Mixtral 8x22B Instruct pricing.
prices as of · 5 providers · 6 prices
Mistral AI's Mixtral 8x22B Instruct holds 66k tokens of context. Open weights, so anyone may host it, which is why the prices below differ so much.
Mixtral 8x22B Instruct costs $2 in and $6 out per million tokens from Mistral AI; the cheapest price we can explain is $4.80 at Fireworks AI, checked 16 Sept 2026.
Mistral AI list price
$12/M tokens
$2 in · $6 out
read · 238% above the market median
Cheapest price we can explain
$4.80/M tokens
$1.20 in · $1.20 out · 60% under list
Fireworks AIread
What it costs for your work
Mistral AI list price
$1.56a month
cheapest we can explain · Fireworks AI
$0.792a month
difference
$0.768saved
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.
Every provider selling Mixtral 8x22B Instruct
Four groups, decided by the price and by what the provider publishes about it. Prices are per million tokens, and the share is that row against Mistral AI's price.
The maker's list price
1 priceWhat the lab that trained the model charges on its own API.
Mistral AIThe price Mistral AI charges for the model it trained. Every row below is measured against it.
$2 / $6in / out per M
1.00×of list price
Cheaper, and we know why
1 priceBelow list, with a published reason: hosting the open weights, a regional price list, credits, a stated discount.
- Fireworks AI
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$1.20 / $1.20in / out per M
0.40×of list price
Same price as the maker
3 pricesThe same price the maker charges, sold by someone else.
$2 / $6in / out per M
1.00×of list price
$2 / $6in / out per M
1.00×of list price
$2 / $6in / out per M
1.00×of list price
Given away with limits
1 free tiers · never rankedThese providers give Mixtral 8x22B Instruct away inside a quota of their own. A limit is not a price, so none of them counts as cheapest here or anywhere else on the site.
NVIDIA build
Frequently asked
- Who sells Mixtral 8x22B Instruct cheapest?
- Fireworks AI, at $1.20 in and $1.20 out per million tokens, read on 16 Sept 2026. Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
- Is Mixtral 8x22B Instruct open weights?
- Yes. Mistral AI publishes the weights, so anyone may host Mixtral 8x22B Instruct, which is why 5 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 $12 per million tokens, Mistral AI's price is 238% above the $3.55 median across the 337 text models we track.