Mistral AIactive
Mistral Medium 3
Frontier-class multimodal model optimized for enterprise-grade performance, high-speed reasoning, and long-context document understanding.
Billing unit: Per 1M tokens
Input / 1M tokens
$0.400
Output / 1M tokens
$2.00
Context window
128K
Capabilities
- Streaming
- Function Calling
- JSON Mode
- Vision
- Multilingual
- Single-node Inference