Mistral 7B Instruct
JSON →A 7-billion parameter instruction-tuned LLM from Mistral AI optimized for efficient 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
releasedSep 2023
knowledge cutoffSep 2023
Resources
API
full doc /v1/models/mistral-7b-instruct