All AI models · LLM benchmarks · Methodology

Mistral

Mistral Small 24B

Mistral Small 24B hosted by IONOS in Berlin, Germany. Zero data retention.

Model facts

Context window
33K tokens
Maximum output
8K tokens
Cheapest paid input
$0.116 per 1M tokens
Cheapest paid output
$0.346 per 1M tokens
Open weights
yes
Providers
1

Capabilities and modalities

tool calling, open weights, text.

Observed price history

  • 2026-09-11: $0.116 input / $0.346 output per 1M tokens

API providers

  • NanoGPT — model id mistralai/mistral-small-24b-instruct-2501; $0.116 input / $0.346 output per 1M tokens; provider documentation