AI model comparison

Mistral Small 4 vs Ministral 3 14B 2512

Side by side comparison of Mistral Small 4 and Ministral 3 14B 2512 on pricing, benchmark scores, context window, and more.

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

The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart.

Input / 1M
$0.20
Output / 1M
$0.20
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

Ministral 3 14B 2512

1.2x cheaper for a typical chat

Higher intelligence score

mistralai logo

Ministral 3 14B 2512

6 vs 4.3 on Artificial Analysis

Larger context window

Tie

262K vs 262K tokens

Newer release

mistralai logo

Mistral Small 4

Released March 16, 2026

Benchmarks

Benchmark scores

Independent scores from Artificial Analysis. Higher is better.

Intelligence index

mistralai logoMistral Small 44.3
mistralai logoMinistral 3 14B 25126

Coding index

mistralai logoMistral Small 426.6
mistralai logoMinistral 3 14B 251214.4

Agentic index

mistralai logoMistral Small 40.8
mistralai logoMinistral 3 14B 25121.1

Pricing

Mistral Small 4 vs Ministral 3 14B 2512 API pricing

Per-token API rates. Cheaper option highlighted.

Metricmistralai logoMistral Small 4mistralai logoMinistral 3 14B 2512
Input tokensPer 1M tokens$0.15$0.20
Output tokensPer 1M tokens$0.60$0.20
Cached input (read)Per 1M tokens$0.02$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 Small 4$0.60
mistralai logoMinistral 3 14B 2512$0.50

Coding task

30K in, 4K out

mistralai logoMistral Small 4$6.90$2.85 cached
mistralai logoMinistral 3 14B 2512$6.80$1.40 cached

Long document summary

150K in, 2K out

mistralai logoMistral Small 4$23.70$3.45 cached
mistralai logoMinistral 3 14B 2512$30.40$3.40 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 Small 4mistralai logoMinistral 3 14B 2512
Context window262K tokens262K tokens
Max output210K tokens210K tokens
Input typesImage, TextImage, Text
Output typesTextText
Reasoning effort levelsHigh, NoneNot available
Default reasoning effortHighNot available
Release dateMarch 16, 2026December 2, 2025

Features

Supported features

API features available for each model.

Metricmistralai logoMistral Small 4mistralai logoMinistral 3 14B 2512
Tool callingSupportedSupported
Structured outputsSupportedSupported
JSON modeSupportedSupported
ReasoningSupportedNot supported
TemperatureSupportedSupported
Stop sequencesSupportedSupported
Deterministic seedSupportedSupported
Verbosity controlNot supportedNot supported

Our take

Ministral 3 14B 2512 is 1.2x cheaper for a typical chat. Ministral 3 14B 2512 scores higher on the Artificial Analysis Intelligence Index (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 Small 4 or Ministral 3 14B 2512 cheaper?

Ministral 3 14B 2512 is cheaper for a typical chat (2K input tokens and 500 output tokens). Ministral 3 14B 2512 costs $0.20 per 1M input tokens and $0.20 per 1M output tokens, while Mistral Small 4 costs $0.15 per 1M input tokens and $0.60 per 1M output tokens.

Which has a bigger context window, Mistral Small 4 or Ministral 3 14B 2512?

Mistral Small 4 supports up to 262K tokens of context, compared with 262K for Ministral 3 14B 2512.

Is Mistral Small 4 smarter than Ministral 3 14B 2512?

On the Artificial Analysis Intelligence Index, Mistral Small 4 scores 4.3 and Ministral 3 14B 2512 scores 6, putting Ministral 3 14B 2512 ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.

Can I use Mistral Small 4 and Ministral 3 14B 2512 at the same time?

Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Mistral Small 4 and Ministral 3 14B 2512 answer side by side and keep the better response.

mistralai logomistralai logo

Why choose? Ask both.

Send one prompt to Mistral Small 4 and Ministral 3 14B 2512 at the same time. Compare the answers side by side and keep the best one.