All Models

Mistral: Mixtral 8x7B Instruct

Tool Calling Open Weights

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 parameters. Instruct model fine-tuned by Mistral. #moe

Providers 1
Released Dec 10, 2023
Input Modalities text
Output Modalities text
Tarsk Use coding

Benchmarks

7.7
Intelligence Index

Available Providers (1)

Provider Model ID Input Cost Output Cost Context Max Output Docs
Kilo Gateway mistralai/mixtral-8x7b-instruct $0.54/MTok $0.54/MTok 32.8K 16.4K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output