Mistral: Mistral Small 4

Mistral: Mistral Small 4

mistralai · Released Mar 16, 2026
Intelligence #132 / 756
47.1 our score
Speed #54 / 330
164.9 tok/s
Input Price #292 / 756
$0.150 per 1M tokens
Output Price #318 / 756
$0.600 per 1M tokens
Context #218 / 756
262,144 tokens

Analysis Summary

Mistral Small 4 is an economical multimodal model for straightforward text and image tasks. A 262K context window, tool use, and function calling give it practical workflow coverage, while vision support helps with visual documents and basic analysis. Its general reasoning, coding, and agentic capability are better suited to bounded tasks than demanding autonomous work.

The low token prices make it attractive for classification, content transformation, metadata generation, and high-volume document intake. It can support routine SEO production with editorial checks, but it should not be the default for complex strategy, sensitive client analysis, or difficult code. Adopt it where cost control and multimodal input matter more than depth.

Assessed September 7, 2026

Editorial notes

Mistral Small 4 offers vision, tool calling, a 262K context, and low pricing for routine content and document workflows, but its reasoning and coding capability are limited.

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

DFO Verdict

Mistral Small 4 offers vision, tool calling, a 262K context, and low pricing for routine content and document workflows, but its reasoning and coding capability are limited.

#132 of 756 overall Down 10 this week

How Mistral: Mistral Small 4 compares

Mistral: Mistral Small 4 ranks #207 of 435 AI models we track for overall intelligence, #124 of 208 for coding, #159 of 190 for agentic tasks. Its 262K-token context window is larger than 71% of the models we list. At $0.15 per million input tokens it is cheaper than 61% of comparable models.

Position in the field
Intelligence: smarter than 83% of models #132
Speed: faster than 84% of models #54
Price: cheaper than 61% of models #292
Context: larger than 71% of models #218
worst in fieldmedianbest in field
Price vs frontier peers · $ per 1M tokens
Mistral: Mistral Small 4 $0.15 in $0.60 out
OpenAI: GPT-6 Astra $10.00 in $50.00 out
Anthropic: Claude Fable 5.1 $10.00 in $50.00 out
Claude Opus 5 $5.00 in $25.00 out

Dark bar = input · light bar = output, scaled to the priciest peer.

Context window vs peers · tokens
Mistral: Mistral Small 4 262K

1M tokens ≈ 8 full-length novels or ~2,500 pages of business documents in a single request.

Intelligence1.8Technical2.4Value8Content6.5
Performance profile

Strongest on value. The pulled-in intelligence corner is the trade-off, and if the shape matters more than the price, this is your model.

Compare shapes side-by-side →

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $0.15 $0.000150
Output $0.60 $0.000600

What would Mistral: Mistral Small 4 cost your business?

Pick the job that looks most like yours, then fine-tune with the sliders. Estimates update live.

A website chatbot handling around 100 customer conversations a day, a few short messages each.

3,000
One request is one message, email, draft or automation call.
1,200 tokens

$0/mo Mistral: Mistral Small 4

Full calculator with 756 models → Price Calculator

DFO AI AUTOMATION

These numbers get smaller with the right architecture.

We route routine calls to cheap models and save Mistral: Mistral Small 4 for the hard ones. Most clients cut their estimate by 60-80%.

Talk to our team

About Mistral: Mistral Small 4

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. It combines strong reasoning from..

Frequently asked questions about Mistral: Mistral Small 4

How much does Mistral: Mistral Small 4 cost?

Mistral: Mistral Small 4 costs $0.15 per million input tokens and $0.60 per million output tokens.

What is the context window of Mistral: Mistral Small 4?

Mistral: Mistral Small 4 has a context window of 262,144 tokens (262K).

Is Mistral: Mistral Small 4 good for coding?

On our coding benchmark index, Mistral: Mistral Small 4 ranks #124 of 208 models, placing it in the broader range of the field for code generation and debugging.

What can Mistral: Mistral Small 4 do?

Mistral: Mistral Small 4 supports image/vision input, tool use, and function calling.

Who created Mistral: Mistral Small 4?

Mistral: Mistral Small 4 is developed by Mistral and was released on March 16, 2026.

© 2026 Design for Online Ltd. Registered in England and Wales No. 10328553. VAT Registered. Design for Online® and Forerunner® are registered trademarks.