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. Nova-3DeepgramRemove
  2. Aura-2DeepgramRemove
  3. GPT-6 LunaOpenAIRemove
  4. Perceptron Mk1.5PerceptronRemove

4 is the maximum. Remove one to add another.

nova-3 vs aura-2 vs gpt-6-luna vs perceptron-mk1.5
AttributeNova-3nova-3Aura-2aura-2GPT-6 Lunagpt-6-lunaPerceptron Mk1.5perceptron-mk1.5
Pricing
Input$0 / 1M$0 / 1M$0.10 / 1M$0.15 / 1M
Output$0 / 1M$0 / 1M$0.50 / 1M$1.50 / 1M
Cache Write (5m)Not applicableNot applicable$0.10 / 1M$0.15 / 1M
Cache Write (1h)Not applicableNot applicable$0.10 / 1M$0.15 / 1M
Cache ReadNot applicableNot applicable$0.10 / 1M$0.15 / 1M
Web Search$0 / 1M$0 / 1M$0 / 1M$0 / 1M
Context
Max contextN/AN/A1.1M36.9K
Max outputN/AN/AN/AN/A
Capabilities
VisionNoNoYesNo
Function CallingNoNoYesNo
JSON ModeNoNoYesNo
StreamingNoNoYesYes
Catalogue
ProviderDeepgramDeepgramOpenAIPerceptron
Categoryvoicevoicechatchat
Charge typePay As You GoPay As You GoPay As You GoPay As You Go
Released2026-07-152026-07-16—2026-09-25
Description
SummaryDeepgram Nova-3 speech-to-text. Billed per second of audio.Deepgram Aura-2 text-to-speech for real-time voice applications. Billed per input character.GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, optimized for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks. It combines low-cost, responsive inference with the GPT-6 family’s improvements in factual reliability and clear, concise communication. At higher reasoning effort, GPT-6 Luna can also handle complex software engineering and computer-use workflows that previously required a Sol-tier model, making it a versatile choice for scalable production applications that need to balance speed, cost, and capability.Perceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token.