Skip to content
Apertis

Compare models

Put up to 4 models beside each other — token prices, context windows, capabilities and provider, from the same catalogue the model pages read.

  1. Voxtral Small 24B 2507 STTMistral AIRemove
  2. Qwen3 ASR 0.6BQwenRemove
  3. S1Fish AudioRemove
  4. Aura-2DeepgramRemove

4 is the maximum. Remove one to add another.

voxtral-small-24b-2507-stt vs qwen3-asr-0.6b vs s1 vs aura-2
AttributeVoxtral Small 24B 2507 STTvoxtral-small-24b-2507-sttQwen3 ASR 0.6Bqwen3-asr-0.6bS1s1Aura-2aura-2
Pricing
Input$0 / 1M$0 / 1M$0 / 1M$0 / 1M
Output$0 / 1M$0 / 1M$0 / 1M$0 / 1M
Cache Write (5m)Not applicableNot applicableNot applicableNot applicable
Cache Write (1h)Not applicableNot applicableNot applicableNot applicable
Cache ReadNot applicableNot applicableNot applicableNot applicable
Web Search$0 / 1M$0 / 1M$0 / 1M$0 / 1M
Context
Max contextN/AN/AN/AN/A
Max outputN/AN/AN/AN/A
Capabilities
VisionNoNoNoNo
Function CallingNoNoNoNo
JSON ModeNoNoNoNo
StreamingNoNoNoNo
Catalogue
ProviderMistral AIQwenFish AudioDeepgram
Categoryvoicevoicevoicevoice
Charge typePay As You GoPay As You GoPay As You GoPay As You Go
Released2026-08-132026-08-132026-07-292026-07-16
Description
SummaryMistral AI Voxtral Small (24B) speech-to-text. Billed per second of audio.Qwen3-ASR 0.6B speech-to-text. Billed per second of audio.Fish Audio S1 text-to-speech. Billed per UTF-8 byte of input text.Deepgram Aura-2 text-to-speech for real-time voice applications. Billed per input character.