Mistral Small 3.2 24B Instruct 2506
Efficient Mistral model for fast chat, extraction, and production assistants
Context
131,072
Max output
131,072
Input / 1M
$0.10
Output / 1M
$0.31
Providers
6
01Profile
Profile
Released
2025-10-01
Last updated
2026-03-17
Knowledge cutoff
2025-09
Weights
Open
02Capabilities
Capabilities
Input
text
Output
text
Reasoning
Yes
Tool calling
Yes
Structured output
Yes
Attachments
No
Cache read
—
Cache write
—
03Pricing
Pricing across 5 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
12+ recent events since 2025-10-01
2026-09-14Removednano-gptofferingremoved→ new
2026-09-03Contextnano-gptMax output131,072→ 16,384
2026-08-05Addedcortecsoffering→ new
2026-07-29Addedgreenptoffering→ new
2026-06-04ContextscalewayContext window128,000→ new
2026-04-26Removedchutesofferingremoved→ new
2026-04-19Price upbergetinput / 1M$0.30→ $0.33
2026-04-19Price upbergetoutput / 1M$0.30→ $0.33
2026-03-17ContextscalewayMax output8,192→ 32,768
2026-02-18Price cutmeganovainput / 1M$0.10→ Not listed
2026-02-18Price cutmeganovaoutput / 1M$0.30→ Not listed
2026-02-18ContextmeganovaContext window96,000→ 32,768