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

Mistral Medium 3.1

API ID mistral-medium-2508

Mistral Medium 3.1 was a Mistral model, released August 2025. It had a 128,000-token context window. It took image and PDF input and supported function calling and structured outputs.

Our frontier-class multimodal model released August 2025. Improving tone and performance.

Mistral's description
Status
Retired
Released
August 2025
Shutdown
Aug 31, 2026

mistral-medium-2508 stopped serving on August 31, 2026. Recommended replacement: mistral-medium-3-5.

How to migrate to Mistral Medium 3.5

Benchmarks

Scores as each source published them
or

Comparing with Mistral Medium 3, 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 Medium 3.1Mistral Medium 3ChangeRankDateSource
Text
By category
  • Math 1395 rank 167 vs 1348 (+47)
  • Creative writing 1378 rank 146 vs 1364 (+14, within range)
  • Instruction following 1395 rank 155 vs 1365 (+30)
  • Hard prompts 1427 rank 150 vs 1401 (+26)
  • Long prompts 1408 rank 158 vs 1392 (+16)
  • Multi-turn 1407 rank 153 vs 1403 (+4, within range)
  • Expert 1411 rank 166 vs 1378 (+33)
1408 ±31387 ±5+21153 of 415
95,341 votes		Oct 13, 2026source
Text: Coding1454 ±51432 ±8+22151 of 410
21,570 votes		Oct 13, 2026source
Vision1159 ±61155 ±8+4
within range		112 of 165
41,631 votes		Oct 9, 2026source

Rated as mistral-medium-2508; Mistral Medium 3 as mistral-medium-2505. 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.

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$0.50$1.00$1.50$2.00$2.50Oct 2026In $0.40Out $2.00Oct 5, 2026 to Oct 15, 2026: Input $0.40, Output $2.00
$0.00$0.50$1.00$1.50$2.00$2.50Oct 2026In $0.40Out $2.00Oct 5, 2026 to Oct 15, 2026: Input $0.40, Output $2.00

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$0.40
Oct 5, 2026Output$2.00

Prices

USD per 1M tokens, every type and band, by tier
TypePrice $/1MIn effect
Standard
input$0.40
output$2.00

Changelog

Changes we detected on Mistral's pages

No changes recorded yet.

Last checked · Sources: Mistral models