mistralai

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

Input Cost
$0.54
per 1M tokens
Output Cost
$0.54
per 1M tokens
Context Window
32,768
tokens
Compare vs GPT-4o
Developer ID: mistralai/mixtral-8x7b-instruct

Related Models

mistralai
$2.00/1M

Mistral: Pixtral Large 2411

Pixtral Large is a 124B parameter, open-weight, multimodal model built on top of [Mistral ...

📝 131,072 ctx Compare →
mistralai
$0.40/1M

Mistral: Mistral Medium 3

Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver...

📝 131,072 ctx Compare →
mistralai
$0.20/1M

Mistral: Saba

Mistral Saba is a 24B-parameter language model specifically designed for the Middle East a...

📝 32,768 ctx Compare →