BerriAI/litellm · error · ValueError

container operations are not supported for {custom_llm_provi

Error message

container operations are not supported for {custom_llm_provider}

What it means

Thrown by litellm/containers/main.py container creation when ProviderConfigManager.get_provider_container_config returns None for the given custom_llm_provider. LiteLLM's container API (code-execution sandboxes for the Responses API) is implemented only for OpenAI and Azure; requesting any other provider is rejected before any HTTP call is made.

Source

Thrown at litellm/containers/main.py:217

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

        # get llm provider logic
        # Pass credential params explicitly since they're named args, not in kwargs
        litellm_params: Final = GenericLiteLLMParams(
            api_key=api_key,
            api_base=api_base,
            api_version=api_version,
            **kwargs,
        )
        # get provider config
        container_provider_config: BaseContainerConfig | None = ProviderConfigManager.get_provider_container_config(
            provider=litellm.LlmProviders(custom_llm_provider),
        )

        if container_provider_config is None:
            raise ValueError(f"container operations are not supported for {custom_llm_provider}")

        local_vars.update(kwargs)
        # Get ContainerCreateOptionalRequestParams with only valid parameters
        container_create_optional_params: Final[ContainerCreateOptionalRequestParams] = (
            ContainerRequestUtils.get_requested_container_create_optional_param(local_vars)
        )

        # Get optional parameters for the container API
        container_create_request_params: Final[dict] = ContainerRequestUtils.get_optional_params_container_create(
            container_provider_config=container_provider_config,
            container_create_optional_params=container_create_optional_params,
        )

        # Pre Call logging
        litellm_logging_obj.update_from_kwargs(
            kwargs=kwargs,
            model="",
            optional_params=dict(container_create_request_params),

View on GitHub (pinned to 6c2dcb801b)

Solutions

1. Use custom_llm_provider='openai' or 'azure' — the only providers with a registered BaseContainerConfig.
2. For Azure, also supply api_base (your resource endpoint) and api_version so the Azure container config can build the URL.
3. Verify the provider string exactly matches a litellm.LlmProviders value; log litellm.LlmProviders(custom_llm_provider) to confirm it parses.
4. Request or implement a provider config by subclassing BaseContainerConfig and adding it to get_provider_container_config.

Example fix

# before
await litellm.acreate_container(
    custom_llm_provider="vertex_ai",
)

# after
await litellm.acreate_container(
    custom_llm_provider="openai",
    expires_after=60 * 10,
)

import litellm
from litellm.litellm_core_utils.core_helpers import ProviderConfigManager

assert ProviderConfigManager.get_provider_container_config(
    litellm.LlmProviders(custom_llm_provider)
) is not None, f"{custom_llm_provider} does not support containers; use 'openai' or 'azure'"

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

try:
    container = await litellm.acreate_container(custom_llm_provider=provider)
except ValueError as e:
    if "not supported" in str(e):
        raise UnsupportedContainerProvider(provider) from e
    raise

When it happens

Trigger: Calling acreate_container (or the synchronous wrapper) with custom_llm_provider='vertex_ai', 'anthropic', 'bedrock', 'gemini', or any value outside {'openai','azure','azure_text'} — including misspelled strings that still parse as an LlmProviders member.

Common situations: Porting OpenAI container examples to another cloud; using a router deployment whose model string maps to a provider without container support; upgrading LiteLLM versions where container support coverage changed.

Related errors

• Container provider config not found for: {resolved_custom_ll
• 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/87c5ad84826f19b2. Report an issue: GitHub.