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. Perceptron Mk1.5PerceptronRemove
  3. GPT-6 AstraOpenAIRemove
  4. Qwen3 ASR 1.7BQwenRemove

4 is the maximum. Remove one to add another.

mai-transcribe-2 vs perceptron-mk1.5 vs gpt-6-astra vs qwen3-asr-1.7b
AttributeMAI-Transcribe 2mai-transcribe-2Perceptron Mk1.5perceptron-mk1.5GPT-6 Astragpt-6-astraQwen3 ASR 1.7Bqwen3-asr-1.7b
Pricing
Input$0 / 1M$0.15 / 1M$10.00 / 1M$0 / 1M
Output$0 / 1M$1.50 / 1M$50.00 / 1M$0 / 1M
Cache Write (5m)Not applicable$0.15 / 1M$10.00 / 1MNot applicable
Cache Write (1h)Not applicable$0.15 / 1M$10.00 / 1MNot applicable
Cache ReadNot applicable$0.15 / 1M$10.00 / 1MNot applicable
Web Search$0 / 1M$0 / 1M$0 / 1M$0 / 1M
Context
Max contextN/A36.9K1MN/A
Max outputN/AN/AN/AN/A
Capabilities
VisionNoNoYesNo
Function CallingNoNoYesNo
JSON ModeNoNoYesNo
StreamingNoYesYesNo
Catalogue
ProviderMicrosoftPerceptronOpenAIQwen
Categoryvoicechatchatvoice
Charge typePay As You GoPay As You GoPay As You GoPay As You Go
Released2026-09-032026-09-25—2026-08-13
Description
SummaryMicrosoft MAI-Transcribe-2 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.GPT-6 Astra is OpenAI's flagship model for demanding end-to-end professional work, designed for advanced analysis, software engineering, deep research, scientific tasks, and document creation. It is particularly strong in long-horizon agentic workflows, including tasks that require sustained reasoning, tool orchestration, and computer and browser use, making it well suited for complex autonomous workflows and production-grade knowledge work.Qwen3-ASR 1.7B speech-to-text. Billed per second of audio.