GPT-6 Luna (batch)
OpenAI · Multimodal · Released Sep 2026
GPT-6 Luna (batch) is OpenAI's fast, cost-efficient model in the GPT-6 series, designed for high-volume and latency-sensitive workloads when batch processing is acceptable.
- Strengths
- Optimized for speed and efficiency with a 1.05M token context window, making it well-suited for rapid inference on straightforward tasks.
- Best for
- High-volume applications like chat, classification, and lightweight agentic workflows where batch processing latency is acceptable.
- Limitations
- Positioned below GPT-6 Luna Pro and the GPT-6 Astra models, so it lacks the advanced reasoning capabilities needed for complex or nuanced problem-solving.
Input / 1M
$0.05
Output / 1M
$0.25
Cached input / 1M
$0.005
Context window
1.05M
Also billed
- Cache write
- $0.0625 / 1M
Price history
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 22 Sep 2026 | $0.05 | $0.25 | $0.005 | Imported from OpenRouter | openrouter.ai |