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. Nova-3DeepgramRemove
  3. Qwen3 ASR 0.6BQwenRemove
  4. Voxtral Mini 3B 2507Mistral AIRemove

4 is the maximum. Remove one to add another.

perceptron-mk1.5 vs nova-3 vs qwen3-asr-0.6b vs voxtral-mini-3b-2507
AttributePerceptron Mk1.5perceptron-mk1.5Nova-3nova-3Qwen3 ASR 0.6Bqwen3-asr-0.6bVoxtral 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
ProviderPerceptronDeepgramQwenMistral AI
Categorychatvoicevoicevoice
Charge typePay As You GoPay As You GoPay As You GoPay As You Go
Released2026-09-252026-07-152026-08-132026-08-13
Description
SummaryPerceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token.Deepgram Nova-3 speech-to-text. Billed per second of audio.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.