BerriAI/litellm · error · ValueError

api_base is required. Unable to determine the correct api_ba

Error message

api_base is required. Unable to determine the correct api_base for the request.

What it means

Raised in get_complete_url of the experimental Anthropic pass-through config: no api_base was resolved from params, litellm_params, or environment, so the Vertex/Anthropic endpoint URL cannot be constructed.

Source

Thrown at litellm/llms/vertex_ai/vertex_ai_partner_models/anthropic/experimental_pass_through/transformation.py:126

        if anthropic_model_info.is_tool_search_used(tools):
            beta_values.add(get_tool_search_beta_header("vertex_ai"))

        if beta_values:
            headers["anthropic-beta"] = ",".join(beta_values)

        return headers, api_base

    def get_complete_url(
        self,
        api_base: str | None,
        api_key: str | None,
        model: str,
        optional_params: dict,
        litellm_params: dict,
        stream: bool | None = None,
    ) -> str:
        if api_base is None:
            raise ValueError("api_base is required. Unable to determine the correct api_base for the request.")
        return api_base  # no transformation is needed - handled in validate_environment

    def transform_anthropic_messages_request(
        self,
        model: str,
        messages: list[dict],
        anthropic_messages_optional_request_params: dict,
        litellm_params: GenericLiteLLMParams,
        headers: dict,
    ) -> dict:
        anthropic_messages_request: Final = super().transform_anthropic_messages_request(
            model=model,
            messages=messages,
            anthropic_messages_optional_request_params=anthropic_messages_optional_request_params,
            litellm_params=litellm_params,
            headers=headers,
        )

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Pass api_base explicitly for the Anthropic pass-through request.
2. Or set vertex_project and vertex_location so litellm can construct the Vertex regional endpoint automatically.

When it happens

Trigger: Thrown at litellm/llms/vertex_ai/vertex_ai_partner_models/anthropic/experimental_pass_through/transformation.py:126 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/d7ef8efb576add58. Report an issue: GitHub.