Back to all models

Mistral Small 3.2

Lightweight 24B model for fast, efficient tasks.

mistral-small-2506
STABLEGet Started
128,000 context
Starting at $0.10/M input tokens
Starting at $0.30/M output tokens
Streaming
Vision
JSON Output

Select Provider

All Providers for Mistral Small 3.2

LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.

Mistral AI
Context: 128k
Input
$0.1
/M tokens
Cached
—
/M tokens
Output
$0.3
/M tokens
Get Started