Mistral Models
Mistral logo

Mixtral 8x7B Instruct

8B

by Mistral

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

Chat with Mixtral 8x7B Instruct
Input Price$0.54/1M tokens
Output Price$0.60/1M tokens
Intelligence7.7
CodingN/A

Specifications

Technical details and pricing.

ProviderMistral
Context Window32,768 tokens
Release DateDec 11, 2023
ModalitiesText

Benchmarks

7 benchmark scores from Artificial Analysis.

GPQA29.2%
MMLU Pro38.7%
HLE4.5%
LiveCodeBench6.6%
MATH 50029.9%
AIME0.0%
SciCode2.8%

Composite Indices

Intelligence, Coding, Math

Standard Benchmarks

Academic and industry benchmarks

Frequently Asked Questions

What is Mixtral 8x7B Instruct good for?

Use Mixtral 8x7B Instruct for everyday tasks like writing, summarizing, brainstorming, and getting clear explanations.

How much does Mixtral 8x7B Instruct cost?

Pricing is based on usage. Current rates are $0.54/1M tokens for input and $0.60/1M tokens for output.

Can I try Mixtral 8x7B Instruct for free?

Yes. You can start a chat instantly and test the model before deciding on a plan.

Does Mixtral 8x7B Instruct support images or audio?

Mixtral 8x7B Instruct focuses on text-based tasks.

Benchmarks and pricing are sourced from Artificial Analysis where available. OpenRouter specs are used as a fallback.