Pixtral 12B

Pixtral 12B is a powerful AI model from Mistral AI that combines advanced text understanding with image comprehension capabilities. This versatile model can handle a wide range of inputs and outputs, including text, images, video, audio, transcription, and text-to-speech.

Supports a 131K token context window. Handles 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 Apache2 license and can be accessed through Mistral AI's API. To learn more, check out the blog post.