Hi,
I know that Grok 4 now support multimodal input (text and image), I’m wondering if we can get image input for ChatGroq? I noticed in the Langchain documentation that image input is still not supported yet.
Model details: Welcome to the xAI documentation
Grok (xAI model family) ≠ Groq (Groq Cloud provider). LangChain’s “ChatGroq” targets Groq, not xAI. Grok 4’s multimodal support doesn’t imply ChatGroq supports images.
I think you meant ChatXAI from langchain-xai, right?
Ah yes indeed. Thank you for that clarification. I am referring to the xAI model family.
Grok and Groq - It is unfortunately quite common that those terms are confused 
I used to mix up these very similar terms as well
Haha yes. Anyways, I was referring to ChatXAI not supporting image input, and I’m wondering if that will be supported.
That is a good question. Isn’t it supported now? I haven’t checked that yet.
I tested this morning and can confirm image input works. I realized XAI is doing the standard image input format, so the image message works nicely with langchain-XAI