All AI models · LLM benchmarks · Methodology

Mistral

Voxtral Small 24B

Efficient Mistral model for fast chat, extraction, and production assistants

Model facts

Context window
33K tokens
Maximum output
32K tokens
Cheapest paid input
$0.0023 per 1M tokens
Cheapest paid output
$0.0023 per 1M tokens
Open weights
yes
Providers
2

Capabilities and modalities

tool calling, attachments, temperature control, open weights, text, audio.

Observed price history

  • 2026-08-24: $0.0023 input / $0.0023 output per 1M tokens

API providers

  • evroc — model id mistralai/Voxtral-Small-24B-2507; $0.0023 input / $0.0023 output per 1M tokens; provider documentation
  • GreenPT — model id voxtral-small-24b-2507; $0.228 input / $0.513 output per 1M tokens; provider documentation