Mistral Small 4: API price, context window and how to connect

Mistral Small 4 by Mistral AI: $0.15 per million input tokens, $0.6 per million output tokens, a 262K-token window. What it is good for, what to compare it with and how to connect it in SKILLOK.

Updated Copy as Markdown
In this article

In short#

Mistral Small 4 is the new release of Mistral's small line, combining the capabilities of several of the company's flagship models in one system. Open weights and a low price.

Specifications#

Provider Mistral AI
Released 2026-03-16
Context window 262K tokens
Accepts text, images
Answers with text
Reasoning mode yes
Tool calling yes
Open weights yes
Identifier mistralai/mistral-small-2603

Price#

Per 1M tokens In dollars
Input (question, context) $0.15
Output (answer) $0.6

For reference: a conversation of 20 questions of ~500 tokens and answers of ~800 tokens costs about $0.011. Models in reasoning mode spend more tokens on an answer than the text shows: the reasoning is paid for too.

What it is good for#

  • Inexpensive everyday tasks
  • Running on your own servers
  • Text and images as input

Similar models#

Catalog models with the same kind of output, closest in the price of a typical request.

Model Input Output Window Price
DeepSeek V3.2 $0.28 $0.42 164K about the same
Llama 4 Maverick $0.188 $0.652 1.05M 1.1× more expensive
Qwen3.8 Flash $0.15 $0.47 1M 1.2× cheaper
Qwen3.8 Omni Flash $0.15 $0.47 1M 1.2× cheaper
GPT-6 Luna $0.1 $0.5 1.05M 1.3× cheaper

Other Mistral AI models#

How to connect in SKILLOK#

Mistral Small 4 works through OpenRouter: add an OpenRouter key in Settings → AI and pick the mistralai/mistral-small-2603 model. It then becomes available in Space AI, in tasks and to the repository agent. In detail — Connecting a model in SKILLOK.

Where the data comes from#

Prices, the context window and capabilities come from the public OpenRouter catalog as of 2026-10-19. A provider may change the price — the exact figure is always on the model's OpenRouter page.

Was this helpful?