GPT-6 Luna
OpenAI · Multimodal · Released Sep 2026
GPT-6 Luna is OpenAI's fast, cost-efficient model in the GPT-6 series, designed for high-volume and latency-sensitive applications with a 1.05M token context window.
- Strengths
- It prioritizes speed and efficiency for real-time inference on straightforward tasks without the overhead of more capable models.
- Best for
- Chat, classification, and lightweight agentic workloads where latency and throughput matter more than reasoning depth.
- Limitations
- It sits below GPT-6 Sol in capability and is not designed for complex reasoning or end-to-end work requiring deep analysis.
Input / 1M
$0.1
Output / 1M
$0.5
Cached input / 1M
$0.01
Context window
1.05M
Also billed
- Cache write
- $0.125 / 1M
Price history
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 22 Sep 2026 | $0.1 | $0.5 | $0.01 | Imported from OpenRouter | openrouter.ai |