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. Voxtral Small 24B 2507 STTMistral AIRemove
  3. Perceptron Mk1.5PerceptronRemove
qwen3-asr-0.6b vs voxtral-small-24b-2507-stt vs perceptron-mk1.5
AttributeQwen3 ASR 0.6Bqwen3-asr-0.6bVoxtral Small 24B 2507 STTvoxtral-small-24b-2507-sttPerceptron Mk1.5perceptron-mk1.5
Pricing
Input$0 / 1M$0 / 1M$0.15 / 1M
Output$0 / 1M$0 / 1M$1.50 / 1M
Cache Write (5m)Not applicableNot applicable$0.15 / 1M
Cache Write (1h)Not applicableNot applicable$0.15 / 1M
Cache ReadNot applicableNot applicable$0.15 / 1M
Web Search$0 / 1M$0 / 1M$0 / 1M
Context
Max contextN/AN/A36.9K
Max outputN/AN/AN/A
Capabilities
VisionNoNoNo
Function CallingNoNoNo
JSON ModeNoNoNo
StreamingNoNoYes
Catalogue
ProviderQwenMistral AIPerceptron
Categoryvoicevoicechat
Charge typePay As You GoPay As You GoPay As You Go
Released2026-08-132026-08-132026-09-25
Description
SummaryQwen3-ASR 0.6B 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.