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. S1Fish AudioRemove
  2. Qwen3 ASR 1.7BQwenRemove
  3. Voxtral Small 24B 2507 STTMistral AIRemove
  4. Perceptron Mk1.5PerceptronRemove

4 is the maximum. Remove one to add another.

s1 vs qwen3-asr-1.7b vs voxtral-small-24b-2507-stt vs perceptron-mk1.5
AttributeS1s1Qwen3 ASR 1.7Bqwen3-asr-1.7bVoxtral Small 24B 2507 STTvoxtral-small-24b-2507-sttPerceptron Mk1.5perceptron-mk1.5
Pricing
Input$0 / 1M$0 / 1M$0 / 1M$0.15 / 1M
Output$0 / 1M$0 / 1M$0 / 1M$1.50 / 1M
Cache Write (5m)Not applicableNot applicableNot applicable$0.15 / 1M
Cache Write (1h)Not applicableNot applicableNot applicable$0.15 / 1M
Cache ReadNot applicableNot applicableNot applicable$0.15 / 1M
Web Search$0 / 1M$0 / 1M$0 / 1M$0 / 1M
Context
Max contextN/AN/AN/A36.9K
Max outputN/AN/AN/AN/A
Capabilities
VisionNoNoNoNo
Function CallingNoNoNoNo
JSON ModeNoNoNoNo
StreamingNoNoNoYes
Catalogue
ProviderFish AudioQwenMistral AIPerceptron
Categoryvoicevoicevoicechat
Charge typePay As You GoPay As You GoPay As You GoPay As You Go
Released2026-07-292026-08-132026-08-132026-09-25
Description
SummaryFish Audio S1 text-to-speech. Billed per UTF-8 byte of input text.Qwen3-ASR 1.7B speech-to-text. Billed per second of audio.Mistral AI Voxtral Small (24B) speech-to-text. Billed per second of audio.Perceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token.