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

4 is the maximum. Remove one to add another.

qwen3-asr-0.6b vs s2.1-pro vs perceptron-mk1.5 vs voxtral-mini-3b-2507
AttributeQwen3 ASR 0.6Bqwen3-asr-0.6bS2.1 Pros2.1-proPerceptron Mk1.5perceptron-mk1.5Voxtral Mini 3B 2507voxtral-mini-3b-2507
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
ProviderQwenFish AudioPerceptronMistral AI
Categoryvoicevoicechatvoice
Charge typePay As You GoPay As You GoPay As You GoPay As You Go
Released2026-08-132026-07-292026-09-252026-08-13
Description
SummaryQwen3-ASR 0.6B speech-to-text. Billed per second of audio.Fish Audio S2.1 Pro text-to-speech. Billed per UTF-8 byte of input text.Perceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token.Mistral AI Voxtral Mini (3B) speech-to-text. Billed per second of audio.