M
Mixtral 8x22B InstructOPEN
Mistral's official instruct fine-tuned version of Mixtral 8x22B.
Prices update automatically — checked daily against provider list prices.
- $3 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
- cheaper than 1% of the 191 open-weight models tracked here
- 19 of 19 Mistral AI models tracked here, from cheapest
Benchmarks & performance
Independent benchmark scores for Mixtral 8x22B Instruct, measured by Artificial Analysis. Higher is better.
Models at this level cost $0.38 per 1M tokens (median of 11) — this one costs $3.
Cheaper and better on this index: GPT-5.6 Sol (batch) · GLM 5.3 · GLM 5.3 Flash and 184 more
About this model
Mixtral 8x22B Instruct is an open-weight AI model by Mistral AI. You can download and self-host it for free; the prices below are hosted-API list prices, tracked daily, for when you prefer convenience over self-hosting.
Frequently asked questions
What is Mixtral 8x22B Instruct?
Mixtral 8x22B Instruct is an AI language model from Mistral AI. It is open-weight: you can download it and run it on your own hardware, for free. It scores 4 on the Artificial Analysis intelligence index.
Is Mixtral 8x22B Instruct free?
The weights are free and open — you can self-host Mixtral 8x22B Instruct and pay nothing per token. If you prefer a hosted API, list prices are $2 per million input tokens and $6 per million output tokens.
What is Mixtral 8x22B Instruct good at?
Independent benchmarks from Artificial Analysis give it GPQA 33.2%, MMLU-Pro 53.7%, Humanity's Last Exam 4%, LiveCodeBench 14.8%, SciCode 18.8%, MATH-500 54.5%, AIME 0%.
Can I self-host Mixtral 8x22B Instruct?
Yes. Mixtral 8x22B Instruct has open weights, so you can download it and run it on your own GPU or server with tools like Ollama, vLLM or llama.cpp — with no per-token cost.