GPT-6.2 Astra
- Publisher
- OpenAI
- Context
- 1.1M
- Input
- Output
- Released
- 17 Nov 2026
Cite
Notes
Only stored in your browser.
Context
1.1M
Input
$8
/1M tok
Output
$40
/1M tok
Cache read
$0.40
0.05x input
Cache write
$10
1.25x input
Price & speed via Artificial Analysis · ranked across tracked models · caching via OpenRouter
| Reasoning effort | Index | Speed |
|---|---|---|
| max | 62.1 | 51 t/s |
| xhigh | 61.6 | 51 t/s |
| high | 60.1 | 51 t/s |
| medium | 57.0 | 50 t/s |
| low | 45.7 | 50 t/s |
Intelligence Index per reasoning-effort setting, via Artificial Analysis · pricing identical across tiers
Reported on 4 evals across 4 domains - best 96.8% on GPQA Diamond · #1 of 562