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. Perceptron Mk1.5PerceptronRemove
  2. S2.1 ProFish AudioRemove
  3. Qwen3 ASR 1.7BQwenRemove
  4. Voxtral Mini 3B 2507Mistral AIRemove

4 is the maximum. Remove one to add another.

perceptron-mk1.5 vs s2.1-pro vs qwen3-asr-1.7b vs voxtral-mini-3b-2507
AttributePerceptron Mk1.5perceptron-mk1.5S2.1 Pros2.1-proQwen3 ASR 1.7Bqwen3-asr-1.7bVoxtral Mini 3B 2507voxtral-mini-3b-2507
Pricing
Input$0.15 / 1M$0 / 1M$0 / 1M$0 / 1M
Output$1.50 / 1M$0 / 1M$0 / 1M$0 / 1M
Cache Write (5m)$0.15 / 1MNot applicableNot applicableNot applicable
Cache Write (1h)$0.15 / 1MNot applicableNot applicableNot applicable
Cache Read$0.15 / 1MNot applicableNot applicableNot applicable
Web Search$0 / 1M$0 / 1M$0 / 1M$0 / 1M
Context
Max context36.9KN/AN/AN/A
Max outputN/AN/AN/AN/A
Capabilities
VisionNoNoNoNo
Function CallingNoNoNoNo
JSON ModeNoNoNoNo
StreamingYesNoNoNo
Catalogue
ProviderPerceptronFish AudioQwenMistral AI
Categorychatvoicevoicevoice
Charge typePay As You GoPay As You GoPay As You GoPay As You Go
Released2026-09-252026-07-292026-08-132026-08-13
Description
SummaryPerceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token.Fish Audio S2.1 Pro 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 Mini (3B) speech-to-text. Billed per second of audio.