AI model comparison

Mistral Medium 3.5 vs Mistral Small 4

Side by side comparison of Mistral Medium 3.5 and Mistral Small 4 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

Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system.

Input / 1M
$0.15
Output / 1M
$0.60
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

Mistral Small 4

11.3x cheaper for a typical chat

Higher intelligence score

mistralai logo

Mistral Medium 3.5

4.6 vs 4.3 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 logoMistral Small 44.3

Coding index

mistralai logoMistral Medium 3.546.9
mistralai logoMistral Small 426.6

Agentic index

mistralai logoMistral Medium 3.57
mistralai logoMistral Small 40.8

Pricing

Mistral Medium 3.5 vs Mistral Small 4 API pricing

Per-token API rates. Cheaper option highlighted.

Metricmistralai logoMistral Medium 3.5mistralai logoMistral Small 4
Input tokensPer 1M tokens$1.50$0.15
Output tokensPer 1M tokens$7.50$0.60
Cached input (read)Per 1M tokensNot available$0.02
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 logoMistral Small 4$0.60

Coding task

30K in, 4K out

mistralai logoMistral Medium 3.5$75
mistralai logoMistral Small 4$6.90$2.85 cached

Long document summary

150K in, 2K out

mistralai logoMistral Medium 3.5$240
mistralai logoMistral Small 4$23.70$3.45 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 logoMistral Small 4
Context window262K tokens262K tokens
Max output210K tokens210K tokens
Input typesFile, Image, TextImage, Text
Output typesTextText
Reasoning effort levelsHigh, NoneHigh, None
Default reasoning effortHighHigh
Release dateApril 30, 2026March 16, 2026

Features

Supported features

API features available for each model.

Metricmistralai logoMistral Medium 3.5mistralai logoMistral Small 4
Tool callingSupportedSupported
Structured outputsSupportedSupported
JSON modeSupportedSupported
ReasoningSupportedSupported
TemperatureSupportedSupported
Stop sequencesSupportedSupported
Deterministic seedSupportedSupported
Verbosity controlNot supportedNot supported

Our take

Mistral Small 4 is 11.3x cheaper for a typical chat. Mistral Medium 3.5 scores higher on the Artificial Analysis Intelligence Index (4.6 vs 4.3). 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 Mistral Small 4 cheaper?

Mistral Small 4 is cheaper for a typical chat (2K input tokens and 500 output tokens). Mistral Small 4 costs $0.15 per 1M input tokens and $0.60 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 Mistral Small 4?

Mistral Medium 3.5 supports up to 262K tokens of context, compared with 262K for Mistral Small 4.

Is Mistral Medium 3.5 smarter than Mistral Small 4?

On the Artificial Analysis Intelligence Index, Mistral Medium 3.5 scores 4.6 and Mistral Small 4 scores 4.3, putting Mistral Medium 3.5 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 Mistral Small 4 at the same time?

Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Mistral Medium 3.5 and Mistral Small 4 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 Mistral Small 4 at the same time. Compare the answers side by side and keep the best one.