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. MAI-Transcribe 2MicrosoftRemove
  2. S2.1 ProFish AudioRemove
  3. Voxtral Mini 3B 2507Mistral AIRemove
  4. Perceptron Mk1.5PerceptronRemove

4 is the maximum. Remove one to add another.

mai-transcribe-2 vs s2.1-pro vs voxtral-mini-3b-2507 vs perceptron-mk1.5
AttributeMAI-Transcribe 2mai-transcribe-2S2.1 Pros2.1-proVoxtral Mini 3B 2507voxtral-mini-3b-2507Perceptron Mk1.5perceptron-mk1.5
Pricing
Input$0 / 1M$0 / 1M$0 / 1M$0.15 / 1M
Output$0 / 1M$0 / 1M$0 / 1M$1.50 / 1M
Cache Write (5m)Not applicableNot applicableNot applicable$0.15 / 1M
Cache Write (1h)Not applicableNot applicableNot applicable$0.15 / 1M
Cache ReadNot applicableNot applicableNot applicable$0.15 / 1M
Web Search$0 / 1M$0 / 1M$0 / 1M$0 / 1M
Context
Max contextN/AN/AN/A36.9K
Max outputN/AN/AN/AN/A
Capabilities
VisionNoNoNoNo
Function CallingNoNoNoNo
JSON ModeNoNoNoNo
StreamingNoNoNoYes
Catalogue
ProviderMicrosoftFish AudioMistral AIPerceptron
Categoryvoicevoicevoicechat
Charge typePay As You GoPay As You GoPay As You GoPay As You Go
Released2026-09-032026-07-292026-08-132026-09-25
Description
SummaryMicrosoft MAI-Transcribe-2 speech-to-text. Billed per second of audio.Fish 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.