BerriAI/litellm · error · ConfigGenerationError

classifier model '{config.classifier.model}' is not a known

Error message

classifier model '{config.classifier.model}' is not a known chat model

What it means

Raised by validate_config when a classifier config that uses an LLM (LLMClassifier-style) names a model that is not in the discovered chat-model set. The complexity classifier cannot call a model the proxy does not expose, so validation fails with ConfigGenerationError; heuristic classifiers are unaffected because they use no model.

Source

Thrown at litellm/proxy/client/cli/commands/autoroute/config.py:122

    semantic_matching: SemanticMatchingChoice = Field(default_factory=NoSemanticMatching)
    adaptive: bool = False


def validate_config(config: AutorouteConfig, discovered: tuple[DiscoveredModel, ...]) -> None:
    """Raise ConfigGenerationError if config references a model discovery didn't return."""
    chat_names: Final[frozenset[str]] = frozenset(m.name for m in chat_models(discovered))
    embedding_names: Final[frozenset[str]] = frozenset(m.name for m in embedding_models(discovered))

    for tier, models in config.tiers.items():
        for model in models:
            if model not in chat_names:
                raise ConfigGenerationError(f"Tier {tier} references unknown chat model '{model}'")

    if config.default_model not in chat_names:
        raise ConfigGenerationError(f"default_model '{config.default_model}' is not a known chat model")

    if isinstance(config.classifier, LLMClassifier) and config.classifier.model not in chat_names:
        raise ConfigGenerationError(f"classifier model '{config.classifier.model}' is not a known chat model")

    if (
        isinstance(config.semantic_matching, SemanticMatching)
        and config.semantic_matching.embedding_model not in embedding_names
    ):
        raise ConfigGenerationError(
            f"embedding model '{config.semantic_matching.embedding_model}' is not a known embedding model"
        )


def _litellm_proxy_deployment(name: str, base_url: str, api_key: str) -> dict[str, JsonValue]:
    return {
        "model_name": name,
        "litellm_params": {
            "model": f"litellm_proxy/{name}",
            "api_base": base_url,
            "api_key": api_key,
        },

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Set classifier.model to a known chat model.

Example fix

classifier:
  model: gpt-4o-mini

When it happens

Trigger: Thrown at litellm/proxy/client/cli/commands/autoroute/config.py:122 when the library encounters an invalid state.

Common situations: The autoroute classifier model is not a recognized chat model.

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/45bb9b974d924c2b. Report an issue: GitHub.