Mistral Small 4
Fast Mistral production model for chat, extraction, and cost-sensitive agents
Context
262,144
Max output
256,000
Input / 1M
$0.15
Output / 1M
$0.60
Providers
4
01Profile
Profile
Released
2026-03-16
Last updated
2026-08-01
Knowledge cutoff
2025-06
Weights
Open
02Capabilities
Capabilities
Input
text · image
Output
text
Reasoning
Yes
Tool calling
Yes
Structured output
No
Attachments
Yes
Cache read
—
Cache write
—
03Pricing
Pricing across 4 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
8+ recent events since 2026-03-16
2026-08-19ContextpioneerContext window262,144→ 32,000
2026-08-19ContextpioneerMax output65,536→ 32,000
2026-08-04Addedinfomaniakoffering→ new
2026-06-30ContextpioneerMax output262,144→ 65,536
2026-06-08Addedpioneeroffering→ new
2026-06-03Addednano-gptoffering→ new
2026-06-03Addednano-gptoffering→ new
2026-05-03Addednvidiaoffering→ new