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. Gemini 3.5 TranscribeGoogleRemove
  2. Perceptron Mk1.5PerceptronRemove
  3. S2.1 ProFish AudioRemove
  4. Voxtral Mini 3B 2507Mistral AIRemove

4 is the maximum. Remove one to add another.

gemini-3.5-transcribe vs perceptron-mk1.5 vs s2.1-pro vs voxtral-mini-3b-2507
AttributeGemini 3.5 Transcribegemini-3.5-transcribePerceptron Mk1.5perceptron-mk1.5S2.1 Pros2.1-proVoxtral Mini 3B 2507voxtral-mini-3b-2507
Pricing
Input$0 / 1M$0.15 / 1M$0 / 1M$0 / 1M
Output$0 / 1M$1.50 / 1M$0 / 1M$0 / 1M
Cache Write (5m)Not applicable$0.15 / 1MNot applicableNot applicable
Cache Write (1h)Not applicable$0.15 / 1MNot applicableNot applicable
Cache ReadNot applicable$0.15 / 1MNot applicableNot applicable
Web Search$0 / 1M$0 / 1M$0 / 1M$0 / 1M
Context
Max context98.3K36.9KN/AN/A
Max outputN/AN/AN/AN/A
Capabilities
VisionYesNoNoNo
Function CallingYesNoNoNo
JSON ModeNoNoNoNo
StreamingNoYesNoNo
Catalogue
ProviderGooglePerceptronFish AudioMistral AI
Categoryvoicechatvoicevoice
Charge typePay As You GoPay As You GoPay As You GoPay As You Go
Released2026-09-252026-09-252026-07-292026-08-13
Description
SummaryGoogle Gemini 3.5 Transcribe speech-to-text. Billed per input and output token.Perceptron 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.Mistral AI Voxtral Mini (3B) speech-to-text. Billed per second of audio.