Mistral·Mistral AI

Voxtral Small 24b 2507

mistral/voxtral-small-24b-2507

1 provider · cheapest €0.20/M via Scaleway

Try in Playground Copy code Docs

operationalZDRaudio

01·01

Overview

Modell-Beschreibung und Capability-Matrix.

About this model

Keine Beschreibung verfügbar. Modelle werden über das Gateway-Catalog gepflegt und automatisch synchronisiert.

Capabilities matrix

streaming—

tools—

json—

vision—

reasoning—

embedding—

02·02

Providers

1 EU-Provider mit Pricing, Throughput, Latency und Uptime — sortierbar. Pin-Button kopiert den X-CleverRouter-Provider-Header.

	Provider Model ID	Context	ZDR						Pin
Scaleway	voxtral-small-24b-2507	fr-par-1	ZDR	€0.20	€0.20	—	—	100.00%

Pin kopiert X-CleverRouter-Provider-Header. Setze ihn an deinen Request, um Routing zu fixieren.

03·03

Code samples

Drop-in OpenAI-kompatibel — drehe an System-Prompt, Temperatur, Max-Tokens und Streaming, die Snippets aktualisieren sich live.

Notes

use-voxtral-small-24b-2507.ts

curl https://cleverouter.eu/v1/audio/transcriptions \
  -H "Authorization: Bearer $CLEVERROUTER_API_KEY" \
  -F file=@./input.mp3 \
  -F model=mistral/voxtral-small-24b-2507

04·04

Performance

Throughput, TTFT, E2E-Latency und Tool-Error-Rate — pro Provider, p50 über 24h.

No performance data for this model yet. Once the first requests roll through, p50/p95 latency, throughput and error rate per provider will appear here.

Scaleway

fr-par-1

Throughput

—tok/s

p50 · 24h

TTFT

—ms

p50 · 24h

E2E Latency

—s

p50 · 24h

Tool Err Rate

—%

last 7d

Source · Aggregiert aus der requests Tabelle, letzte 24 h. p50/p95 via Postgres-Native PERCENTILE_CONT.

05·05

Uptime

30-Tage-Heatmap pro Provider, aggregierte Verfügbarkeit und Incident-Historie.

Aggregated uptime

100.00%

Last 30 days · all providers combined

≥ 99 %95–99 %< 95 %no data

Scaleway

fr-par-1ZDR

100.00%

last 30 days

Recent incidents · last 30 days

Keine Incidents in den letzten 30 Tagen.

06·06

Apps & use cases

What you can typically build with Mistral audio models — ready-made snippets to get you started.

Transcription

Calls, Meetings oder Voice-Notes mit hoher Genauigkeit transkribieren — Whisper-kompatible API.

const file = await fs.readFile('./call.mp3');
const res = await client.audio.transcriptions.create({
  model: 'mistral/voxtral-small-24b-2507',
  file,
});

Voice-first bots
Combine STT + LLM + TTS für Voicebots am Telefon oder im Browser-Voice-Interface.