As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/voxtral-small/

# Voxtral Small

Mistral AI, Voxtral family. Status: current. Type: multimodal model. Released: 2025-07. Training cutoff: not published.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Mistral API | `voxtral-small-2507` | https://api.mistral.ai/v1/chat/completions | https://docs.mistral.ai/models/overview |
| Hugging Face | `mistralai/Voxtral-Small-24B-2507` |  | https://huggingface.co/mistralai/Voxtral-Small-24B-2507 |

## Pricing

- Price not published.
- Last checked: 2026-09-29

## Specs

- Input: audio, text
- Output: text
- Context window: not published
- Max output: not published
- Open weights: yes
- Licence: apache-2.0

## What it has not seen

- No published training cutoff. Counted from its release (2025-07): at least 2,009 AI events since (464 major, 88 historic), as of 2026-11-13.
- Everything since June 2025: https://postcutoff.com/since/2025-06/

## What stands out

- Audio-understanding chat model: Mistral's first model with audio input for instruct use (Q&A, summarization, function calling from voice) on top of transcription. Source: https://docs.mistral.ai/models/overview

## Notes

Still listed as active (v25.07) on Mistral's models overview on 2026-09-29; its small siblings voxtral-mini-2507 and Voxtral Mini Transcribe 25.07 were retired 2026-05-31. Pricing and exact release day not re-verified (July 2025 launch).

Open 24B audio-in LLM from Mistral (July 2025).

Sources: https://docs.mistral.ai/models/overview · https://huggingface.co/mistralai/Voxtral-Small-24B-2507

Model page: https://postcutoff.com/m/voxtral-small/