Mixtral 8x7B Instruct (nitro)

mistralai/mixtral-8x7b-instruct:nitro

Updated Mar 732,768 context
$0.54/M input tkns$0.54/M output tkns

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

Note: this is a higher-throughput version of this model, and may have higher prices and slightly different outputs.