Model by Mistral AI

Mistral Small 4

Open-weights model from Mistral. 262,144-token context. Listed at $0.15 in and $0.6 out per 1M tokens on OpenRouter (2026-10-31).

Checked 2026-10-31

Loading poll...

Mistral Small 4 is a compact Mistral model released 2026-03-16 under Apache 2.0, which is a standard permissive licence. OpenRouter lists $0.15 per million input tokens and $0.6 output with a 262,144-token context and text and image input. We would suggest it for teams that want an open model they can host themselves under clear terms, or call cheaply through a gateway, for tasks such as extraction, chat and light coding assistance. The limit is that it is a small model, so harder reasoning may need Large 4 or a model from another maker, and that the hardware you need depends on how you serve it, which we did not test. Mistral's Ministral line goes smaller still, at around ten cents per million tokens. Prices and specifications come from the OpenRouter listing we checked on 31 October 2026, and we have not tested the model ourselves.

Mentioned here

Questions

What is the context window of Mistral Small 4?

262,144 tokens, with up to 209,715 tokens of output.

How much does Mistral Small 4 cost?

$0.15 per million input tokens and $0.6 per million output tokens, checked 31 October 2026.

Can I run Mistral Small 4 on my own hardware?

Yes, the weights are published under the Apache 2.0 licence. They are on huggingface.co.

Who makes Mistral Small 4?

Mistral AI makes it, and released it on 16 March 2026.

Loading poll...

Reviews

Loading reviews…

Write a review

Your rating

Up to 1000 characters. Stars alone are enough.

Part of the Wbcom Designs family

The all-in-one WordPress community stack

Also ours: wbcomdesigns.comvapvarun.combrndle.com