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. S2.1 ProFish AudioRemove
  2. Qwen3 ASR 0.6BQwenRemove
  3. Voxtral Mini 3B 2507Mistral AIRemove
  4. Perceptron Mk1.5PerceptronRemove

4 is the maximum. Remove one to add another.

s2.1-pro vs qwen3-asr-0.6b vs voxtral-mini-3b-2507 vs perceptron-mk1.5
AttributeS2.1 Pros2.1-proQwen3 ASR 0.6Bqwen3-asr-0.6bVoxtral Mini 3B 2507voxtral-mini-3b-2507Perceptron 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 S2.1 Pro text-to-speech. Billed per UTF-8 byte of input text.Qwen3-ASR 0.6B speech-to-text. Billed per second of audio.Mistral AI Voxtral Mini (3B) 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.