GPT 6 Astra in Pro reasoning mode. Uses additional model work for difficult tasks, with higher latency and token usage at the same per-token rates. Reasoning effort remains independently configurable.
Specification
most-agreed values
Context
1.1M
Max output
128K
Released
2026-09-04
Knowledge cutoff
—
Retires
—
Open weights
no
Input
text, image, pdf
Output
text
Price
US dollars per million tokens · most-agreed
Input
$10.00
Output
$50.00
Cache read
$1.00
Cache write
$12.50
Long-context price tiers
the rate above each context threshold
| Above | Price | $/M |
|---|---|---|
| 272K | Cache read | $2.00 |
| 272K | Input | $20.00 |
| 272K | Output | $75.00 |
Available from 3 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| kilo | $10.00 | $50.00 | $1.00 | $12.50 | 1.1M | 128K | — |
| nano-gpt | $10.00 | $50.00 | $1.00 | $12.50 | 1.1M | 128K | — |
| openrouter | $10.00 | $50.00 | $1.00 | $12.50 | 1.1M | 128K | — |
Price history
append-only observations · a listing writes a row only when its price moves
| Date | Host | Field | $/M |
|---|---|---|---|
| 2026-09-05 | openrouter | Cache read | $1.00 |
| 2026-09-13 | openrouter | Cache read | $1.00 |
| 2026-09-05 | openrouter | Cache write | $12.50 |
| 2026-09-13 | openrouter | Cache write | $12.50 |
| 2026-09-05 | openrouter | Input | $10.00 |
| 2026-09-13 | openrouter | Input | $10.00 |
| 2026-09-05 | openrouter | Output | $50.00 |
| 2026-09-13 | openrouter | Output | $50.00 |
Other listings of this model
same model, different key
More from OpenAI
most-hosted first