Custom Model Integrations

{
  "authentication_type": "api_key",
  "api_key_header": "YOUR_API_KEY_HEADER",
  "api_key_value": "YOUR_API_KEY_VALUE",
  "model_properties": [
    {
      "name": "gpt-5.2",
      "alias": "GPT 5.2",
      "supported_parameters": [
        "max_tokens",
        "n",
        "reasoning_effort",
        "stop_sequences",
        "temperature",
        "tool_choice",
        "tools",
        "verbosity"
      ]
    },
    {
      "name": "gpt-5.4",
      "alias": "GPT 5.4",
      "based_on": "gpt-5.4"
    },
    {
      "name": "claude-opus-4-6",
      "alias": "Opus 4.6",
      "based_on": "Claude Opus 4.6"
    }
  ],
  "endpoint": "https://YOUR_PROVIDER_BASE_URL"
}

{
  "authentication_type": "api_key",
  "api_key_header": "Authorization",
  "api_key_value": "Bearer YOUR_TOKEN",
  "model_properties": [
    {
      "name": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
      "alias": "Llama 4 Scout",
      "supported_parameters": [
        "max_tokens",
        "stop_sequences",
        "temperature",
        "top_p"
      ]
    }
  ],
  "endpoint": "https://api.together.xyz/v1"
}

{
  "authentication_type": "oauth2",
  "oauth2_token_url": "https://auth.provider.com/oauth2/token",
  "token": "{\"client_id\": \"YOUR_CLIENT_ID\", \"client_secret\": \"YOUR_CLIENT_SECRET\"}",
  "authentication_scope": "inference",
  "model_properties": [
    {
      "name": "provider-model-v2",
      "alias": "Provider Model v2",
      "supported_parameters": [
        "max_tokens",
        "temperature",
        "top_p"
      ]
    }
  ],
  "endpoint": "https://api.provider.com/v1"
}

{
  "authentication_type": "none",
  "model_properties": [
    {
      "name": "internal-model-v1",
      "alias": "Internal Model",
      "supported_parameters": [
        "max_tokens",
        "temperature",
        "top_p"
      ]
    }
  ],
  "endpoint": "https://internal-gateway.local/v1"
}

# File: proprietary_handler.py

from litellm import CustomLLM
from litellm.types.utils import ModelResponse
import httpx


class ProprietaryLLMHandler(CustomLLM):
    """Custom handler for proprietary LLM API."""

    def __init__(self, timeout: int = 30, retry_count: int = 1):
        self.timeout = timeout
        self.retry_count = retry_count

    async def acompletion(
        self,
        model: str,
        messages: list,
        api_base: str,
        custom_llm_provider: str,
        **kwargs
    ) -> ModelResponse:
        """Handle async completion requests to the proprietary API."""

        # Transform messages to provider's format
        payload = self._transform_request(messages, **kwargs)

        # Make the async API call
        async with httpx.AsyncClient() as client:
            response = await client.post(
                f"{api_base}/generate",
                json=payload,
                timeout=self.timeout
            )
            response.raise_for_status()

        # Transform response to LiteLLM format
        return self._transform_response(response.json(), model)

    def _transform_request(self, messages: list, **kwargs) -> dict:
        """Transform LiteLLM messages to provider format."""
        return {
            "prompt": messages,
            "temperature": kwargs.get("temperature", 0.7),
            "max_tokens": kwargs.get("max_tokens", 1024)
        }

    def _transform_response(self, data: dict, model: str) -> ModelResponse:
        """Transform provider response to LiteLLM format."""
        return ModelResponse(
            id=data.get("id", "response-id"),
            choices=[{
                "message": {
                    "role": "assistant",
                    "content": data["output"]
                },
                "finish_reason": "stop"
            }],
            model=model,
            usage={
                "prompt_tokens": data.get("input_tokens", 0),
                "completion_tokens": data.get("output_tokens", 0),
                "total_tokens": data.get("total_tokens", 0)
            }
        )

{
  "authentication_type": "none",
  "model_properties": [
    {
      "name": "proprietary-model",
      "alias": "Proprietary Model",
      "based_on": "gpt-5.4"
    }
  ],
  "endpoint": "https://ai.example.com/inference",
  "custom_llm_config": {
    "file_name": "proprietary_handler.py",
    "class_name": "ProprietaryLLMHandler",
    "init_kwargs": {
      "timeout": 60,
      "retry_count": 3
    }
  }
}