LiteLLM cost map — 4 entries only (auto/pro/sonic/zero, 1M ctx). Needs MODEL_COST_MAP_MAX_SHRINK_RATIO=0 + MODEL_COST_MAP_MIN_MODEL_COUNT=4

models.json

{
    "auto": {
        "cache_creation_input_token_cost": 0,
        "cache_read_input_token_cost": 2.6e-07,
        "input_cost_per_token": 1.4e-06,
        "output_cost_per_token": 4.4e-06,
        "litellm_provider": "openai",
        "max_input_tokens": 1048576,
        "max_output_tokens": 128000,
        "mode": "chat",
        "supports_function_calling": true,
        "supports_prompt_caching": true,
        "supports_reasoning": true,
        "supports_tool_choice": true,
        "supports_vision": true
    },
    "pro": {
        "input_cost_per_token": 7.5e-07,
        "output_cost_per_token": 3.75e-06,
        "litellm_provider": "openai",
        "max_input_tokens": 1048576,
        "max_output_tokens": 65536,
        "max_tokens": 65536,
        "mode": "chat",
        "supports_function_calling": true,
        "supports_tool_choice": true,
        "supports_reasoning": true,
        "supports_response_schema": true,
        "supports_vision": true,
        "supports_pdf_input": true,
        "supports_audio_input": true,
        "cache_read_input_token_cost": 7.5e-08,
        "supports_prompt_caching": true
    },
    "sonic": {
        "cache_creation_input_token_cost": 0,
        "cache_read_input_token_cost": 3e-08,
        "input_cost_per_token": 1.5e-07,
        "output_cost_per_token": 5e-07,
        "litellm_provider": "openai",
        "max_input_tokens": 1048576,
        "max_output_tokens": 128000,
        "mode": "chat",
        "supports_function_calling": true,
        "supports_prompt_caching": true,
        "supports_reasoning": true,
        "supports_tool_choice": true,
        "supports_vision": true
    },
    "zero": {
        "cache_read_input_token_cost": 2.5e-07,
        "input_cost_per_token": 2e-06,
        "litellm_provider": "openai",
        "max_input_tokens": 991808,
        "max_output_tokens": 131072,
        "max_tokens": 131072,
        "mode": "chat",
        "output_cost_per_token": 6e-06,
        "supports_function_calling": true,
        "supports_prompt_caching": true,
        "supports_reasoning": true,
        "supports_response_schema": true,
        "supports_tool_choice": true,
        "supports_vision": true
    },
    "luna": {
        "input_cost_per_token": 2e-07,
        "output_cost_per_token": 1.2e-06,
        "litellm_provider": "openai",
        "max_input_tokens": 922000,
        "max_output_tokens": 128000,
        "max_tokens": 128000,
        "mode": "chat",
        "supports_function_calling": true,
        "supports_tool_choice": true,
        "supports_reasoning": true,
        "supports_response_schema": true,
        "supports_vision": true,
        "supports_pdf_input": true,
        "supports_audio_input": false,
        "cache_read_input_token_cost": 2e-08,
        "supports_prompt_caching": true
    }
}