modelgrep
M

Mistral: Mistral Medium 3.1

mistralai/mistral-medium-3.1

115th smartest of 178ToolsJSONVision
Use via OpenRouter ↗
Intelligence
21.3
115th of 178
Design Elo
1192
Data Viz
Speed
tokens/sec
Latency
first token
Input price
$0.400
148th cheapest
Context
131K

How it compares

Smarter than35%
of all ranked models
Cheaper than50%
of all ranked models

Overview

Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...

Benchmarks

independent · via OpenRouter
Artificial Analysis35th percentile
Intelligence Index
21.3
Coding Index
18.3
Agentic Index
25.3
GPQA Diamond
59%
Humanity's Last Exam
4%
SciCode
34%
Tau²-Bench (agentic)
41%
Design Arena · Elo14,172 tournaments
Data Viz
1192
Website
1178
codecategories
1172
3D
1163
UI Component
1155
Game Dev
1143
svg
1049
asciiart
1040

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
Mistral$0.400$2.00100%

Specifications

Context window131K
Max output
Knowledge cutoffJun 2025
Input modalitiestext, image, file
Output modalitiestext
Prompt caching
Cache read price$0.040/M
ModeratedNo

Mistral Medium 3.1 FAQ

How much does Mistral Medium 3.1 cost?

Mistral Medium 3.1 costs $0.400 per million input tokens and $2.00 per million output tokens via OpenRouter, making it 148th cheapest of 298 paid models.

How smart is Mistral Medium 3.1?

Mistral Medium 3.1 scores 21.3 on the Artificial Analysis Intelligence Index, ranking 115th of 178 benchmarked models, with a GPQA Diamond score of 59%.

What is Mistral Medium 3.1's context window?

Mistral Medium 3.1 supports a 131K-token context window. It accepts text, image, file input.

Compare head-to-head