GPT 6.2 Astra Pro
GPT-6.2 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.
- Reasoning
- Vision
- Tool Calling
- Structured Output
Added Nov 18, 2026
Pricing
Auto routing · per 1M tokens- Input
- $8.00
- Output
- $40.00
- Cache read
- $0.40
Specifications
- Context window
- 922K
- Max output
- 128K
Benchmarks
No public benchmark scores for this model yet.
Providers
Auto routing is available for this model. Explicit provider selection is not available.
| Cache write /M | ||||||
|---|---|---|---|---|---|---|
Recommended | $8.00 | $40.00 | $0.40 | $10.00 | N/A | N/A |
| >272k | $16.00 | $60.00 | $0.80 | $20.00 |