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. Aura-2DeepgramRemove
  3. GPT-6 AstraOpenAIRemove
  4. Voxtral Mini 3B 2507Mistral AIRemove

4 is the maximum. Remove one to add another.

perceptron-mk1.5 vs aura-2 vs gpt-6-astra vs voxtral-mini-3b-2507
AttributePerceptron Mk1.5perceptron-mk1.5Aura-2aura-2GPT-6 Astragpt-6-astraVoxtral Mini 3B 2507voxtral-mini-3b-2507
Pricing
Input$0.15 / 1M$0 / 1M$10.00 / 1M$0 / 1M
Output$1.50 / 1M$0 / 1M$50.00 / 1M$0 / 1M
Cache Write (5m)$0.15 / 1MNot applicable$10.00 / 1MNot applicable
Cache Write (1h)$0.15 / 1MNot applicable$10.00 / 1MNot applicable
Cache Read$0.15 / 1MNot applicable$10.00 / 1MNot applicable
Web Search$0 / 1M$0 / 1M$0 / 1M$0 / 1M
Context
Max context36.9KN/A1MN/A
Max outputN/AN/AN/AN/A
Capabilities
VisionNoNoYesNo
Function CallingNoNoYesNo
JSON ModeNoNoYesNo
StreamingYesNoYesNo
Catalogue
ProviderPerceptronDeepgramOpenAIMistral AI
Categorychatvoicechatvoice
Charge typePay As You GoPay As You GoPay As You GoPay As You Go
Released2026-09-252026-07-16—2026-08-13
Description
SummaryPerceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token.Deepgram Aura-2 text-to-speech for real-time voice applications. Billed per input character.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.Mistral AI Voxtral Mini (3B) speech-to-text. Billed per second of audio.