Mistral
Mistral

Mixtral 8x7B Instruct

mistralai/mixtral-8x7b-instruct

A pretrained generative Sparse Mixture of Experts, by Mistral AI, for chat and instruction use. Incorporates 8 experts (feed-forward networks) for a total of 47 billion parameters.

Instruct model fine-tuned by Mistral. #moe

Community

Open Source

Context Window

32,768

Max Output Tokens

8,192

ProviderInput Token PriceOutput Token Price
OctoAI$0.45/Million Tokens$0.45/Million Tokens