All times Eastern (ET)Provider pages checked daily at
ProSign inRSS

Mistral Small 3.2

API ID mistral-small-2506

Mistral Small 3.2 was a Mistral model, released June 2025. It had a 128,000-token context window. It took image and PDF input and supported function calling and structured outputs.

An update to our previous small model, released June 2025.

Mistral's description
Status
Retired
Released
June 2025
Shutdown
Jul 31, 2026

mistral-small-2506 stopped serving on July 31, 2026. Recommended replacement: mistral-small-2603.

How to migrate to Mistral Small 4

Benchmarks

Scores as each source published them
or

Comparing with Mistral Small 3.1, the previous model in this line. A score is compared only with the same benchmark from the same source, at the same setting where both have it. Full comparison: prices, limits, features

Arena

ArenaMistral Small 3.2Mistral Small 3.1ChangeRankDateSource
Text
By category
  • Math 1338 rank 223 vs 1277 (+61)
  • Creative writing 1323 rank 207 vs 1270 (+53)
  • Instruction following 1336 rank 220 vs 1293 (+43)
  • Hard prompts 1373 rank 209 vs 1319 (+54)
  • Long prompts 1358 rank 213 vs 1321 (+37)
  • Multi-turn 1365 rank 198 vs 1291 (+74)
  • Expert 1331 rank 234 vs 1302 (+29, within range)
1356 ±51303 ±5+53209 of 415
17,464 votes		Oct 13, 2026source
Text: Coding1411 ±101361 ±8+50201 of 410
3,338 votes		Oct 13, 2026source
Vision1140 ±91127 ±8+13
within range		123 of 165
10,846 votes		Oct 9, 2026source

Rated as mistral-small-2506; Mistral Small 3.1 as mistral-small-3.1-24b-instruct-2503. Ratings come from people voting between two anonymous answers; Text and Vision are style-controlled, as on arena.ai. Data: Arena (arena.ai), CC BY 4.0.

Epoch AI

BenchmarkMistral Small 3.2Mistral Small 3.1ChangeSettingRunSource
GPQA Diamond49.1%41.9%+7.2 ptsAug 28, 2026source
OTIS Mock AIME 2024-202530.3%3.9%+26.4 ptsAug 30, 2026source

Run independently by Epoch AI. Data: Epoch AI, Capabilities & benchmarking (epoch.ai/benchmarks), CC BY.

Features

Compare models
FeatureValueSinceSource
Structured outputsThe model can be held to a JSON schema you supply, so every reply parses without retries or cleanup.Supportedin place when tracking began (October 6, 2026)source
Function callingAlso called tool use. You describe functions; the model replies with a function name and arguments for your code to run, then uses the result.Supportedin place when tracking began (October 6, 2026)source
Batch APISend many requests as one job that runs in the background, usually finished within 24 hours, at a lower price than live requests.Supportedin place when tracking began (October 6, 2026)source
Image inputImages such as screenshots, photos and charts can go in the prompt for the model to read.Supportedin place when tracking began (October 6, 2026)source
PDF inputPDF files can go in the prompt directly, without converting them to text first.Supportedin place when tracking began (October 6, 2026)source
Context windowThe most the model can work with in one request, in tokens: your prompt, conversation history and files. A token is about three-quarters of an English word.128,000 tokensin place when tracking began (October 6, 2026)source

Not published by Mistral: Prompt caching, Reasoning / thinking, Fine-tuning, Built-in web search, temperature parameter, top_p parameter, logprobs, Max output tokens.

Price history

USD per 1M tokens, standard tier
$0.00$0.10$0.20$0.30$0.40Oct 2026In $0.10Out $0.30Oct 5, 2026 to Oct 15, 2026: Input $0.10, Output $0.30
$0.00$0.10$0.20$0.30$0.40Oct 2026In $0.10Out $0.30Oct 5, 2026 to Oct 15, 2026: Input $0.10, Output $0.30

We started recording this model's prices on Oct 5, 2026. The history grows with each daily check.

Show as a table
FromTypePrice
Oct 5, 2026Input$0.10
Oct 5, 2026Output$0.30

Prices

USD per 1M tokens, every type and band, by tier
TypePrice $/1MIn effect
Standard
input$0.10
output$0.30

Changelog

Changes we detected on Mistral's pages

No changes recorded yet.

Last checked · Sources: Mistral models