Mistral
Voxtral Small (latest)
Instruct model with native audio input for speech understanding and tool use
Model facts
- Context window
- 32K tokens
- Maximum output
- 32K 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.
Observed price history
- 2026-08-24: $0.1 input / $0.3 output per 1M tokens
API providers
- LLMTR — model id mistral/voxtral-small-latest; $0.1 input / $0.3 output per 1M tokens; provider documentation
- Mistral — model id voxtral-small-latest; $0.1 input / $0.3 output per 1M tokens; provider documentation
- Eden AI — model id mistral/voxtral-small-latest; $0.1 input / $0.4 output per 1M tokens; provider documentation