{
  "schema_version": 1,
  "default_endpoint": "local-litellm",
  "endpoints": [
    {
      "name": "local-litellm",
      "base_url": "http://localhost:4000",
      "tool_calling": true,
      "thinking": {
        "on_body": { "reasoning_effort": "medium" },
        "off_body": { "reasoning_effort": "none" },
        "parse_think_tags": true
      }
    },
    {
      "name": "openai",
      "base_url": "https://api.openai.com",
      "api_key_env": "OPENAI_API_KEY",
      "max_tokens_field": "max_completion_tokens",
      "context_window": 128000,
      "max_output_tokens": 16000,
      "honors_sampling": true
    },
    {
      "name": "vllm-local",
      "base_url": "http://localhost:8000",
      "api_key": "sk-local-only-not-a-real-secret",
      "context_window": 32768,
      "model_overrides": [
        { "model_pattern": "qwen2.5-vl*", "vision": true, "tool_calling": true, "params_b": 7 },
        { "model_pattern": "my-custom-*", "vendor": "acme", "family": "llama", "params_b": 70 }
      ]
    }
  ]
}