All AI models · LLM benchmarks · Methodology

Mistral

Voxtral Small 24B 2507

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

Model facts

Context window
33K tokens
Maximum output
26K tokens
Cheapest paid input
$0.1 per 1M tokens
Cheapest paid output
$0.3 per 1M tokens
Open weights
yes
Providers
3

Capabilities and modalities

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

Observed price history

  • 2026-08-24: $0.1 input / $0.3 output per 1M tokens

API providers

  • OpenRouter — model id mistralai/voxtral-small-24b-2507; $0.1 input / $0.3 output per 1M tokens; provider documentation
  • Kilo Gateway (Mistral) — model id mistralai/voxtral-small-24b-2507; $0.1 input / $0.3 output per 1M tokens; provider documentation
  • Amazon Bedrock — model id mistral.voxtral-small-24b-2507; $0.15 input / $0.35 output per 1M tokens; provider documentation