Voxtral Small 24B 2507

Mistral· released 30 Oct 2025

mistralai/voxtral-small-24b-2507

Input / 1M tokens: $0.1
Output / 1M tokens: $0.3

Context window33K tokens

Longest answer: 26K tokens

reads textreads audioreads fileopen weightstool calling

About

Voxtral Small 24B 2507 is Mistral’s 24-billion-parameter model for text and audio-oriented workloads. It adds audio input capabilities to the Mistral Small 3 line while retaining text performance, with uses including speech transcription, translation, and audio understanding. The model accepts text, audio, and file inputs, and returns text outputs. It lists tools support and has open weights with Hugging Face identifier mistralai/Voxtral-Small-24B-2507. Its context window is 32,768 tokens, with a maximum output of 26,214 tokens. Released on 2025-10-30, it is in the mistralai family and is available through the listed OpenRouter page. Pricing is USD 0.10 per 1M input tokens and USD 0.30 per 1M output tokens. These details make it suitable for applications that combine spoken or uploaded content with language generation.

Who it is for

It suits teams processing speech, audio files, transcripts, or multilingual audio content alongside text. Open weights and tool support may fit developers integrating it into broader workflows.

What is good

Accepts text, audio, and file inputs
Supports speech transcription
Supports translation and audio understanding
Open weights are available
Tools are listed

What to know first

32,768-token context window
Maximum output is 26,214 tokens
Output pricing is USD 0.30 per 1M tokens

Verdict

Voxtral Small 24B 2507 is aimed at applications where audio understanding and text generation share one model. Its context and output limits should be checked against long-document or extended-conversation requirements.

Details

Lab: Mistralopenrouter.ai · 3 Oct 2026
Context: 33Kopenrouter.ai · 3 Oct 2026
Input price: $0.1 / 1Mopenrouter.ai · 3 Oct 2026
Output price: $0.3 / 1Mopenrouter.ai · 3 Oct 2026
Max output: 26,214 tokensopenrouter.ai · 3 Oct 2026
Inputs: text, audio, fileopenrouter.ai · 3 Oct 2026
Open weights: Yesopenrouter.ai · 3 Oct 2026

More longest-context models

See the list

Auto Router ctx2,000KinVaries by model routed tooutVaries by model routed to openrouter Auto Router (Beta) ctx2,000KinVaries by model routed tooutVaries by model routed to openrouter Grok 4.20 ctx2,000Kin$1.25 / 1Mout$2.5 / 1M SpaceXAI Grok 4.20 Multi-Agent ctx2,000Kin$1.25 / 1Mout$2.5 / 1M SpaceXAI Pareto Code Router ctx2,000KinVaries by model routed tooutVaries by model routed to openrouter Llama 4 Scout ctx1,311Kin$0.1 / 1Mout$0.3 / 1M Meta

Listed on Inferse

Longest-Context Models in 2026466 listed
Newest Models in 2026466 listed
Cheapest Language Models in 2026437 listed
Models with Tool Calling in 2026395 listed
Open-Weight Models in 2026178 listed
Mistral Models: Pricing per 1M Tokens and Context (2026)23 listed

Sources

openrouter.ai/mistralai/voxtral-small-24b-2507· checked 3 Oct 2026