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.
- Perceptron Mk1.5PerceptronRemove
- GPT-6 Luna ProOpenAIRemove
- Aura-2DeepgramRemove
- GPT-6 LunaOpenAIRemove
4 is the maximum. Remove one to add another.
| Attribute | Perceptron Mk1.5perceptron-mk1.5 | GPT-6 Luna Progpt-6-luna-pro | Aura-2aura-2 | GPT-6 Lunagpt-6-luna |
|---|---|---|---|---|
| Pricing | ||||
| Input | $0.15 / 1M | $0.10 / 1M | $0 / 1M | $0.10 / 1M |
| Output | $1.50 / 1M | $0.50 / 1M | $0 / 1M | $0.50 / 1M |
| Cache Write (5m) | $0.15 / 1M | $0.10 / 1M | Not applicable | $0.10 / 1M |
| Cache Write (1h) | $0.15 / 1M | $0.10 / 1M | Not applicable | $0.10 / 1M |
| Cache Read | $0.15 / 1M | $0.10 / 1M | Not applicable | $0.10 / 1M |
| Web Search | $0 / 1M | $0 / 1M | $0 / 1M | $0 / 1M |
| Context | ||||
| Max context | 36.9K | 1.1M | N/A | 1.1M |
| Max output | N/A | N/A | N/A | N/A |
| Capabilities | ||||
| Vision | No | Yes | No | Yes |
| Function Calling | No | Yes | No | Yes |
| JSON Mode | No | Yes | No | Yes |
| Streaming | Yes | Yes | No | Yes |
| Catalogue | ||||
| Provider | Perceptron | OpenAI | Deepgram | OpenAI |
| Category | chat | chat | voice | chat |
| Charge type | Pay As You Go | Pay As You Go | Pay As You Go | Pay As You Go |
| Released | 2026-09-25 | — | 2026-07-16 | — |
| Description | ||||
| Summary | Perceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token. | GPT-6 Luna Pro uses the same underlying model as GPT-6 Luna, but runs with reasoning.mode set to pro for higher-quality responses on complex tasks. It combines Luna's speed and cost efficiency with deeper reasoning and more reliable multi-step execution, making it well suited for advanced coding, computer use, and agentic workflows where higher solution quality is needed without moving to a larger GPT-6 tier. | 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. |