GPT-6 Luna (High)
By OpenAI · released 2026-09-22 (4 weeks) · snapshot 2026-10-24
- Intelligence index
- 32.90
- Cost to run the AA index
- $47.9
- Price per 1M tokens (in / out)
- $0.10 / $0.50
- End-to-end time
- 11.2s
Is GPT-6 Luna (High) on the Pareto frontier, and what beats it?
On the Pareto frontier
Yes. Nothing live under $10,000 is both smarter and cheaper to run.
The daily check URL below returns 409 the day that changes.
Open in the picker Daily check URL: 200 on the frontier, 409 once beaten
GPT-6 Luna (High) today
Intelligence: Artificial Analysis Intelligence Index. Cost: total cost to run that benchmark, so reasoning tokens count. API id: gpt-6-luna-high.
Compare head to head
Suggested: what beats it, its effort levels, and frontier models near its price.
- GPT-6 Luna (High) vs GPT-6 Luna (Low)
- GPT-6 Luna (High) vs GPT-6 Luna (Non-reasoning)
- GPT-6 Luna (High) vs GPT-6 Luna (Medium)
- GPT-6 Luna (High) vs GPT-6 Luna (Xhigh)
- GPT-6 Luna (High) vs GPT-6 Luna (Max)
- GPT-6 Luna (High) vs Claude Haiku 5.5 (Medium)
- GPT-6 Luna (High) vs Claude Haiku 5.5 (High)
- GPT-6 Luna (High) vs MiMo-V2.6-Flash
What the GPT-6 Luna release did to the frontier on 2026-09-22
5 of 6 effort levels reached the frontier at launch (GPT-6 Luna (Low), GPT-6 Luna (Medium), GPT-6 Luna (High), GPT-6 Luna (Xhigh), GPT-6 Luna (Max)). Impact 10.20, #2 of 46 releases this past year.
Should you use GPT-6 Luna (High)?
Should you use GPT-6 Luna (High)?
Yes, for the money: nothing live under $10,000 is both smarter and cheaper to run, so it sits on the value frontier.
What is better and cheaper than GPT-6 Luna (High)?
Nothing: no live model under $10,000 is both smarter and cheaper.
How much does GPT-6 Luna (High) cost?
$0.10/$0.50 in/out per 1M tokens, and $47.9 to run the full Artificial Analysis Intelligence Index, the honest all-in number for reasoning models.
Is GPT-6 Luna (High) on the Pareto frontier?
Yes: GPT-6 Luna (High) is on the intelligence-vs-cost Pareto frontier.
Frontier membership by axis pair
Other axis pairs where GPT-6 Luna (High) is Pareto-optimal.
| Y axis | X axis | On the frontier |
|---|---|---|
| AA intelligence index | AA total cost to run (USD) | |
| AA intelligence index | End-to-end total seconds | |
| AA intelligence index | Output speed tokens/sec |
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/models/gpt-6-luna-high · Markdown: /api/v1/models/gpt-6-luna-high?format=md · llms.txt · agent skill