BerriAI/litellm · error · ValueError

video generation is not supported for {custom_llm_provider}

Error message

video generation is not supported for {custom_llm_provider}

What it means

Provider-support check in video generation: get_provider_video_config returned None for the resolved provider/model, meaning that provider has no video-generation transformation implemented, so the create call cannot proceed.

Source

Thrown at litellm/videos/main.py:213

            response: Final = VideoObject(**mock_response)
            return response

        # get llm provider logic
        litellm_params: Final = GenericLiteLLMParams(**kwargs)
        model, custom_llm_provider, _, _ = get_llm_provider(
            model=model or DEFAULT_VIDEO_ENDPOINT_MODEL,
            custom_llm_provider=custom_llm_provider,
        )

        # get provider config
        video_generation_provider_config: BaseVideoConfig | None = ProviderConfigManager.get_provider_video_config(
            model=model,
            provider=litellm.LlmProviders(custom_llm_provider),
        )

        if video_generation_provider_config is None:
            raise ValueError(f"video generation is not supported for {custom_llm_provider}")

        local_vars.update(kwargs)
        # Get VideoGenerationOptionalRequestParams with only valid parameters
        video_generation_optional_params: Final[VideoCreateOptionalRequestParams] = (
            VideoGenerationRequestUtils.get_requested_video_generation_optional_param(local_vars)
        )

        # Get optional parameters for the video generation API
        video_generation_request_params: Final[dict] = VideoGenerationRequestUtils.get_optional_params_video_generation(
            model=model,
            video_generation_provider_config=video_generation_provider_config,
            video_generation_optional_params=video_generation_optional_params,
        )

        # Pre Call logging
        litellm_logging_obj.update_from_kwargs(
            kwargs=kwargs,
            model=model,

View on GitHub (pinned to 77b7c6c40c)

Solutions

  1. Use a provider that supports video generation (e.g. openai/sora, gemini/veo) instead of {custom_llm_provider}.
  2. Implement video generation in a custom provider wrapper.
Defensive patterns

Strategy: validation

When it happens

Trigger: Thrown at litellm/videos/main.py:213 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/8cf2a8013c03ed86. Report an issue: GitHub.