All models
Mistral

Mistral AI

Voxtral Small 24B

mistral/voxtral-small

operationalZDRtextaudiostreaming

01·01

Overview

Modell-Beschreibung und Capability-Matrix.

About this model

Audio-Language-Modell von Mistral fuer Speech-to-Text und Audio-Verstehen.

Capabilities matrix

streaming
tools
json
vision
reasoning
embedding

02·02

Providers

1 EU-Provider mit Region, ZDR-Status und Preisen pro Million Tokens.

ProviderProvider Model IDRegionZDRInput €/MOutput €/MPriority
Scalewayvoxtral-small-24b-2507fr-par-1 ZDR€0.20€0.20100

03·03

Performance

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

Best Throughput

Scaleway157 tok/s

Lowest Latency

Scaleway1.46s

Scaleway

fr-par-1

Throughput

157tok/s

p50 · 24h
TTFT

221ms

p50 · 24h
E2E Latency

1.46s

p50 · 24h
Tool Err Rate

0.66%

last 7d

Note · Real metrics ship in Phase 4 once we log per-request TTFT + TPS into requests table aggregations.

04·04

Pricing

Pro Provider — relative Preisvisualisierung gegen den teuersten Anbieter dieses Modells.

Scaleway

ZDR
Input · per 1M tokens€0.20
Output · per 1M tokens€0.20
Regionfr-par-1

05·05

Uptime

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

Aggregated uptime

99.96%

Last 30 days · all providers combined

≥ 99 %95–99 %< 95 %

Scaleway

fr-par-1ZDR

99.96%

last 30 days

Recent incidents · last 30 days

Maintenance27 Apr 2026, 08:00 UTCScaleway8 min

Scheduled GPU driver upgrade

Rolling Upgrade auf einen neueren CUDA-Treiber, ein Pool nach dem anderen. Keine User-Impact.

06·06

API

Drop-in OpenAI-kompatibler Endpoint. Tausche nur die baseURL — der Rest bleibt.

use-voxtral-small.ts
curl https://cleverouter.eu/v1/chat/completions \
  -H "Authorization: Bearer $CLEVERROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistral/voxtral-small",
    "messages": [
      { "role": "user", "content": "Hallo aus der EU." }
    ]
  }'