GPT-6 Luna Pro uses the same underlying model as GPT-6 Luna with Pro reasoning mode enabled for higher-quality responses on complex tasks.
Specification
most-agreed values
Context
1.1M
Max output
128K
Released
2026-09-22
Knowledge cutoff
—
Retires
—
Open weights
no
Input
text, image, pdf
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.10
Output
$0.50
Cache read
$0.01
Cache write
$0.125
Long-context price tiers
the rate above each context threshold
| Above | Price | $/M |
|---|---|---|
| 272K | Cache read | $0.02 |
| 272K | Cache write | $0.25 |
| 272K | Input | $0.20 |
| 272K | Output | $0.75 |
Available from 4 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| openrouter · batch | $0.05 | $0.25 | $0.005 | $0.0625 | 1.1M | 128K | — |
| kilo | $0.10 | $0.50 | $0.01 | $0.125 | 1.1M | 128K | — |
| nano-gpt | $0.10 | $0.50 | $0.01 | $0.125 | 1.1M | 128K | — |
| openrouter | $0.10 | $0.50 | $0.01 | $0.125 | 1.1M | 128K | — |
Price history
append-only observations · a listing writes a row only when its price moves
| Date | Host | Field | $/M |
|---|---|---|---|
| 2026-09-23 | nano-gpt | Cache read | $0.005 |
| 2026-09-24 | nano-gpt | Cache read | $0.01 |
| 2026-09-23 | nano-gpt | Cache write | $0.0625 |
| 2026-09-24 | nano-gpt | Cache write | $0.125 |
| 2026-09-23 | nano-gpt | Input | $0.05 |
| 2026-09-24 | nano-gpt | Input | $0.10 |
| 2026-09-23 | nano-gpt | Output | $0.25 |
| 2026-09-24 | nano-gpt | Output | $0.50 |
More from OpenAI
most-hosted first