24B
Parameters
Dense Transformer
AIVory Smart Inference · Voxtral
Open WeightVoxtral Small 24B - multilingual speech, understood.
Mistral's 24B voice model. Understands speech in dozens of languages. Goes beyond transcription to actually process what was said.
At a glance
Voxtral Small 24B via Smart Inference.
Routed to the cheapest live provider on every request. Same model, lower bill.
32K
Context window
tokens per request
—
Cheapest input price
per 1M tokens via Smart Inference
—%
Cheaper
vs the priciest endpoint for the same model
Pricing
Voxtral Small 24B: price comparison.
Our cheapest routed price vs what you'd pay elsewhere.
Prices in USD per 1M input tokens · updated live from the router
Quick start
Use Voxtral Small 24B in three lines.
OpenAI-compatible. Swap your base_url, keep everything else.
from openai import OpenAI
client = OpenAI(
base_url="https://smart.aivory.net/v1",
api_key="sk-aivory-...",
)
resp = client.chat.completions.create(
model="voxtral-small-24b-2507",
messages=[{"role": "user", "content": "Ship it."}],
)
print(resp.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://smart.aivory.net/v1",
apiKey: process.env.AIVORY_API_KEY,
});
const resp = await client.chat.completions.create({
model: "voxtral-small-24b-2507",
messages: [{ role: "user", content: "Ship it." }],
});
console.log(resp.choices[0].message.content);curl https://smart.aivory.net/v1/chat/completions \
-H "Authorization: Bearer $AIVORY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "voxtral-small-24b-2507",
"messages": [{"role": "user", "content": "Ship it."}]
}'That's the whole migration. Get early access and try it →
Use cases
What Voxtral Small 24B is great at.
-
Multilingual Voice Support
Accept voice input in French, German, Spanish, Japanese, Mandarin, and dozens more languages. Voxtral Small handles the language detection, transcription, and understanding in one call. No per-language model switching needed.
-
Meeting Summarization
Send audio segments from a meeting recording. Voxtral Small understands context, identifies topics, and generates structured summaries. Use function calling to push action items into your project tracker.
-
Voice Analytics
Process call center recordings. Extract customer intent, sentiment, and key phrases. The 24B model captures nuance that Voxtral Mini's 3B model misses, including sarcasm, hesitation, and implied meaning.
FAQ
Common questions.
What does Voxtral Small 24B cost on AIVory?
Priced in the same range as other 24B models. The voice capability doesn't add a premium to the per-token cost. Check the live table above for current rates.
Voxtral Small vs Voxtral Mini - when to use each?
Mini (3B) handles simple voice commands and short transcription. Small (24B) understands complex conversations, handles more languages, and captures nuance. Use Mini for cost, Small for quality.
What audio formats are supported?
Base64-encoded audio in the messages array. Standard formats (WAV, MP3, M4A) work. Check the API reference for specifics on format and size limits.
Can Voxtral Small handle accented speech?
Better than Voxtral Mini, thanks to the larger model and broader training data. Heavy accents and noisy audio still benefit from preprocessing. For critical accuracy, test with your actual audio samples before deploying.
Start using Voxtral Small 24B. Today.
Swap your base_url, keep shipping.
The router is live. Credits from $10, no subscription, no commitment.