Mistral: Mixtral 8x7B (base)

mistralai/mixtral-8x7b

Created Dec 10, 202332,768 context

$0.54/M input tokens$0.54/M output tokens

Mixtral 8x7B is a pretrained generative Sparse Mixture of Experts, by Mistral AI. Incorporates 8 experts (feed-forward networks) for a total of 47B parameters. Base model (not fine-tuned for instructions) - see Mixtral 8x7B Instruct for an instruct-tuned model.

#moe

Mistral: Mixtral 8x7B (base)

mistralai/mixtral-8x7b

Mistral: Mixtral 8x7B (base)

mistralai/mixtral-8x7b

Providers for Mixtral 8x7B (base)

OpenRouter routes requests to the top-ranked providers able to handle your prompts.

Providers for Mixtral 8x7B (base)

OpenRouter routes requests to the top-ranked providers able to handle your prompts.