AI model comparison

Mistral Medium 3.5 vs Devstral 2 2512

Side by side comparison of Mistral Medium 3.5 and Devstral 2 2512 on pricing, benchmark scores, context window, and more.

Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI.

Mistral Medium 3.5 is scheduled to be retired on January 31, 2027. Consider Mistral Large 4 instead.

Input / 1M
$1.50
Output / 1M
$7.50
Context
262K

Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window.

Input / 1M
$0.40
Output / 1M
$2
Context
262K

Comparing image generators? Compare image models

At a glance

Quick verdict

How the two models stack up on the things people ask about most.

Lower price

mistralai logo

Devstral 2 2512

3.8x cheaper for a typical chat

Higher intelligence score

mistralai logo

Devstral 2 2512

8.6 vs 4.6 on Artificial Analysis

Larger context window

Tie

262K vs 262K tokens

Newer release

mistralai logo

Mistral Medium 3.5

Released April 30, 2026

Benchmarks

Benchmark scores

Independent scores from Artificial Analysis. Higher is better.

Intelligence index

mistralai logoMistral Medium 3.54.6
mistralai logoDevstral 2 25128.6

Coding index

mistralai logoMistral Medium 3.546.9
mistralai logoDevstral 2 251231.3

Agentic index

mistralai logoMistral Medium 3.57
mistralai logoDevstral 2 25122.3

Pricing

Mistral Medium 3.5 vs Devstral 2 2512 API pricing

Per-token API rates. Cheaper option highlighted.

Metricmistralai logoMistral Medium 3.5mistralai logoDevstral 2 2512
Input tokensPer 1M tokens$1.50$0.40
Output tokensPer 1M tokens$7.50$2
Cached input (read)Per 1M tokensNot available$0.04
Cache writePer 1M tokensNot availableNot available

What it costs in practice

Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.

Chat message

2K in, 500 out

mistralai logoMistral Medium 3.5$6.75
mistralai logoDevstral 2 2512$1.80

Coding task

30K in, 4K out

mistralai logoMistral Medium 3.5$75
mistralai logoDevstral 2 2512$20$9.20 cached

Long document summary

150K in, 2K out

mistralai logoMistral Medium 3.5$240
mistralai logoDevstral 2 2512$64$10 cached

Specs

Context window and capabilities

How much each model can read, how much it can write, and what it accepts as input.

Metricmistralai logoMistral Medium 3.5mistralai logoDevstral 2 2512
Context window262K tokens262K tokens
Max output210K tokens210K tokens
Input typesFile, Image, TextFile, Text
Output typesTextText
Reasoning effort levelsHigh, NoneNot available
Default reasoning effortHighNot available
Release dateApril 30, 2026December 9, 2025

Features

Supported features

API features available for each model.

Metricmistralai logoMistral Medium 3.5mistralai logoDevstral 2 2512
Tool callingSupportedSupported
Structured outputsSupportedSupported
JSON modeSupportedSupported
ReasoningSupportedNot supported
TemperatureSupportedSupported
Stop sequencesSupportedSupported
Deterministic seedSupportedSupported
Verbosity controlNot supportedNot supported

Our take

Devstral 2 2512 is 3.8x cheaper for a typical chat. Devstral 2 2512 scores higher on the Artificial Analysis Intelligence Index (8.6 vs 4.6). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.

FAQ

Frequently asked questions

Is Mistral Medium 3.5 or Devstral 2 2512 cheaper?

Devstral 2 2512 is cheaper for a typical chat (2K input tokens and 500 output tokens). Devstral 2 2512 costs $0.40 per 1M input tokens and $2 per 1M output tokens, while Mistral Medium 3.5 costs $1.50 per 1M input tokens and $7.50 per 1M output tokens.

Which has a bigger context window, Mistral Medium 3.5 or Devstral 2 2512?

Mistral Medium 3.5 supports up to 262K tokens of context, compared with 262K for Devstral 2 2512.

Is Mistral Medium 3.5 smarter than Devstral 2 2512?

On the Artificial Analysis Intelligence Index, Mistral Medium 3.5 scores 4.6 and Devstral 2 2512 scores 8.6, putting Devstral 2 2512 ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.

Can I use Mistral Medium 3.5 and Devstral 2 2512 at the same time?

Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Mistral Medium 3.5 and Devstral 2 2512 answer side by side and keep the better response.

mistralai logomistralai logo

Why choose? Ask both.

Send one prompt to Mistral Medium 3.5 and Devstral 2 2512 at the same time. Compare the answers side by side and keep the best one.