dolphin-2.6-mixtral-8x7b
The Dolphin 2.6 Mixtral 8x7b model is a finetuned version of the Mixtral-8x7b model, trained on a variety of data including coding data, for 3 days on 4 A100 GPUs.
text → text · made by cognitivecomputations
$0.24→$0.24per Mtok in / out
DeepInfra · 2 sellers
Sold by 2 ways
| Seller | Lane | Rate |
|---|---|---|
| DeepInfra aggregator | standard | $0.24per Mtok in$0.24per Mtok outapi.deepinfra.com · read 2026-08-25 |
| Fireworks AI aggregator | standard | $0.5per Mtok in$0.5per Mtok outraw.githubusercontent.com · read 2026-09-16 |
About
dolphin-2.6-mixtral-8x7b — a text model from cognitivecomputations, sold by 2 companies from $0.24 in and $0.24 out per million tokens.
It takes text and returns text, with a context window of 32,768 tokens. The catalogue files it under chat. Two companies sell it. The cheapest is $0.24 in and $0.24 out per million tokens at DeepInfra.
Every current figure
- Maker
- cognitivecomputations
- Register
- model
- Takes
- text
- Returns
- text
- Context
- 32,768 tokens
- Licence
- not read
- Sellers
- 2
- Maker's own price
- not read
- Price
- $0.24 in and $0.24 out per million tokens — DeepInfra
Known as 1 name
cognitivecomputations/dolphin-2.6-mixtral-8x7b