All AI models · LLM benchmarks · Methodology

mistral-7b-instruct-v0.2

Mistral 7B Instruct is a compact, 7B parameter model optimized for fast and efficient text and code generation with a 32K token context window.

Model facts

Context window
32K tokens
Maximum output
8K tokens
Cheapest paid input
$0.159 per 1M tokens
Cheapest paid output
$0.219 per 1M tokens
Open weights
no
Providers
1

Capabilities and modalities

attachments, text, pdf.

Observed price history

  • 2026-08-24: $0.159 input / $0.219 output per 1M tokens

API providers

  • Cortecs — model id mistral-7b-instruct-v0.2; $0.159 input / $0.219 output per 1M tokens; provider documentation