MistralMistral MediumMar 17, 2025

Magistral Small 2509

Complex thinking, backed by deep understanding, with transparent reasoning you can follow and verify. The model excels in maintaining high-fidelity reasoning across numerous languages, even when switching between languages mid-task.

Context Window
128K
tokens
Max Output
64K
tokens
Released
Mar 17, 2025
Arena Rank

Capabilities

👁Vision
🧠Reasoning
🔧Tool Calling
Prompt Caching
🖥Computer Use
🎨Image Generation

Pricing Comparison

RouterInput / 1MOutput / 1MCached Input / 1M
Vercel AI$0.50$1.50

Model IDs

Tags

reasoningvision
Compare with another model

Related Models