Pixtral 12B

Pixtral 12B is a frontier-class multimodal model from Mistral Research, capable of understanding and generating text, images, video, audio, and more. With a 131K token context window, it excels at a wide range of tasks including text generation, image captioning, video understanding, and audio transcription.

Supports Text, Image, Video, Audio, Transcription, Text-to-Speech inputs and outputs. Supports fine-tuning for custom applications. Supports tool use for advanced automation. Capable of generating structured output formats.

Pixtral 12B is available under the Mistral Research License and can be accessed via the Mistral API. Learn more in the Pixtral 12B blog post.