microsoft/autogen · error · ValueError

Model does not support vision and image was provided

Error message

Model does not support vision and image was provided

What it means

Raised by AzureAIChatCompletionClient._validate_model_info during create()/create_stream() when self.model_info['vision'] is False and any UserMessage in the conversation has a list content containing at least one autogen Image. The client refuses to forward images to a model declared non-vision rather than let the service fail opaquely.

Source

Thrown at python/packages/autogen-ext/src/autogen_ext/models/azure/_azure_ai_client.py:341

    def add_usage(self, usage: RequestUsage) -> None:
        self._total_usage = RequestUsage(
            self._total_usage.prompt_tokens + usage.prompt_tokens,
            self._total_usage.completion_tokens + usage.completion_tokens,
        )

    def _validate_model_info(
        self,
        messages: Sequence[LLMMessage],
        tools: Sequence[Tool | ToolSchema],
        json_output: Optional[bool | type[BaseModel]],
        create_args: Dict[str, Any],
    ) -> None:
        if self.model_info["vision"] is False:
            for message in messages:
                if isinstance(message, UserMessage):
                    if isinstance(message.content, list) and any(isinstance(x, Image) for x in message.content):
                        raise ValueError("Model does not support vision and image was provided")

        if json_output is not None:
            if self.model_info["json_output"] is False and json_output is True:
                raise ValueError("Model does not support JSON output")

            if isinstance(json_output, type):
                # TODO: we should support this in the future.
                raise ValueError("Structured output is not currently supported for AzureAIChatCompletionClient")

            if json_output is True and "response_format" not in create_args:
                create_args["response_format"] = "json_object"

        if self.model_info["json_output"] is False and json_output is True:
            raise ValueError("Model does not support JSON output")
        if self.model_info["function_calling"] is False and len(tools) > 0:
            raise ValueError("Model does not support function calling")

    async def create(

View on GitHub (pinned to 027ecf0a37)

Solutions

1. If the deployed model does support vision, fix model_info to vision=True
2. If it truly does not, strip Image parts from UserMessage content before calling create (or replace with a text placeholder)
3. Gate image-attaching code paths on client.model_info['vision']

Example fix

# before
model_info = ModelInfo(family="llama-3-1-8b-instruct", vision=False, ...)
await client.create([UserMessage(content=["what is this?", img], source="user")])

# after
content = ["what is this?", img] if client.model_info["vision"] else ["what is this? (image omitted)"]
await client.create([UserMessage(content=content, source="user")])

from autogen_core.models import UserMessage, Image

def has_images(messages) -> bool:
    return any(
        isinstance(m, UserMessage) and isinstance(m.content, list)
        and any(isinstance(p, Image) for p in m.content)
        for m in messages
    )

if client.model_info["vision"] is False:
    assert not has_images(msgs), "cannot send images to a non-vision model"

from autogen_core.models import UserMessage, Image

def message_contains_image(msg) -> bool:
    return isinstance(msg, UserMessage) and isinstance(msg.content, list) \
        and any(isinstance(p, Image) for p in msg.content)

When it happens

Trigger: Sending Image parts in a UserMessage to a model whose model_info was built with vision=False (e.g. a text-only Llama or GPT model deployed on Azure AI Foundry); reusing a vision conversation history after swapping to a text-only deployment.

Common situations: model_info copied from a text model while the deployment actually serves a vision model (mis-declared capabilities); pipeline branches that attach screenshots unconditionally.

Related errors

• Model does not support vision and image was provided
• Unknown content type: {message.content}
• model_info is required for AzureAIChatCompletionClient
• Model does not support JSON output
• Model does not support function calling

AI-assisted analysis of microsoft/autogen@027ecf0a37 (2026-08-15). Data as JSON: /api/errors/025c96726c5c3b2d. Report an issue: GitHub.