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

Magistral Medium 1.0

API ID magistral-medium-2506

Magistral Medium 1.0 was a Mistral model, released June 2025. It had a 40,000-token context window. It took PDF input and supported function calling and reasoning.

Our first frontier-class reasoning model released June 2025.

Mistral's description
Status
Retired
Released
June 2025
Shutdown
Nov 30, 2025

magistral-medium-2506 stopped serving on November 30, 2025. Recommended replacement: mistral-medium-3-5.

How to migrate to Mistral Medium 3.5

Benchmarks

Scores as each source published them
or

No comparison. Pick a model to see the difference on each benchmark.

Arena

ArenaMagistral Medium 1.0RankDateSource
Text
By category
  • Math 1286 rank 266
  • Creative writing 1281 rank 263
  • Instruction following 1301 rank 261
  • Hard prompts 1332 rank 251
  • Long prompts 1337 rank 240
  • Multi-turn 1313 rank 257
  • Expert 1292 rank 272
1305 ±6281 of 415
11,507 votes		Oct 13, 2026source
Text: Coding1387 ±12224 of 410
2,245 votes		Oct 13, 2026source

Rated as magistral-medium-2506. Ratings come from people voting between two anonymous answers; Text is style-controlled, as on arena.ai. Data: Arena (arena.ai), CC BY 4.0.

Features

Compare models
FeatureValueSinceSource
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
PDF inputPDF files can go in the prompt directly, without converting them to text first.Supportedin place when tracking began (October 6, 2026)source
Reasoning / thinkingThe model can work through a problem step by step before it answers: usually better answers to hard questions, at the cost of more tokens and time.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.40,000 tokensin place when tracking began (October 6, 2026)source

Not published by Mistral: Structured outputs, Prompt caching, Image input, 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$2.00$4.00$6.00Oct 2026In $2.00Out $5.00Oct 5, 2026 to Oct 15, 2026: Input $2.00, Output $5.00
$0.00$2.00$4.00$6.00Oct 2026In $2.00Out $5.00Oct 5, 2026 to Oct 15, 2026: Input $2.00, Output $5.00

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$2.00
Oct 5, 2026Output$5.00

Prices

USD per 1M tokens, every type and band, by tier
TypePrice $/1MIn effect
Standard
input$2.00
output$5.00

Changelog

Changes we detected on Mistral's pages

No changes recorded yet.

Last checked · Sources: Mistral models