It is vision only (not multimodal)
https://github.com/mistralai/mistral-common/releases/tag/v1.... https://github.com/mistralai/mistral-common/pull/45
https://github.com/mistralai/mistral-common/releases/tag/v1.... https://github.com/mistralai/mistral-common/pull/45
Pixtral is out! Mistral common has image support! You can now pass images and URLs alongside text into the user message.
So, it's multimodal then.