Mixtral 8x7B
Mistral's first open mixture-of-experts model, state-of-the-art competing against models up to two to three times larger; 47B parameters with 13B active, now retired.
text → text · made by Mistral AI
$0.45→$0.7per Mtok in / out
AWS Bedrock · 2 sellers
Sold by 3 ways
| Seller | Lane | Rate |
|---|---|---|
| AWS Bedrock cloud | standard | $0.45per Mtok in$0.7per Mtok outaws.amazon.com · read 2026-08-24 |
| AWS Bedrock cloud | in-region | $0.45per Mtok in$0.7per Mtok outpricing.us-east-1.amazonaws.com · read 2026-08-24 |
| Fireworks AI aggregator | standard | $0.5per Mtok in$0.5per Mtok outdocs.fireworks.ai · read 2026-08-24 |
About
Mixtral 8x7B — a text model from Mistral AI, sold by 2 companies from $0.45 in and $0.7 out per million tokens.
It takes text and returns text, with a context window of 32,768 tokens. Its sellers say it can call a tool. The catalogue files it under chat. Two companies sell it. The cheapest is $0.45 in and $0.7 out per million tokens at AWS Bedrock. Beside the standard rate there is a regional lane.
Every current figure
- Maker
- Mistral AI
- Register
- model
- Takes
- text
- Returns
- text
- Context
- 32,768 tokens
- Longest answer
- 32,000 tokens
- Knowledge to
- January 2024
- Sellers
- 2
- Maker's own price
- not read
- Price
- $0.45 in and $0.7 out per million tokens — AWS Bedrock
Known as 1 name
mistral.mixtral-8x7b-instruct-v0:1