Mistral Small 4, the Mistral AI model in numbers

Mistral Small 4 at a glance

Mistral Small 4 is a language model from Mistral AI, released on March 16, 2026. That makes it 7 months old as of October 22, 2026. It is an open-weight model: you can host it yourself on infrastructure you control, and 19 API providers listed on models.dev also offer it. It has a reasoning mode: it can "think" before answering, which helps with multi-step problems but uses more tokens, and therefore more money.

We file it under open-weight models (68 models in this category on the site).

What do independent benchmarks say?

As of October 22, 2026, Epoch AI publishes no score for Mistral Small 4 on our basket's benchmarks. To place it, rely on its specifications and price, then test it on your own cases.

At Mistral AI, the best-scoring model we track is Mistral Large 4, with an index of 79.7.

How much does Mistral Small 4 cost?

Mistral Small 4 costs $0.16 per million input tokens and $0.63 per million output tokens (median of 19 providers, checked on October 22, 2026).

In practice, an agent task that reads 20,000 tokens and writes 2,000 costs about $0.004, or $4.39 for 1,000 such tasks.

That is 1.6 times cheaper than the median output price of open-weight models ($1).

To estimate your own budget, use the agent cost calculator.

Context and capabilities

Its context window reaches 262,144 tokens, roughly 393 pages of text at 500 words per page: enough for a long report or several contracts at once. A single answer can run to 81,920 tokens.

It accepts as input: text. Its knowledge stops at June 2025: beyond that, it needs web search or your documents.

It can call tools (functions, APIs), which makes it a possible foundation for an AI agent.

The weights are published on Hugging Face (mistralai/Mistral-Small-4-119B-2603). See also our list of open-source models.

When to choose it

Given its category, Mistral Small 4 is mainly aimed at projects where you want control over your data or hosting, or want to adapt the model to your field.

Its very low cost (under half a cent for our sample task) means it can be called thousands of times a day.

Before adopting it, test it on your own examples: benchmarks measure standard tasks, not your job.

Alternatives

In the same category, the models closest to Mistral Small 4 are:

• DeepSeek V4 Flash Vision Exp (DeepSeek, $0.65 per million output tokens)
• DeepSeek V4.1 Flash 1017 (DeepSeek, index 90.6)
• Hy3 (Tencent (Hunyuan), $0.53 per million output tokens)
• Nemotron 3 Super 120B A12B (NVIDIA, $0.52 per million output tokens)