Mistral AI

Mixtral 8x22B Instruct

Generally availableOpen weights66K context

Summary

Mixtral 8x22B Instruct is an open-weight language model from Mistral AI, released on 17 Apr 2024. It accepts text and PDFs and generates text, with a 66K-token context window and up to 52K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $2 per million input tokens and $6 per million output tokens (OpenRouter), across 1 provider we track.

Mistral model for multilingual chat, reasoning, and tool-assisted workflows

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperMistral AI
Release date17 Apr 2024 [models.dev]
StatusGenerally available [models.dev]
WeightsOpen weights [models.dev]
Context window66K (65,536 tokens) [models.dev]
Max output52K tokens [models.dev]
Knowledge cutoff31 Jan 2024 [models.dev]
InputText and PDFs [models.dev]
OutputText [models.dev]
Reasoning modeNo [models.dev]
Tool callingYes [models.dev]
Structured outputYes [models.dev]
Hugging Facemistralai/Mixtral-8x22B-Instruct-v0.1

Mixtral 8x22B Instruct API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
OpenRouter
mistralai/mixtral-8x22b-instruct
$2$6$0.2066KOpenRouter, 18 Nov 2026

Frequently asked questions

What is the context window of Mixtral 8x22B Instruct?

Mixtral 8x22B Instruct has a context window of 65,536 tokens (66K) and can generate up to 52,428 tokens in a single response, according to models.dev.

How much does the Mixtral 8x22B Instruct API cost?

Mixtral 8x22B Instruct is listed from $2 per million input tokens and $6 per million output tokens (OpenRouter). Prices last verified 18 Nov 2026.

Is Mixtral 8x22B Instruct open source?

Mixtral 8x22B Instruct is an open-weight model: its weights are published on Hugging Face as mistralai/Mixtral-8x22B-Instruct-v0.1. Check the license terms before commercial use.

When was Mixtral 8x22B Instruct released?

Mistral AI released Mixtral 8x22B Instruct on 17 Apr 2024, according to models.dev.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
WizardLM 2 8x22BMicrosoft15 Apr 202466K$0.62$0.62Open
Magnum v4 72BAnthracite ORG22 Oct 202433K$2.50$5Open
Command R+Cohere30 Aug 2024128K$2.50$10Open
DeepSeek-R1DeepSeek20 Jan 202564K$0.70$2.50Open
Llama 3.1 70B InstructMeta23 Jul 2024128K$0.72$0.72Open
GPT-3.5 Turbo 16kOpenAI28 Aug 202316K$3$4–

Change history

  • Input modalities changed from text, file to text, pdf

Sources