1 on CyberGym. Its KV cache is compressed to 890 bytes per token, four times smaller than V4 Flash and over 400 times smaller than V1, cutting the cache hit costs that dominate agent workloads. 1M token context window, 384K max output, thinking and non thinking modes, tool calling, structured JSON output and prompt caching. Served on DeepInfra in FP8 at $0.20 input, $0.006 cache read and $0.60 output per 1M tokens, with a flex tier at 0.8x. Open weights are published on Hugging Face. Ideal for coding agents, long context RAG, high throughput batch processing and multimodal assistants.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "hugging_face_id": "deepseek-ai/DeepSeek-V4.1-Flash",
    "open_weights": true,
    "model_lab": "deepseek",
    "model_canonical_name": "deepseek-v4.1-flash"
}

{
    "api": "chat",
    "id": "openai/gpt-6-astra:flex",
    "object": "model",
    "created": 1788556144,
    "updated": 1790847020,
    "owned_by": "system",
    "input_price": 5.0000000000000004090152695701565477293115691281855106353759765625e-6,
    "caching_price": 6.2500000000000002995108501491205998945588362403213977813720703125e-6,
    "cached_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-7,
    "output_price": 2.500000000000000119804340059648239957823534496128559112548828125e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 5.0000000000000004090152695701565477293115691281855106353759765625e-6,
            "caching_price": 6.2500000000000002995108501491205998945588362403213977813720703125e-6,
            "cached_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-7,
            "output_price": 2.500000000000000119804340059648239957823534496128559112548828125e-5
        },
        {
            "prompt_tokens_threshold": 272000,
            "input_price": 1.0000000000000000818030539140313095458623138256371021270751953125e-5,
            "caching_price": 1.2500000000000000599021700298241199789117672480642795562744140625e-5,
            "cached_price": 9.99999999999999954748111825886258685613938723690807819366455078125e-7,
            "output_price": 3.74999999999999967148674173689215649574180133640766143798828125e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1050000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": true,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "GPT-6 Astra is OpenAI's most capable model, built for the hardest end-to-end work. It is suited for complex reasoning, coding, computer use, research, and document creation, with reasoning effort levels from low up to xhigh and max.",
    "data_retention": true,
    "data_retention_days": 30,
    "data_used_for_training": false,
    "privacy_comments": "No training on customer data. Data retained for 30 days.",
    "geolocation": "global",
    "open_weights": false,
    "model_lab": "openai",
    "model_canonical_name": "gpt-6-astra"
}

{
    "api": "chat",
    "id": "azure/gpt-6-astra@eastus2",
    "object": "model",
    "created": 1788555830,
    "updated": 1790845756,
    "owned_by": "system",
    "input_price": 1.0000000000000000818030539140313095458623138256371021270751953125e-5,
    "caching_price": 1.2500000000000000599021700298241199789117672480642795562744140625e-5,
    "cached_price": 9.99999999999999954748111825886258685613938723690807819366455078125e-7,
    "output_price": 5.00000000000000023960868011929647991564706899225711822509765625e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.0000000000000000818030539140313095458623138256371021270751953125e-5,
            "caching_price": 1.2500000000000000599021700298241199789117672480642795562744140625e-5,
            "cached_price": 9.99999999999999954748111825886258685613938723690807819366455078125e-7,
            "output_price": 5.00000000000000023960868011929647991564706899225711822509765625e-5
        },
        {
            "prompt_tokens_threshold": 272000,
            "input_price": 2.000000000000000163606107828062619091724627651274204254150390625e-5,
            "caching_price": 2.500000000000000119804340059648239957823534496128559112548828125e-5,
            "cached_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-6,
            "output_price": 7.4999999999999993429734834737843129914836026728153228759765625e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1050000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": true,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "GPT-6 Astra is OpenAI's most capable model, built for the hardest end-to-end work. It is suited for complex reasoning, coding, computer use, research, and document creation, with reasoning effort levels from low up to xhigh and max.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "us",
    "open_weights": false,
    "model_lab": "openai",
    "model_canonical_name": "gpt-6-astra"
}

{
    "api": "chat",
    "id": "openai/gpt-6-astra",
    "object": "model",
    "created": 1788555169,
    "updated": 1790847020,
    "owned_by": "system",
    "input_price": 1.0000000000000000818030539140313095458623138256371021270751953125e-5,
    "caching_price": 1.2500000000000000599021700298241199789117672480642795562744140625e-5,
    "cached_price": 9.99999999999999954748111825886258685613938723690807819366455078125e-7,
    "output_price": 5.00000000000000023960868011929647991564706899225711822509765625e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.0000000000000000818030539140313095458623138256371021270751953125e-5,
            "caching_price": 1.2500000000000000599021700298241199789117672480642795562744140625e-5,
            "cached_price": 9.99999999999999954748111825886258685613938723690807819366455078125e-7,
            "output_price": 5.00000000000000023960868011929647991564706899225711822509765625e-5
        },
        {
            "prompt_tokens_threshold": 272000,
            "input_price": 2.000000000000000163606107828062619091724627651274204254150390625e-5,
            "caching_price": 2.500000000000000119804340059648239957823534496128559112548828125e-5,
            "cached_price": 1.99999999999999990949622365177251737122787744738161563873291015625e-6,
            "output_price": 7.4999999999999993429734834737843129914836026728153228759765625e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1050000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": true,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "GPT-6 Astra is OpenAI's most capable model, built for the hardest end-to-end work. It is suited for complex reasoning, coding, computer use, research, and document creation, with reasoning effort levels from low up to xhigh and max.",
    "data_retention": true,
    "data_retention_days": 30,
    "data_used_for_training": false,
    "privacy_comments": "No training on customer data. Data retained for 30 days.",
    "geolocation": "global",
    "open_weights": false,
    "model_lab": "openai",
    "model_canonical_name": "gpt-6-astra"
}

{
    "api": "chat",
    "id": "vertex/gemini-3.8-flash",
    "object": "model",
    "created": 1788307200,
    "updated": 1788365728,
    "owned_by": "system",
    "input_price": 7.5000000000000001900064307280846520598061033524572849273681640625e-7,
    "cached_price": 7.4999999999999996606108386941469401421045404276810586452484130859375e-8,
    "output_price": 3.75000000000000009500321536404232602990305167622864246368408203125e-6,
    "discount_percentage": 50,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 7.5000000000000001900064307280846520598061033524572849273681640625e-7,
            "cached_price": 7.4999999999999996606108386941469401421045404276810586452484130859375e-8,
            "output_price": 3.75000000000000009500321536404232602990305167622864246368408203125e-6
        }
    ],
    "max_output_tokens": 65535,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": true,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Gemini 3.8 Flash is Google's most intelligent workhorse model, delivering significant improvements over 3.7 Flash across software engineering, agentic tasks, and critical multi step reasoning in specialized domains.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "open_weights": false,
    "model_lab": "google",
    "model_canonical_name": "gemini-3.8-flash"
}

{
    "api": "chat",
    "id": "vertex/gemini-3.8-flash@eu",
    "object": "model",
    "created": 1788307200,
    "updated": 1788365777,
    "owned_by": "system",
    "input_price": 8.250000000000000420765310614468202032867338857613503932952880859375e-7,
    "cached_price": 8.250000000000000420765310614468202032867338857613503932952880859375e-8,
    "output_price": 4.125000000000000316261773714021643399973982013761997222900390625e-6,
    "discount_percentage": 50,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 8.250000000000000420765310614468202032867338857613503932952880859375e-7,
            "cached_price": 8.250000000000000420765310614468202032867338857613503932952880859375e-8,
            "output_price": 4.125000000000000316261773714021643399973982013761997222900390625e-6
        }
    ],
    "max_output_tokens": 65535,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": true,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Gemini 3.8 Flash is Google's most intelligent workhorse model, delivering significant improvements over 3.7 Flash across software engineering, agentic tasks, and critical multi step reasoning in specialized domains.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "eu",
    "open_weights": false,
    "model_lab": "google",
    "model_canonical_name": "gemini-3.8-flash"
}

{
    "api": "chat",
    "id": "anthropic/claude-fable-5.1",
    "object": "model",
    "created": 1788220800,
    "updated": 1788288205,
    "owned_by": "system",
    "input_price": 1.0000000000000000818030539140313095458623138256371021270751953125e-5,
    "caching_price": 1.2500000000000000599021700298241199789117672480642795562744140625e-5,
    "cached_price": 2.4999999999999998868702795647156467140348468092270195484161376953125e-7,
    "output_price": 5.00000000000000023960868011929647991564706899225711822509765625e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.0000000000000000818030539140313095458623138256371021270751953125e-5,
            "caching_price": 1.2500000000000000599021700298241199789117672480642795562744140625e-5,
            "caching_5m_price": 1.2500000000000000599021700298241199789117672480642795562744140625e-5,
            "caching_1h_price": 2.000000000000000163606107828062619091724627651274204254150390625e-5,
            "cached_price": 2.4999999999999998868702795647156467140348468092270195484161376953125e-7,
            "output_price": 5.00000000000000023960868011929647991564706899225711822509765625e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": true,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Claude Fable 5.1 is Anthropic's most capable model, improving on Claude Fable 5 across agentic coding, long running agentic workflows, and knowledge work such as large code refactors, front end and visual code generation, and finance and analysis tasks. It ships a 1M token context window by default with 128K max output, is more token efficient and concise than Fable 5, and supports per message effort control. It is a Mythos class model with robust safeguards.",
    "data_retention": true,
    "data_retention_days": 30,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "open_weights": false,
    "model_lab": "anthropic",
    "model_canonical_name": "claude-fable-5.1"
}

{
    "api": "chat",
    "id": "vertex/claude-fable-5.1",
    "object": "model",
    "created": 1788220800,
    "updated": 1788288205,
    "owned_by": "system",
    "input_price": 1.0000000000000000818030539140313095458623138256371021270751953125e-5,
    "caching_price": 1.2500000000000000599021700298241199789117672480642795562744140625e-5,
    "cached_price": 2.4999999999999998868702795647156467140348468092270195484161376953125e-7,
    "output_price": 5.00000000000000023960868011929647991564706899225711822509765625e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.0000000000000000818030539140313095458623138256371021270751953125e-5,
            "caching_price": 1.2500000000000000599021700298241199789117672480642795562744140625e-5,
            "caching_5m_price": 1.2500000000000000599021700298241199789117672480642795562744140625e-5,
            "caching_1h_price": 2.000000000000000163606107828062619091724627651274204254150390625e-5,
            "cached_price": 2.4999999999999998868702795647156467140348468092270195484161376953125e-7,
            "output_price": 5.00000000000000023960868011929647991564706899225711822509765625e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": true,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Claude Fable 5.1 is Anthropic's most capable model, improving on Claude Fable 5 across agentic coding, long running agentic workflows, and knowledge work such as large code refactors, front end and visual code generation, and finance and analysis tasks. It ships a 1M token context window by default with 128K max output, is more token efficient and concise than Fable 5, and supports per message effort control. It is a Mythos class model with robust safeguards.",
    "data_retention": true,
    "data_retention_days": 30,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "open_weights": false,
    "model_lab": "anthropic",
    "model_canonical_name": "claude-fable-5.1"
}

{
    "api": "chat",
    "id": "vertex/claude-fable-5.1@eu",
    "object": "model",
    "created": 1788220800,
    "updated": 1788288205,
    "owned_by": "system",
    "input_price": 1.099999999999999971398746689832393030883395113050937652587890625e-5,
    "caching_price": 1.3750000000000000489517280877205251954364939592778682708740234375e-5,
    "cached_price": 2.750000000000000140255103538156067344289112952537834644317626953125e-7,
    "output_price": 5.50000000000000019580691235088210078174597583711147308349609375e-5,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.099999999999999971398746689832393030883395113050937652587890625e-5,
            "caching_price": 1.3750000000000000489517280877205251954364939592778682708740234375e-5,
            "caching_5m_price": 1.3750000000000000489517280877205251954364939592778682708740234375e-5,
            "caching_1h_price": 2.19999999999999994279749337966478606176679022610187530517578125e-5,
            "cached_price": 2.750000000000000140255103538156067344289112952537834644317626953125e-7,
            "output_price": 5.50000000000000019580691235088210078174597583711147308349609375e-5
        }
    ],
    "max_output_tokens": 128000,
    "context_window": 1000000,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": true,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": true,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "Claude Fable 5.1 is Anthropic's most capable model, improving on Claude Fable 5 across agentic coding, long running agentic workflows, and knowledge work such as large code refactors, front end and visual code generation, and finance and analysis tasks. It ships a 1M token context window by default with 128K max output, is more token efficient and concise than Fable 5, and supports per message effort control. It is a Mythos class model with robust safeguards.",
    "data_retention": true,
    "data_retention_days": 30,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "eu",
    "open_weights": false,
    "model_lab": "anthropic",
    "model_canonical_name": "claude-fable-5.1"
}

{
    "api": "chat",
    "id": "fireworks/deepseek-v4-flash-vision-exp",
    "object": "model",
    "created": 1788134400,
    "updated": 1791474259,
    "owned_by": "system",
    "input_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
    "cached_price": 6.999999999999999815585680789688238778722961797029711306095123291015625e-9,
    "output_price": 6.6000000000000003366122484915745616262938710860908031463623046875e-7,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 2.2000000000000001122040828305248538754312903620302677154541015625e-7,
            "cached_price": 6.999999999999999815585680789688238778722961797029711306095123291015625e-9,
            "output_price": 6.6000000000000003366122484915745616262938710860908031463623046875e-7
        }
    ],
    "max_output_tokens": 131072,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "DeepSeek V4 Flash Vision Exp is the first experimental multimodal model in the DeepSeek V4 family. It builds on DeepSeek V4 Flash with added visual modules and continued training for visual understanding, with substantially improved multimodal agent capabilities while remaining comparable on text only agent tasks. 305B MoE, 1M token context. Served via Fireworks.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "hugging_face_id": "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp",
    "open_weights": true,
    "model_lab": "deepseek",
    "model_canonical_name": "deepseek-v4-flash-vision-exp"
}

{
    "api": "chat",
    "id": "runware/glm-5.3-flash",
    "object": "model",
    "created": 1787875200,
    "updated": 1791474259,
    "owned_by": "system",
    "input_price": 1.4999999999999999321221677388293880284209080855362117290496826171875e-7,
    "cached_price": 2.999999999999999731895437469174348077416425439878366887569427490234375e-8,
    "output_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-7,
    "pricing": [
        {
            "prompt_tokens_threshold": 0,
            "input_price": 1.4999999999999999321221677388293880284209080855362117290496826171875e-7,
            "cached_price": 2.999999999999999731895437469174348077416425439878366887569427490234375e-8,
            "output_price": 4.999999999999999773740559129431293428069693618454039096832275390625e-7
        }
    ],
    "max_output_tokens": 131072,
    "context_window": 1048576,
    "supports_caching": true,
    "supports_vision": true,
    "supports_computer_use": false,
    "supports_reasoning": true,
    "supports_image_generation": false,
    "supports_tool_calling": true,
    "supports_role_developer": false,
    "supports_web_search": false,
    "supports_output_json_object": true,
    "supports_output_json_schema": true,
    "supports_system_mid_conversation": true,
    "description": "GLM 5.3 Flash is Z.ai's lower-cost model from the GLM 5.3 family for coding and long-horizon agent workflows, with reasoning and efficient long-context serving. Image input is not supported on this deployment. Served via Runware.",
    "data_retention": false,
    "data_retention_days": 0,
    "data_used_for_training": false,
    "privacy_comments": "N/A",
    "geolocation": "global",
    "hugging_face_id": "zai-org/GLM-5.3-Flash",
    "open_weights": true,
    "model_lab": "zai",
    "model_canonical_name": "glm-5.3-flash"
}