BerriAI/litellm · error · ValueError

OpenAI client is not an instance of OpenAI. Make sure you pa

Error message

OpenAI client is not an instance of OpenAI. Make sure you passed a sync OpenAI client.

What it means

ValueError raised when a synchronous (non-_is_async) OpenAI operation is handed a client that is not a sync OpenAI instance — usually an AsyncOpenAI client was passed to a sync method such as cancel_batch. The sync path cannot use an async client, so it rejects it up front.

Source

Thrown at litellm/llms/openai/openai.py:2111

            organization=organization,
            client=client,
            _is_async=_is_async,
        )
        if openai_client is None:
            raise ValueError(
                "OpenAI client is not initialized. Make sure api_key is passed or OPENAI_API_KEY is set in the environment."
            )

        if _is_async is True:
            if not isinstance(openai_client, AsyncOpenAI):
                raise ValueError(
                    "OpenAI client is not an instance of AsyncOpenAI. Make sure you passed an AsyncOpenAI client."
                )
            return self.acancel_batch(cancel_batch_data=cancel_batch_data, openai_client=openai_client)

        # At this point, openai_client is guaranteed to be a sync OpenAI client
        if not isinstance(openai_client, OpenAI):
            raise ValueError("OpenAI client is not an instance of OpenAI. Make sure you passed a sync OpenAI client.")
        response: Final = openai_client.batches.cancel(**cancel_batch_data)
        return LiteLLMBatch.model_validate(response.model_dump())

    async def alist_batches(
        self,
        openai_client: AsyncOpenAI,
        after: str | None = None,
        limit: int | None = None,
    ):
        verbose_logger.debug("listing batches, after= %s, limit= %s", after, limit)
        response: Final = await openai_client.batches.list(after=after, limit=limit)
        return response

    def list_batches(
        self,
        _is_async: bool,
        api_key: str | None,
        api_base: str | None,

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Pass a sync OpenAI client instance for synchronous calls.

When it happens

Trigger: Thrown at litellm/llms/openai/openai.py:2111 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/2b1d855fec9c572c. Report an issue: GitHub.