AI Hub
All models
LLM

Mistral 7B Instruct

Mistral AI

Updated May 22, 2026 · Benchmarks via Artificial Analysis, specs & pricing via OpenRouter · Methodology · Report an error

Specifications

Type
LLM
Released
September 27, 2023
Output speed
90 tok/s
Latency (TTFT)
0.39s
API pricing
$0.20 in · $0.20 out / 1M tokens

Benchmarks

Reasoning

Coding

Math

Compare Mistral 7B Instruct with

See all Mistral 7B Instruct alternatives →