GPT-5.6 Luna
Overview
GPT-5.6 Luna is the cost-effective model in the GPT-5.6 series, keeping strong reasoning and coding ability while significantly lowering cost. It is designed for cost-sensitive, high-volume production workloads. It accepts text and image inputs and offers a 1.05M-token context window.
Key Features
- Cost First: Lowest price in the series, suited to large-scale calls
- Long Context: 1.05M-token context
- Multimodal Input: Supports text and image inputs, and can parse PDF documents
Best Use Cases
- High-Frequency Light Tasks: Classification, extraction, and summarization at scale
- Real-Time Interaction: Online scenarios sensitive to both latency and cost
- Pre-Filtering and Preprocessing: The lightweight first stage in a multi-model pipeline
Specifications
| Item | Detail |
|---|---|
| Platform model ID | gpt-5.6-luna |
| Context window | 1,050,000 tokens |
| Input modalities | Text, image, PDF |
| Reasoning / thinking | Supported |
| First released (market) | 2026-07-09 |
| Live pricing | See the model marketplace |
Capabilities and Limitations
| Capability | Description |
|---|---|
| Reasoning | Above average. Good for light-to-moderate tasks; use Sol for the hardest work |
| Multimodal | Supports text, image, and PDF input (no audio/video) |
| Context Window | 1,050,000 tokens |
| Speed | Fast. Cost-effective positioning |
Last updated on