GPT-5.6 Luna
OpenAI · Multimodal · Released Jul 2026
OpenAI's lightweight model in the GPT-5.6 series, designed for speed and efficiency with a 1.05M token context window.
- Strengths
- Fast inference and low resource consumption relative to other models in the GPT-5.6 lineup.
- Best for
- Latency-sensitive applications, high-volume inference, and tasks where raw reasoning capability is less critical than throughput.
- Limitations
- Positioned as the lightweight tier in the GPT-5.6 series; GPT-5.6 Terra offers better capability-to-efficiency balance, and GPT-5.6 Sol provides stronger reasoning for complex tasks.
Input / 1M
$0.2
Output / 1M
$1.20
Cached input / 1M
$0.02
Context window
1.05M
Also billed
- Cache write
- $0.25 / 1M
Price history
Input (solid)Output (dashed)
Price change
- 30d
- in — out —
- 90d
- in decreased 80.0% out decreased 80.0%
- 1y
- in decreased 80.0% out decreased 80.0%
- Since launch
- in decreased 80.0% out decreased 80.0%
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 17 Aug 2026 | $0.2 | $1.20 | $0.02 | Imported from OpenRouter | openrouter.ai |
| 30 Jul 2026 | $0.1 | $0.6 | $0.01 | Imported from OpenRouter | openrouter.ai |
| 27 Jul 2026 | $0.5 | $3.00 | $0.05 | Imported from OpenRouter | openrouter.ai |
| 10 Jul 2026 | $1.00 | $6.00 | $0.1 | Imported from OpenRouter | openrouter.ai |