Skip to content
Mistral

Mixtral 8x22B Instruct

Mixtral 8x22B Instruct is a large language model made by Mistral, added to the catalog on 17 Apr 2024. It has a context window of 65,536 tokens and costs $2.00 per 1M input tokens and $6.00 per 1M output tokens. It accepts text and files and produces text. Typical uses: enhance multilingual customer support, develop educational tools with complex reasoning and automate coding assistance.

Price checked · source: OpenRouter

What Mixtral 8x22B Instruct is

Released in April 2024 by Mistral, the Mixtral 8x22B Instruct model is a versatile text-to-text AI designed for tasks requiring strong math, coding, and reasoning skills. With a substantial context window of 65,536 tokens, it can handle complex text interactions efficiently. This model supports multiple languages, including English, French, Italian, German, and Spanish, making it a valuable tool for multilingual applications. It offers a range of adjustable parameters like frequency penalty and temperature, allowing users to tailor outputs to specific needs. The model is particularly suited for scenarios where large context processing and multilingual fluency are crucial.

Key features

  • 65,536 token context window
  • Supports English, French, Italian, German, Spanish
  • Strong in math, coding, reasoning
  • Adjustable parameters for tailored outputs
  • Text-to-text modality

Typical uses

  • Enhance multilingual customer support
  • Develop educational tools with complex reasoning
  • Automate coding assistance
  • Generate detailed analytical reports
  • Conduct large-scale text analysis

Mixtral 8x22B Instruct pricing

US dollars, list price through OpenRouter.

Checked
Mixtral 8x22B Instruct price list
ItemStandard
Input, per 1M tokens$2.00
Output, per 1M tokens$6.00
Cached input read, per 1M tokens$0.20

No price change since it was added on 17 Apr 2024.

What typical tasks cost with Mixtral 8x22B Instruct
What a task costsCost
Answer a short question500 in / 300 out$0.0028
Summarise a 50-page PDF25,000 in / 800 out$0.055
Review a 2,000-line source file30,000 in / 2,000 out$0.072
Read a 300-page contract set150,000 in / 1,500 out$0.309
Check the provider's pageToken counts are estimates. A maker's direct price and its monthly plans can differ from the per-token price shown here.

Mixtral 8x22B Instruct specifications

Mixtral 8x22B Instruct limits and identity
Model idmistralai/mixtral-8x22b-instruct
Versionmixtral-8x22b-instruct
Context window65,536 tokensAbout 49,152 English words
Max output52,428 tokens
Knowledge cutoff2024-01-31
Added to catalog17 Apr 2024
Mixtral 8x22B Instruct capabilities
Input typestext, file
Output typestext
Tool callingYes
Structured outputsYes
Reasoning effort controlNo
Content moderationNot applied by provider

Sample outputs

The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.

Write a short essay

RUN20 Nov 2026
Prompt

Write 150 words on how AI might positively upend work, leisure and creativity

Output

AI has the potential to revolutionize work, leisure, and creativity in profound ways. In the workplace, AI can automate repetitive tasks, freeing humans to focus on strategic, creative, and interpersonal roles. It can enhance productivity by providing real-time insights, optimizing workflows, and enabling smarter decision-making. For leisure, AI-powered personalization—such as tailored entertainment recommendations, virtual travel experiences, and adaptive fitness programs—can make downtime more engaging and fulfilling. Creativity, too, will be transformed as AI tools assist artists, writers, and designers by generating ideas, refining drafts, and even co-creating entirely new forms of expression. While concerns about job displacement and ethical use exist, AI’s ability to augment human capabilities promises a future where work is more meaningful, leisure is more immersive, and creativity knows no bounds. By embracing AI responsibly, society can unlock unprecedented opportunities for innovation, well-being, and artistic exploration.

Compare Mixtral 8x22B Instruct

Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.

Mixtral 8x22B Instruct questions

How much does Mixtral 8x22B Instruct cost?

Mixtral 8x22B Instruct costs $2.00 per 1M input tokens and $6.00 per 1M output tokens through OpenRouter, as checked on 22 Nov 2026. Summarising a 50-page PDF costs about $0.055.

What is the context window of Mixtral 8x22B Instruct?

65,536 tokens, or roughly 49,152 English words. It can write up to 52,428 tokens in one response.

Can Mixtral 8x22B Instruct read images and PDFs?

It accepts text and files as input. It produces text, so it cannot generate images.

How do I try Mixtral 8x22B Instruct?

Use the "Try Mixtral 8x22B Instruct" button on this page. It opens the chat with Mixtral 8x22B Instruct selected; you type the question and press send.

Try Mixtral 8x22B Instruct on your own question.

It opens in the chat with this model already selected.

Sign in to Upend

Use an account you already have, or get a one-time code by email.

Use a password instead

For accounts that already have a password. Forgotten it? An emailed code signs you in just the same.