Pixtral Large

Pixtral Large is a frontier-class multimodal model with vision-capable reasoning capabilities, making it well-suited for a wide range of complex tasks and sophisticated applications.

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.