Mixtral 8x22B Instruct pricing.
Prices checked
Mixtral 8x22B Instruct costs $2 in and $6 out per million tokens from Mistral AI; the cheapest price is $0.60 at Nscale, checked .
Mistral AI's own price
Mistral AI
$2 in · $6 out
240% above the typical price of the 392 text models we track.
Cheapest price
Nscale
$0.60 in · $0.60 out
80% less than Mistral AI, and the provider says why.
Every provider selling Mixtral 8x22B Instruct
- 1
$0.60 in · $0.60 out
$0.60/M tokens - 2
$1.20 in · $1.20 out
$1.20/M tokens - 3
$2 in · $6 out
$3/M tokens - 4
$2 in · $6 out
$3/M tokens - 5
$2 in · $6 out
$3/M tokens - 6
$2 in · $6 out
$3/M tokens - 7
$2 in · $6 out
$3/M tokens - 8Costs more
$2.12 in · $6.35 out
$3.17/M tokens - 9Costs more
$2.20 in · $6.60 out
$3.30/M tokens
What it costs for your work
A month at Mistral AI's own price
A month at Nscale, the cheapest
What you save
A page is about 600 tokens in and 60 out, a support reply 200 in and 300 out, an email 150 in and 250 out. Nothing else is counted: no cache discount, no batch rate, no free tier.
How we count
Prices are per million tokens. The big number on each row is blended 3 in : 1 out, the way most work uses a model. A price below Mistral AI's own is listed as cheapest only when the provider says why.
- Runs it themselves
- The provider runs the open weights on hardware of its own, so the price is its own rather than a resale.
- Same as maker
- Sold by someone else at the price the maker charges.
- Maker's price
- What the lab that trained the model charges on its own API. Every other row is measured against it.
- Costs more
- Sold by someone else for more than the maker charges.
Similar models
Models from other labs that do what Mixtral 8x22B Instruct does, cheapest first. Each percentage is against Mixtral 8x22B Instruct's cheapest price, $0.60 per M tokens.
Frequently asked
- Who sells Mixtral 8x22B Instruct cheapest?
- Nscale, at $0.60 in and $0.60 out per million tokens, checked 31 Oct 2026. The provider runs the open weights on hardware of its own, so the price is its own rather than a resale.
- Is Mixtral 8x22B Instruct open weights?
- Yes. Mistral AI publishes the weights, so anyone may host Mixtral 8x22B Instruct, which is why 9 providers sell it and why their prices differ so much.
- How much context does Mixtral 8x22B Instruct hold?
- 65,536 tokens in one call, which is about 66k, and it can call your own functions.
- How does Mixtral 8x22B Instruct compare with the rest of the market?
- At $3 per million tokens, Mistral AI's own price is 240% above the typical $0.88 across the 392 text models we track.
More from Mistral AI