How much does Pixtral 12B cost?

Mistral has not published per-token API pricing for Pixtral 12B at the time of writing. Check the official site for current pricing tiers, or compare against alternative models on LLMDex.

What is Pixtral 12B's context window?

Pixtral 12B supports a context window of 128K tokens.

Is Pixtral 12B open source?

Pixtral 12B 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 Pixtral 12B released?

Pixtral 12B was released on Sep 17, 2024 by Mistral.

How much does Pixtral 12B cost?

Mistral has not published per-token API pricing for Pixtral 12B at the time of writing. Check the official site for current pricing tiers, or compare against alternative models on LLMDex.

What is Pixtral 12B's context window?

Pixtral 12B supports a context window of 128K tokens.

Is Pixtral 12B open source?

Pixtral 12B 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 Pixtral 12B released?

Pixtral 12B was released on Sep 17, 2024 by Mistral.

Open weightsMistralsmalltextvision

Pixtral 12B

Mistral's 12B multimodal, first vision-capable Apache-2.0 model from the company.

UpdatedApr 30, 2026

Quick facts

Released: Sep 2024
Context: 128K tokens
Output / 1M: Pricing not published
License: Apache-2.0

About Pixtral 12B

Pixtral 12B was Mistral's mid-2024 entry into multimodal LLMs, Apache-2.0 licensed and designed for efficient single-GPU inference. The 12B size makes it deployable on a single 24GB consumer GPU after quantization.

For self-hosted document extraction, screenshot understanding, and small-scale OCR pipelines, Pixtral 12B is a popular pick. It's been largely complemented (not replaced) by Qwen2-VL for higher-quality workloads.

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 We do not publish numbers we cannot source, see methodology.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
Vision in 12B size
Single-GPU

Tracked weaknesses

Superseded by Pixtral Large for quality

Pricing

Per-million-token rates as published by Mistral.

Per-token pricing not yet published for Pixtral 12B. Check the official provider site for current tiers.

Call Pixtral 12B 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: "pixtral-12b",
  messages: [
    { role: "user", content: "What's the time complexity of quicksort?" },
  ],
});

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

Compare Pixtral 12B with…

Frequently asked

How much does Pixtral 12B cost?
Mistral has not published per-token API pricing for Pixtral 12B at the time of writing. Check the official site for current pricing tiers, or compare against alternative models on LLMDex.
What is Pixtral 12B's context window?
Pixtral 12B supports a context window of 128K tokens.
Is Pixtral 12B open source?
Pixtral 12B 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 Pixtral 12B released?
Pixtral 12B was released on Sep 17, 2024 by Mistral.

Friday digest

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