- Context window
- 1.1M
- Input
- Image · Text
- Output
- Text
- Released
- 2026-07-09
- Max output
- 128K
- Knowledge cutoff
- 2026-02-16
- Weights
- Closed
- Capabilities
- Attachments, Reasoning, Structured, Tool call
IN
$0.20 – $0.40
USD / 1,000,000 token
$0.20 · prompt: <=272000 input tokens
$0.40 · prompt: >272000 input tokens
Cache read
$0.02 – $0.04
USD / 1,000,000 token
$0.02 · prompt: <=272000 input tokens
$0.04 · prompt: >272000 input tokens
Cache write
$0.25 – $1.00
USD / 1,000,000 token
$0.25 · prompt: <=272000 input tokens; cache minimum lifetime 30m; total write rate (not surcharge)
$0.50 · prompt: >272000 input tokens; cache minimum lifetime 30m; total write rate (not surcharge)
$0.50 · prompt: <=272000 input tokens; cache minimum lifetime 12h; total write rate (not surcharge)
$1.00 · prompt: >272000 input tokens; cache minimum lifetime 12h; total write rate (not surcharge)
OUT
$1.20 – $1.80
USD / 1,000,000 token
$1.20 · prompt: <=272000 input tokens
$1.80 · prompt: >272000 input tokens
Performance
Overall capability
52.6/100
- Coding
- 48.8
- Reasoning
- 49.7
- Professional work
- 54.4
- Knowledge & language
- 50.7
| MysteryMechanism | Reasoning | Vals AI | 2026-11-05 | |
| AA-OmniscienceGPT-5.6 Luna (Max) | Knowledge & language | Artificial Analysis | 2026-11-05 | |
| SimpleQA Verified | Knowledge & language | Epoch AI | 2026-11-05 | |
| Finance Agent | Professional work | Vals AI | 2026-11-05 | |
| MLCR-AA（Artificial Analysis）GPT-5.6 Luna (Max) | Knowledge & language | Artificial Analysis | 2026-11-05 | |
| AA-Briefcase | Professional work | Artificial Analysis | 2026-11-05 | |
| Humanity’s Last ExamGPT-5.6 Luna (Max) | Reasoning | Artificial Analysis | 2026-11-05 | |
| APEX-Agents 1.1 | Professional work | Mercor | 2026-11-05 |
Providers
| Input | Output | Cache read | Cache write | ||||
|---|---|---|---|---|---|---|---|
| OpenAI | gpt-5.6-luna | Openai responses | global | ||||
| OpenRouter | openai/gpt-5.6-luna | Openai chat | global |
ModelRegistry · Catalog updated 2026-11-05