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. Speech 2.8 TurboMiniMaxRemove
  2. Universal-3.5 ProAssemblyAIRemove
  3. Perceptron Mk1.5PerceptronRemove
speech-2.8-turbo vs universal-3-5-pro vs perceptron-mk1.5
AttributeSpeech 2.8 Turbospeech-2.8-turboUniversal-3.5 Prouniversal-3-5-proPerceptron 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
ProviderMiniMaxAssemblyAIPerceptron
Categoryvoicevoicechat
Charge typePay As You GoPay As You GoPay As You Go
Released2026-07-162026-09-222026-09-25
Description
SummaryMiniMax Speech 2.8 Turbo text-to-speech. Billed per input character; each Chinese (Han) character counts as 2.AssemblyAI Universal-3.5 Pro 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.