Mistral Small

A leader in the small models category with image understanding capabilities, Mistral Small is designed for a wide range of tasks with a good balance of performance and efficiency.

Supports a 32768 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.

For API pricing details, please visit our pricing page.

Fine-tuning Customize models for your specific use cases with complete control over the training process. La Plateforme's fine-tuning capabilities enable teams to adapt models to their domain-specific needs while maintaining performance and reliability.

Learn more