Mistral Medium 3.1 vs Mistral Medium 3

Compare Mistral Medium 3.1 from Mistral and Mistral Medium 3 from Mistral on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the OpenRouter API.

Favicon for mistralai
Mistral Medium 3.1
Favicon for mistralai
Mistral Medium 3

Overview

Mistral Medium 3.1
Author
Mistral
Mistral Medium 3
Author
Mistral
Mistral Medium 3.1
Context length
131Ktokens
Mistral Medium 3
Context length
131Ktokens
Mistral Medium 3.1
Reasoning
Mistral Medium 3
Reasoning
Mistral Medium 3.1
Input modalities
Mistral Medium 3
Input modalities
Mistral Medium 3.1
Output modalities
Mistral Medium 3
Output modalities

Analysis

Mistral Medium 3.1 vs Mistral Medium 3 at a glance

Mistral Medium 3.1
Input price
$0.40/M tokens
Mistral Medium 3
Input price
$0.40/M tokens
Mistral Medium 3.1
Output price
$2/M tokens
Mistral Medium 3
Output price
$2/M tokens
Mistral Medium 3.1
Context window
131,072 tokens
Mistral Medium 3
Context window
131,072 tokens
Mistral Medium 3.1
Intelligence Index
Not available
Mistral Medium 3
Intelligence Index
Not available
Mistral Medium 3.1
Coding Index
20.5
Mistral Medium 3
Coding Index
Not available
Mistral Medium 3.1
Agentic Index
1.9
Mistral Medium 3
Agentic Index
Not available
Mistral Medium 3.1
Latency (p50)
0.71 s
Mistral Medium 3
Latency (p50)
1.39 s
Mistral Medium 3.1
Throughput (p50)
88.0 tok/s
Mistral Medium 3
Throughput (p50)
79.0 tok/s
Mistral Medium 3.1
Provided by
Mistral
Mistral Medium 3
Provided by
Mistral

Benchmark data updated

Frequently asked questions

Is Mistral Medium 3.1 cheaper than Mistral Medium 3?

Mistral Medium 3.1 and Mistral Medium 3 cost the same on OpenRouter: $0.40/M tokens input and $2/M tokens output.

Which has the longer context window, Mistral Medium 3.1 or Mistral Medium 3?

Mistral Medium 3.1 and Mistral Medium 3 have the same context window of 131,072 tokens.

Which is faster, Mistral Medium 3.1 or Mistral Medium 3?

Mistral Medium 3.1 is faster on OpenRouter, generating a median 88.0 tokens per second compared with 79.0 tokens per second for Mistral Medium 3.