{
  "schema_version": "1.0",
  "models": {
    "gemma-7b-it": {
      "mode": "chat",
      "context_window": {
        "max_input": 8192,
        "max_output": 8192,
        "max_tokens": 8192
      },
      "pricing": {
        "input_per_million_tokens": 0.05,
        "output_per_million_tokens": 0.08
      },
      "capabilities": {
        "function_calling": true,
        "vision": false,
        "reasoning": false,
        "prompt_caching": false,
        "response_schema": false
      },
      "last_updated_at": "2026-04-24"
    },
    "llama-3.1-8b-instant": {
      "mode": "chat",
      "context_window": {
        "max_input": 128000,
        "max_output": 8192,
        "max_tokens": 8192
      },
      "pricing": {
        "input_per_million_tokens": 0.05,
        "output_per_million_tokens": 0.08
      },
      "capabilities": {
        "function_calling": true,
        "vision": false,
        "reasoning": false,
        "prompt_caching": false,
        "response_schema": false
      },
      "last_updated_at": "2026-04-24"
    },
    "llama-3.3-70b-versatile": {
      "mode": "chat",
      "context_window": {
        "max_input": 128000,
        "max_output": 32768,
        "max_tokens": 32768
      },
      "pricing": {
        "input_per_million_tokens": 0.59,
        "output_per_million_tokens": 0.79
      },
      "capabilities": {
        "function_calling": true,
        "vision": false,
        "reasoning": false,
        "prompt_caching": false,
        "response_schema": false
      },
      "last_updated_at": "2026-04-24"
    },
    "meta-llama/llama-4-maverick-17b-128e-instruct": {
      "mode": "chat",
      "context_window": {
        "max_input": 131072,
        "max_output": 8192,
        "max_tokens": 8192
      },
      "pricing": {
        "input_per_million_tokens": 0.2,
        "output_per_million_tokens": 0.6
      },
      "capabilities": {
        "function_calling": true,
        "vision": true,
        "reasoning": false,
        "prompt_caching": false,
        "response_schema": true
      },
      "last_updated_at": "2026-04-24"
    },
    "meta-llama/llama-4-scout-17b-16e-instruct": {
      "mode": "chat",
      "context_window": {
        "max_input": 131072,
        "max_output": 8192,
        "max_tokens": 8192
      },
      "pricing": {
        "input_per_million_tokens": 0.11,
        "output_per_million_tokens": 0.34
      },
      "capabilities": {
        "function_calling": true,
        "vision": true,
        "reasoning": false,
        "prompt_caching": false,
        "response_schema": true
      },
      "last_updated_at": "2026-04-24"
    },
    "meta-llama/llama-guard-4-12b": {
      "mode": "chat",
      "context_window": {
        "max_input": 8192,
        "max_output": 8192,
        "max_tokens": 8192
      },
      "pricing": {
        "input_per_million_tokens": 0.2,
        "output_per_million_tokens": 0.2
      },
      "capabilities": {
        "function_calling": false,
        "vision": false,
        "reasoning": false,
        "prompt_caching": false,
        "response_schema": false
      },
      "last_updated_at": "2026-04-24"
    },
    "moonshotai/kimi-k2-instruct-0905": {
      "mode": "chat",
      "context_window": {
        "max_input": 262144,
        "max_output": 16384,
        "max_tokens": 16384
      },
      "pricing": {
        "input_per_million_tokens": 1.0,
        "output_per_million_tokens": 3.0,
        "cache_read_per_million_tokens": 0.5
      },
      "capabilities": {
        "function_calling": true,
        "vision": false,
        "reasoning": false,
        "prompt_caching": false,
        "response_schema": true
      },
      "last_updated_at": "2026-04-24"
    },
    "openai/gpt-oss-120b": {
      "mode": "chat",
      "context_window": {
        "max_input": 131072,
        "max_output": 32766,
        "max_tokens": 32766
      },
      "pricing": {
        "input_per_million_tokens": 0.15,
        "output_per_million_tokens": 0.6,
        "cache_read_per_million_tokens": 0.075
      },
      "capabilities": {
        "function_calling": true,
        "vision": false,
        "reasoning": true,
        "prompt_caching": false,
        "response_schema": true
      },
      "last_updated_at": "2026-04-24"
    },
    "openai/gpt-oss-20b": {
      "mode": "chat",
      "context_window": {
        "max_input": 131072,
        "max_output": 32768,
        "max_tokens": 32768
      },
      "pricing": {
        "input_per_million_tokens": 0.075,
        "output_per_million_tokens": 0.3,
        "cache_read_per_million_tokens": 0.0375
      },
      "capabilities": {
        "function_calling": true,
        "vision": false,
        "reasoning": true,
        "prompt_caching": false,
        "response_schema": true
      },
      "last_updated_at": "2026-04-24"
    },
    "openai/gpt-oss-safeguard-20b": {
      "mode": "chat",
      "context_window": {
        "max_input": 131072,
        "max_output": 65536,
        "max_tokens": 65536
      },
      "pricing": {
        "input_per_million_tokens": 0.075,
        "output_per_million_tokens": 0.3,
        "cache_read_per_million_tokens": 0.037
      },
      "capabilities": {
        "function_calling": true,
        "vision": false,
        "reasoning": true,
        "prompt_caching": false,
        "response_schema": true
      },
      "last_updated_at": "2026-04-24"
    },
    "qwen/qwen3-32b": {
      "mode": "chat",
      "context_window": {
        "max_input": 131000,
        "max_output": 131000,
        "max_tokens": 131000
      },
      "pricing": {
        "input_per_million_tokens": 0.29,
        "output_per_million_tokens": 0.59
      },
      "capabilities": {
        "function_calling": true,
        "vision": false,
        "reasoning": true,
        "prompt_caching": false,
        "response_schema": false
      },
      "last_updated_at": "2026-04-24"
    }
  }
}