How much does Mistral Small cost per million tokens?

Mistral Small is priced at $0.20 / 1M tokens for input tokens and $0.60 / 1M tokens for output tokens via the official Mistral API at the time of writing.

What is Mistral Small's context window?

Mistral Small supports a context window of 128K tokens.

Is Mistral Small open source?

Mistral Small ships with open weights under the Apache-2.0 license. You can self-host it, fine-tune it, and (subject to the license terms) deploy it commercially.

When was Mistral Small released?

Mistral Small was released on Sep 18, 2024 by Mistral.

How much does Mistral Small cost per million tokens?

Mistral Small is priced at $0.20 / 1M tokens for input tokens and $0.60 / 1M tokens for output tokens via the official Mistral API at the time of writing.

What is Mistral Small's context window?

Mistral Small supports a context window of 128K tokens.

Is Mistral Small open source?

Mistral Small ships with open weights under the Apache-2.0 license. You can self-host it, fine-tune it, and (subject to the license terms) deploy it commercially.

When was Mistral Small released?

Mistral Small was released on Sep 18, 2024 by Mistral.

Open weightsMistralsmalltext

Mistral Small

Mistral's small-tier API model, fast and cheap for routing and high-volume tasks.

UpdatedApr 30, 2026

Quick facts

Released: Sep 2024
Context: 128K tokens
Output / 1M: $0.60 / 1M tokens
License: Apache-2.0

About Mistral Small

Mistral Small is the company's small-tier API model, comparable in size to Llama 3 8B / 70B blends but optimised for Mistral's deployment stack and EU data residency.

The model also ships under Apache-2.0 for self-hosting, making it one of the few small-tier models from a major lab that's clean for commercial fine-tuning and resale.

Benchmarks

Published scores from Mistral's model card or independent leaderboards. We do not publish numbers we cannot source, see methodology.

HumanEval

Python coding pass@1

MMLU

Broad academic knowledge

GPQA

Graduate-level reasoning

SWE-bench

Real software-engineering tasks

Benchmark scores not yet available. We only publish numbers we can source from official model cards or independent leaderboards, see methodology.

Capabilities

Strengths

Apache-2.0 open-weight
Fast and cheap

Tracked weaknesses

Quality limited at small size

Pricing

Per-million-token rates as published by Mistral.

Tier	Price	Notes
Input	$0.20 / 1M tokens	Tokens you send to the model
Output	$0.60 / 1M tokens	Tokens the model generates
Context	128K tokens	Max combined input + output

Call Mistral Small from your code

Drop-in snippet for the Mistral SDK. Set your API key in the environment and run.

typescript

import OpenAI from "openai";

const client = new OpenAI({
  // Use OPENAI_API_KEY for OpenAI, or your provider's key + baseURL.
  apiKey: process.env.OPENAI_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "mistral-small",
  messages: [
    { role: "user", content: "What's the time complexity of quicksort?" },
  ],
});

console.log(completion.choices[0].message.content);

Compare Mistral Small with…

Frequently asked

How much does Mistral Small cost per million tokens?
Mistral Small is priced at $0.20 / 1M tokens for input tokens and $0.60 / 1M tokens for output tokens via the official Mistral API at the time of writing.
What is Mistral Small's context window?
Mistral Small supports a context window of 128K tokens.
Is Mistral Small open source?
Mistral Small ships with open weights under the Apache-2.0 license. You can self-host it, fine-tune it, and (subject to the license terms) deploy it commercially.
When was Mistral Small released?
Mistral Small was released on Sep 18, 2024 by Mistral.

Friday digest

One short email every Friday, new model launches, leaderboard moves, and pricing drops. Curated by hand. Free, no spam.