BerriAI/litellm · error · ValueError

Container provider config not found for: {resolved_custom_ll

Error message

Container provider config not found for: {resolved_custom_llm_provider}

What it means

Raised by the container-endpoint factory when LiteLLM cannot find a container (code-execution sandbox) provider config for the resolved provider. ProviderConfigManager.get_provider_container_config only knows OpenAI and Azure; every other LlmProviders value returns None and this ValueError fires. The provider may come from your custom_llm_provider argument or from decoding a LiteLLM-managed container ID.

Source

Thrown at litellm/containers/endpoint_factory.py:99

            litellm_params = GenericLiteLLMParams(**kwargs)
            # Strip LiteLLM-managed container IDs before calling the provider API
            # (OpenAI enforces max length 64 on container_id).
            if "container_id" in kwargs and isinstance(kwargs["container_id"], str):
                (
                    kwargs["container_id"],
                    resolved_custom_llm_provider,
                    litellm_params,
                ) = decode_managed_container_id_for_request(
                    container_id=kwargs["container_id"],
                    custom_llm_provider=resolved_custom_llm_provider,
                    litellm_params=litellm_params,
                )
            container_provider_config: BaseContainerConfig | None = ProviderConfigManager.get_provider_container_config(
                provider=litellm.LlmProviders(resolved_custom_llm_provider),
            )

            if container_provider_config is None:
                raise ValueError(f"Container provider config not found for: {resolved_custom_llm_provider}")

            # Build optional params for logging
            optional_params: Final = {k: kwargs.get(k) for k in path_params if k in kwargs}

            # Pre-call logging
            litellm_logging_obj.update_from_kwargs(
                kwargs=kwargs,
                model="",
                optional_params=optional_params,
                litellm_params={"litellm_call_id": litellm_call_id},
                custom_llm_provider=resolved_custom_llm_provider,
            )

            # Use generic handler
            return generic_container_handler.handle(
                endpoint_name=endpoint_name,
                container_provider_config=container_provider_config,
                litellm_params=litellm_params,

View on GitHub (pinned to 6c2dcb801b)

Solutions

1. Set custom_llm_provider='openai' (or 'azure' with api_base/api_version pointing at your Azure OpenAI resource) for container operations.
2. If you passed a LiteLLM-managed container_id, verify it was issued for an OpenAI/Azure container and was not re-encoded with a different provider.
3. Check the provider string for typos against litellm.LlmProviders members; only OPENAI, AZURE and AZURE_TEXT have container configs.
4. If you need containers on another provider, contribute a BaseContainerConfig subclass and register it in ProviderConfigManager.get_provider_container_config (litellm/utils.py).

Example fix

# before
litellm.acontainer_create_container(
    custom_llm_provider="anthropic",  # ValueError: no container config
)

# after
litellm.acontainer_create_container(
    custom_llm_provider="openai",
    api_key=os.environ["OPENAI_API_KEY"],
)

from litellm import LlmProviders
from litellm.litellm_core_utils.core_helpers import ProviderConfigManager

SUPPORTED = {LlmProviders.OPENAI, LlmProviders.AZURE, LlmProviders.AZURE_TEXT}

def containers_supported(provider: str) -> bool:
    try:
        return ProviderConfigManager.get_provider_container_config(
            LlmProviders(provider)
        ) is not None
    except Exception:
        return False

if not containers_supported(resolved_provider):
    raise SkipContainerOp(f"no container support for {resolved_provider}")

def is_container_provider(provider: str) -> bool:
    """True when LiteLLM has a container config for this provider."""
    try:
        return ProviderConfigManager.get_provider_container_config(
            litellm.LlmProviders(provider)
        ) is not None
    except Exception:
        return False

try:
    await litellm.acreate_get_container(container_id=cid, custom_llm_provider=provider)
except ValueError as e:
    if "Container provider config not found" in str(e):
        logger.warning("container op skipped, unsupported provider %s", provider)
    else:
        raise

When it happens

Trigger: Calling a container API (create/get/list/delete/files of a code-execution container) with custom_llm_provider set to anything except 'openai' or 'azure' (e.g. 'anthropic', 'bedrock'), or passing a LiteLLM-encoded container_id whose embedded custom_llm_provider decodes to an unsupported provider.

Common situations: Assuming the Responses-API container feature works for all providers because the API shape is generic; routing a container_id that was created on one gateway through a deployment labeled with another provider; typos in the provider string ('open_ai', 'azure-openai').

Related errors

• container operations are not supported for {custom_llm_provi
• Container provider config not found for provider: {custom_ll
• Container provider config not found for provider: {resolved_
• Failed to transform Braintrust response: {str(e)}
• soft_budget cannot be negative. Received: {data.soft_budget}

AI-assisted analysis of BerriAI/litellm@6c2dcb801b (2026-08-15). Data as JSON: /api/errors/750be2e59d76417d. Report an issue: GitHub.