Mixtral 8x22B Instruct

Mistral AImistralai/mixtral-8x22b-instructProviders: 3
Inputi$2per 1M tokens
Outputi$6per 1M tokens
Contexti64K65,536 tokens
ReleasedApr 17, 2024Max output: 52K

Where it stands

Quality in independent tests against price, next to 135 other models. Up means more capable, left means cheaper.

100110120130140150160170$0.01$0.03$0.1$0.3$1$3$10$30$100Overall indexPrice per million tokens, log scale (3 parts input to 1 part output)↖ Cheaper and smarterMixtral 8x22B Instruct
Scores: Epoch AI (CC BY 4.0). Prices: OpenRouter. View as a table

About this model

Mixtral 8x22B Instruct is an AI model from Mistral AI, made available through the API on April 17, 2024. It can read up to 65,536 tokens in one request, roughly 123 pages of text, and write up to 52,428 tokens in a single answer. Besides text, it accepts files such as PDFs as input.

Through the API it costs $2 per million input tokens and $6 per million output tokens. Its pricing sits in the middle of the market.

It can call tools and functions, so developers can connect it to search, databases or other software. Its weights are openly published (mistralai/Mixtral-8x22B-Instruct-v0.1), so it can also be downloaded and run on your own hardware.

Quality scores

Rankings →
122.0Overall index · #127 of 136

Benchmark data: Epoch AI, licensed CC BY 4.0

Where to use it

Companies that serve this model through an API: 3. Prices per million tokens, cheapest first.

ProviderInputiOutputiContextiUptime (24 h)i
MistralOfficialCheapest
$2$664K100.0%
MistralOfficialCheapest
$2$664K100.0%
MistralOfficial
$2.20$6.6064K100.0%

Availability and prices come from OpenRouter’s public API and are refreshed daily. Uptime is the share of successful requests over the last 24 hours. Some providers run a compressed version of open models (fp8, int4), which is cheaper but can be slightly less accurate.

Use it in your code

Call Mixtral 8x22B Instruct through OpenRouter’s OpenAI-compatible API: create a key on openrouter.ai, then run one of these examples.

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "mistralai/mixtral-8x22b-instruct", "messages": [{"role": "user", "content": "Hello! What can you do?"}]}'

The same code works with every model on this site: only the model ID changes. Many labs also offer their own API and SDK.

What it costs in practice

  • 1,000 chat replies
    ≈ 500 tokens in, 300 out each
    $2.80
  • Summarise a 100-page document
    ≈ 50,000 tokens in, 1,000 out
    $0.106
  • An app with 10,000 requests a day for a month
    ≈ 1,000 tokens in, 400 out each
    $1,320

Cost calculator →

Similar-priced alternatives

News about Mistral AI

See all →

Frequently asked questions

How much does Mixtral 8x22B Instruct cost?
Mixtral 8x22B Instruct costs $2 per million input tokens and $6 per million output tokens through the API. For example, 1,000 chat replies of about 500 tokens in and 300 out cost around $2.80.
What is the context window of Mixtral 8x22B Instruct?
Mixtral 8x22B Instruct can read up to 65,536 tokens in one request, about 123 pages of text. It can write up to 52,428 tokens in a single answer.
Is Mixtral 8x22B Instruct open source?
Yes. Its weights are published (mistralai/Mixtral-8x22B-Instruct-v0.1), so you can download it and run it on your own hardware, or use it through one of 3 API providers.
Who makes Mixtral 8x22B Instruct?
Mixtral 8x22B Instruct is made by Mistral AI. It became available through the API on April 17, 2024.
How good is Mixtral 8x22B Instruct?
Mixtral 8x22B Instruct has an overall index of 122.0 in Epoch AI’s independent tests, ranking #127 of 136 models we track.
Can Mixtral 8x22B Instruct read images?
Yes. Besides text, it accepts files such as PDFs as input.
What are the alternatives to Mixtral 8x22B Instruct?
Models with a similar price from other companies include GPT-6.1 Sol Pro, Claude Sonnet 5.5 and Grok 4.7. You can compare them side by side on this page.