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

Mistral Large 2.1

API ID mistral-large-2411

Mistral Large 2.1 was a Mistral model, released November 2024. It had a 128,000-token context window. It took PDF input and supported function calling and structured outputs.

Our top-tier large model for high-complexity tasks with the lastest version released November 2024.

Mistral's description
Status
Retired
Released
November 2024
Shutdown
May 31, 2026

mistral-large-2411 stopped serving on May 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 Large 2.0, 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 Large 2.1Mistral Large 2.0ChangeRankDateSource
Text
By category
  • Math 1282 rank 269 vs 1288 (−6, within range)
  • Creative writing 1276 rank 270 vs 1287 (−11, within range)
  • Instruction following 1295 rank 268 vs 1299 (−4, within range)
  • Hard prompts 1313 rank 276 vs 1320 (−7, within range)
  • Long prompts 1305 rank 280 vs 1305 (0, within range)
  • Multi-turn 1294 rank 274 vs 1297 (−3, within range)
  • Expert 1271 rank 287 vs 1302 (−31)
1306 ±41314 ±4−8
within range		280 of 415
28,073 votes		Oct 13, 2026source
Text: Coding1346 ±91354 ±8−8
within range		275 of 410
4,212 votes		Oct 13, 2026source

Rated as mistral-large-2411; Mistral Large 2.0 as mistral-large-2407. 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.

Epoch AI

BenchmarkMistral Large 2.1Mistral Large 2.0ChangeSettingRunSource
GPQA Diamond51.3%49.0%+2.3 ptsFeb 25, 2025source
MATH Level 550.3%44.8%+5.5 ptsFeb 25, 2025source
OTIS Mock AIME 2024-20257.8%8.5%−0.7 ptsFeb 25, 2025source

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
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, Image input, 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$2.00$4.00$6.00$8.00Oct 2026In $2.00Out $6.00Oct 5, 2026 to Oct 15, 2026: Input $2.00, Output $6.00
$0.00$2.00$4.00$6.00$8.00Oct 2026In $2.00Out $6.00Oct 5, 2026 to Oct 15, 2026: Input $2.00, Output $6.00

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$6.00

Prices

USD per 1M tokens, every type and band, by tier
TypePrice $/1MIn effect
Standard
input$2.00
output$6.00

Changelog

Changes we detected on Mistral's pages

No changes recorded yet.

Last checked · Sources: Mistral models