par Mistral AI
32K context · $0.5400/M tokens
Mixtral 8x7B Instruct is 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...
Site officiel
https://openrouter.ai/models/mistralai/mixtral-8x7b-instruct
Documentation API
https://docs.mistral.ai/api/