BerriAI/litellm · error · ValueError

LEMONADE_API_BASE is not set. Please set the environment var

Error message

LEMONADE_API_BASE is not set. Please set the environment variable to query Lemonade's /models endpoint.

What it means

The Lemonade provider (AMD's LLM inference server) has no usable api_base default by the time get_models runs its check, so listing models raises ValueError. Resolution order is the api_base argument, then provider env vars, then LEMONADE_API_BASE; if all are None the /models query cannot proceed.

Source

Thrown at litellm/llms/lemonade/chat/transformation.py:84

        return super().get_config()

    def get_models(self, api_key: str | None = None, api_base: str | None = None):
        """
        Get available models from Lemonade API.

        This method queries the Lemonade /models endpoint to retrieve the list of available models.

        Args:
            api_key: Optional API key for authenticated Lemonade servers
            api_base: Optional API base URL (defaults to LEMONADE_API_BASE env var or http://localhost:8000)

        Returns:
            List of model names prefixed with "lemonade/"
        """
        api_base, api_key = self._get_openai_compatible_provider_info(api_base=api_base, api_key=api_key)

        if api_base is None:
            raise ValueError(
                "LEMONADE_API_BASE is not set. Please set the environment variable to query Lemonade's /models endpoint."
            )

        # Getting the list of models from lemonade
        try:
            response: Final = litellm.module_level_client.get(
                url=f"{api_base}/models",
                headers=self._get_auth_headers(api_key),
            )
        except Exception as e:
            raise ValueError(
                f"Failed to fetch models from Lemonade. Set Lemonade API Base via `LEMONADE_API_BASE` environment variable. Error: {e}"
            )

        if response.status_code != 200:
            raise ValueError(
                f"Failed to fetch models from Lemonade. Status code: {response.status_code}, Response: {response.text}"
            )

View on GitHub (pinned to 6c2dcb801b)

Solutions

export LEMONADE_API_BASE="http://localhost:8000" (or your Lemonade server URL) and restart the process
Or pass api_base explicitly when calling get_models / configuring the model entry
Confirm the Lemonade server is running: curl http://localhost:8000/models

Example fix

# before
models = provider.get_models()  # ValueError

# after
import os
os.environ["LEMONADE_API_BASE"] = "http://localhost:8000"
models = provider.get_models()

Defensive patterns

Strategy: validation

Validate before calling

import os

def ensure_lemonade_base() -> str:
    base = os.getenv("LEMONADE_API_BASE")
    if not base:
        raise ValueError("LEMONADE_API_BASE must be set before listing Lemonade models")
    return base

Try / catch

try:
    models = provider.get_models()
except ValueError as e:
    if "LEMONADE_API_BASE is not set" in str(e):
        os.environ["LEMONADE_API_BASE"] = "http://localhost:8000"
        models = provider.get_models()

Prevention

Set LEMONADE_API_BASE explicitly even if you expect the localhost default — the fallback chain can yield None
Add the variable to your service manifest / .env loaded at process start
Health-check {base}/models on boot before populating model lists

When it happens

Trigger: Calling the models-list path (e.g. proxy model population or provider get_models) without api_base and without LEMONADE_API_BASE in the environment.

Common situations: Fresh setup expecting the documented http://localhost:8000 default but the env var fallback chain resolves to None; Lemonade server not started yet; env var set in a different session/container.

Related errors

AI-assisted analysis of BerriAI/litellm@6c2dcb801b (2026-08-15). Data as JSON: /api/errors/db4029d957974b11. Report an issue: GitHub.