Mistral › Mixtral 8x22B Instruct › Pricing
Mixtral 8x22B Instruct pricing
API list price by Mistral · checked Oct 23, 2026
$2 / $6per 1M tokens in / out
$0.20cache read · −90%
#495on OpenRouter by tokens · 25M / week
Price sheetper 1M tokens
| Input | $2 | list |
| Output | $6 | |
| Cache read | $0.20 | −90% vs input |
| Context · max output | 66K · 52K | tokens |
Where to buy1 provider · per 1M tokens
| Provider | Input | Output | Context |
|---|---|---|---|
| Mistrallab | $2 | $6 | 66K |
In Mistral's line-upper 1M in / out
| Mixtral 8x7B Instruct v0.1 | $0.54 / $0.54 | −82% |
| Devstral Medium | $0.40 / $2 | −73% |
| Devstral 2 123B | $0.40 / $2 | −73% |
| Mistral Small | $1 / $3 | −50% |
| Mistral Large 4 | $1.36 / $4.18 | −31% |
| Mistral Medium 3.5 | $1.50 / $7.50 | 0% |
| Mixtral 8x22B Instruct | $2 / $6 | this model |
Cheaper for the same workvs Mixtral 8x22B Instruct
| Muse Spark 1.3 max | -33% | score ×8.4 | $1.60 |
| MiMo v2.6 Pro thinkingOpen | -82% | score ×8.1 | $0.13 |
| DeepSeek V4.1 Flash 1017 maxOpen | -83% | score ×7.9 | $0.26 |
| GLM 5.3 maxOpen | -28% | score ×7.8 | $2.01 |
| Step 5 Preview thinkingOpen | -52% | score ×7.6 | $1.03 |
Pricing questions
How much does Mixtral 8x22B Instruct cost?›
$2 per 1M input tokens and $6 per 1M output tokens. Cached input is $0.20.
Is Mixtral 8x22B Instruct free to use?›
There is no free API tier, but the weights are open: you can run it on your own hardware for the cost of compute.
How much does prompt caching save?›
Cache reads cost $0.20 per 1M, 90% below the input price.
What is a cheaper alternative to Mixtral 8x22B Instruct?›
Muse Spark 1.3 at max effort costs -33% per task with a score ×8.4 on Humanity's Last Exam.