All AI models · LLM benchmarks · Methodology

Mistral

Mixtral 8x22B

Mistral model for multilingual chat, reasoning, and tool-assisted workflows

Model facts

Context window
66K tokens
Maximum output
52K tokens
Cheapest paid input
$2 per 1M tokens
Cheapest paid output
$6 per 1M tokens
Open weights
yes
Providers
5

Capabilities and modalities

tool calling, structured output, attachments, temperature control, open weights, text, pdf.

Artificial Analysis benchmarks

Compare this model on the full LLM benchmark leaderboard.

ConfigurationAAICodingMathOutput tokens/s
default4.0not measurednot measurednot measured

Observed price history

  • 2026-08-24: $2 input / $6 output per 1M tokens

API providers

  • Nvidia — model id mistralai/mixtral-8x22b-instruct; free input / free output per 1M tokens; provider documentation
  • Kilo Gateway — model id mistralai/mixtral-8x22b-instruct; $2 input / $6 output per 1M tokens; provider documentation
  • Mistral — model id open-mixtral-8x22b; $2 input / $6 output per 1M tokens; provider documentation
  • NanoGPT — model id mistralai/mixtral-8x22b-instruct-v0.1; $2 input / $6 output per 1M tokens; provider documentation
  • OpenRouter — model id mistralai/mixtral-8x22b-instruct; $2 input / $6 output per 1M tokens; provider documentation