BerriAI/litellm · error · ValueError

api_base is required in generic_prompt_config

Error message

api_base is required in generic_prompt_config

What it means

Raised by prompt_initializer() in the generic prompt management integration when litellm_params.api_base is falsy. The generic prompt manager must call a LiteLLM-compatible prompt management API, and api_base is the URL of that API; without it there is nothing to fetch the prompt from.

Source

Thrown at litellm/integrations/generic_prompt_management/__init__.py:43

                - api_base: Base URL for the API
                - api_key: Optional API key for authentication
                - timeout: Request timeout in seconds (default: 30)
    """
    import litellm

    litellm.global_generic_prompt_config = config


def prompt_initializer(litellm_params: "PromptLiteLLMParams", prompt_spec: "PromptSpec") -> "CustomPromptManagement":
    """
    Initialize a prompt from a generic prompt management API.
    """
    prompt_id: Final = getattr(litellm_params, "prompt_id", None)

    api_base: Final = litellm_params.api_base
    api_key: Final = litellm_params.api_key
    if not api_base:
        raise ValueError("api_base is required in generic_prompt_config")

    provider_specific_query_params: Final = litellm_params.provider_specific_query_params

    try:
        generic_prompt_manager: Final = GenericPromptManager(
            api_base=api_base,
            api_key=api_key,
            prompt_id=prompt_id,
            additional_provider_specific_query_params=provider_specific_query_params,
            **litellm_params.model_dump(
                exclude_none=True,
                exclude={
                    "prompt_id",
                    "api_key",
                    "provider_specific_query_params",
                    "api_base",
                },
            ),

View on GitHub (pinned to 6c2dcb801b)

Solutions

1. Add api_base (the root URL of your prompt management API, e.g. https://api.litellm.ai or a self-hosted proxy) to the litellm_params of the model that uses the generic prompt integration.
2. If set via litellm.global_generic_prompt_config, verify that dict includes 'api_base' alongside api_key.
3. Check for typos: the attribute read is exactly litellm_params.api_base — 'base_url', 'api_url', or 'url' are silently ignored and leave api_base falsy.

Example fix

# before (config.yaml model_list entry)
model_name: my-prompt
litellm_params:
  model: openai/gpt-4o
  prompt_integration: generic_api
  prompt_id: my-prompt-id
  # api_base missing -> ValueError

# after
model_name: my-prompt
litellm_params:
  model: openai/gpt-4o
  prompt_integration: generic_api
  prompt_id: my-prompt-id
  api_base: https://your-litellm-proxy.example.com

def validate_generic_prompt_params(litellm_params) -> None:
    if not getattr(litellm_params, "api_base", None):
        raise ValueError(
            "Prompt integration 'generic_api' requires litellm_params.api_base "
            "(root URL of the prompt management API)"
        )

validate_generic_prompt_params(model.litellm_params)

def has_api_base(litellm_params) -> bool:
    return bool(getattr(litellm_params, "api_base", None))

When it happens

Trigger: Calling litellm.router.completion with a model whose model_info declares prompt_integration='generic_api' (or setting litellm.global_generic_prompt_config) but omitting api_base in the model's litellm_params; passing api_base=None or an empty string; typo like 'apiUrl' or 'base_url' instead of 'api_base'.

Common situations: Defining a prompt-management model in the config.yaml of the proxy without an api_base entry; assuming the prompt manager reads a base URL from an environment variable (it does not); renaming the key when migrating config from the LiteLLM proxy UI where the field is labeled differently.

Related errors

• gitlab_config is required for gitlab prompt integration
• prompt_id is required for Arize Phoenix prompt manager
• Event hook {hook} is not in the supported event hooks {suppo
• Event hook {event_hook} is not in the supported event hooks
• Invalid environment: {environment}. Please use one of the fo

AI-assisted analysis of BerriAI/litellm@6c2dcb801b (2026-08-15). Data as JSON: /api/errors/80126977ac105c3c. Report an issue: GitHub.