Skip to content

Mixtral 8x7B

Mistral AILanguage modeling/generationQuestion answeringQuantitative reasoningTranslationOpen weights

Developed by Mistral AI in 2023, Mixtral 8x7B is a language modeling/generation model with 46700000000.0 parameters with openly available weights.

About Mixtral 8x7B

Today, the team is proud to release Mixtral 8x7B, a high-quality sparse mixture of experts model (SMoE) with open weights. Licensed under Apache 2.0. Mixtral outperforms Llama 2 70B on most benchmarks with 6x faster inference. It is the strongest ope

LLM pricing & performance

Full LLM page →

Mixtral 8x7B is available via API — live cost, context, and benchmark data:

Input / 1M
$0.70
Output / 1M
$0.70
Context
32K
Tokens/sec

Details

Provider
Mistral AI
Task
Language modeling/generation,Question answering,Quantitative reasoning,Translation
Parameters
46700000000.0
Released
2023-12-11
Open weights
Yes
View model source

Explore

FAQ