Mistral

Mixtral 8x22B Instruct

Mistral mixtral-8x22b-instruct
Model Information
Slug mixtral-8x22b-instruct
LLM.txt View
Release Date April 17, 2024
Organization
Model Description
Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include:
- strong math, coding, and reasoning
- large context length (64k)
- fluency in English, French, Italian, German, and Spanish

See benchmarks on the launch announcement [here](https://mistral.ai/news/mixtral-8x22b/).
#moe
Available at 10 Providers
Provider Type Model Name Original Model Input ($/1M) Output ($/1M) Free Actions
Blackbox AI
Blackbox AI
Code
Mistral: Mixtral 8x22B Instruct
mistralai/mixtral-8x22b-instruct $0.90 $0.90
Vercel AI Gateway
Vercel AI Gateway
Mixtral MoE 8x22B Instruct
mixtral-8x22b-instruct $1.20 $1.20
Fireworks AI
Fireworks AI
Mixtral MoE 8x22B Instruct
mixtral-8x22b-instruct $1.20 $1.20
OpenRouter
OpenRouter
Chat Code
Mixtral 8x22B Instruct
mistralai/mixtral-8x22b-instruct $2.00 $6.00
Kilo Code
Kilo Code
Code
Mistral: Mixtral 8x22B Instruct
mistralai/mixtral-8x22b-instruct $2.00 $6.00
WaveSpeed AI
WaveSpeed AI
Chat Code
mixtral-8x22b-instruct
mistralai/mixtral-8x22b-instruct $2.20 $6.60
ValorGPT
ValorGPT
Mixtral 8x22B Instruct
mistralai-mixtral-8x22b-instruct - -
Yupp
Yupp
Chat
Mixtral 8x22B Instruct (OpenRouter)
mistralai/mixtral-8x22b-instruct - -
LangDB
LangDB
mixtral-8x22b-instruct
mixtral-8x22b-instruct - -
Writingmate
Writingmate
Chat Code
Mistral: Mixtral 8x22B Instruct
mistralai/mixtral-8x22b-instruct - -