Mistral Small
Efficient model for fast inference
Pricing
Input
$0.10/M
per million tokens
Output
$0.30/M
per million tokens
About Mistral Small
Mistral Small offers excellent performance for cost-sensitive applications. Fast inference with strong capabilities for common tasks.
Modalities
Input
Text
Output
Text
Capabilities
× Vision
✓ Tool Use
✓ Function Calling
✓ Streaming
✓ JSON Mode
Specifications
- Context Window
- 32K
- Max Output
- 8K
- Model Type
- chat
- Model ID
- mistral/mistral-small
- Source
- manual
Provider
Mistral AI
4 models
European AI lab creating efficient models
Visit website →Explore More Models
Browse our database of AI models from all major providers
Browse All Models