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. Aura-2DeepgramRemove
  4. S1Fish AudioRemove

4 is the maximum. Remove one to add another.

voxtral-small-24b-2507-stt vs qwen3-asr-0.6b vs aura-2 vs s1
AttributeVoxtral Small 24B 2507 STTvoxtral-small-24b-2507-sttQwen3 ASR 0.6Bqwen3-asr-0.6bAura-2aura-2S1s1
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 AIQwenDeepgramFish Audio
Categoryvoicevoicevoicevoice
Charge typePay As You GoPay As You GoPay As You GoPay As You Go
Released2026-08-132026-08-132026-07-162026-07-29
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.Deepgram Aura-2 text-to-speech for real-time voice applications. Billed per input character.Fish Audio S1 text-to-speech. Billed per UTF-8 byte of input text.