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. Voxtral Mini 3B 2507Mistral AIRemove
  3. Perceptron Mk1.5PerceptronRemove
  4. Qwen3 ASR 1.7BQwenRemove

4 is the maximum. Remove one to add another.

s2.1-pro vs voxtral-mini-3b-2507 vs perceptron-mk1.5 vs qwen3-asr-1.7b
AttributeS2.1 Pros2.1-proVoxtral Mini 3B 2507voxtral-mini-3b-2507Perceptron Mk1.5perceptron-mk1.5Qwen3 ASR 1.7Bqwen3-asr-1.7b
Pricing
Input$0 / 1M$0 / 1M$0.15 / 1M$0 / 1M
Output$0 / 1M$0 / 1M$1.50 / 1M$0 / 1M
Cache Write (5m)Not applicableNot applicable$0.15 / 1MNot applicable
Cache Write (1h)Not applicableNot applicable$0.15 / 1MNot applicable
Cache ReadNot applicableNot applicable$0.15 / 1MNot applicable
Web Search$0 / 1M$0 / 1M$0 / 1M$0 / 1M
Context
Max contextN/AN/A36.9KN/A
Max outputN/AN/AN/AN/A
Capabilities
VisionNoNoNoNo
Function CallingNoNoNoNo
JSON ModeNoNoNoNo
StreamingNoNoYesNo
Catalogue
ProviderFish AudioMistral AIPerceptronQwen
Categoryvoicevoicechatvoice
Charge typePay As You GoPay As You GoPay As You GoPay As You Go
Released2026-07-292026-08-132026-09-252026-08-13
Description
SummaryFish Audio S2.1 Pro text-to-speech. Billed per UTF-8 byte of input text.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.Qwen3-ASR 1.7B speech-to-text. Billed per second of audio.