Back to Models

mixtral-8x7b-instruct

mixtral-8x7b-instruct

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...

Modalities

Input

text

Output

text
Pricing
Cost per 1 million tokens
Input
$0.648
Output
$0.648
Model Specs
Context Window
32,768
Max Output
16,384
Release Date
2023-12-10
Knowledge Cutoff
Capabilities
Reasoning
Tool Calling
Vision

Last Updated: 2026-03-15

Provider: