Mixtral 8x7B Instruct
JSON →A mixture-of-experts LLM from Mistral AI with 8x7B parameters, offering high performance for text generation and reasoning.
Specs
context window 4K tokens
max output 4K tokens
input price $0.07 / 1M tokens
output price $0.28 / 1M tokens
Capabilities
open-weightsstreamingcode-generationreasoning
Dates
releasedDec 2023
knowledge cutoffSep 2023
Resources
API
full doc /v1/models/mixtral-8x7b-instruct