GPT-6 Astra is our most capable model for the most demanding work. Use it for complex reasoning, coding, computer use, research, and document creation. `reasoning.effort` supports `low`, `medium`, `high`, `xhigh`, and `max`.
| Input | Output | Cached Read | Cached Write | |
|---|---|---|---|---|
| ≤ 272K tokens | $10 | $50 | $1 | $12.5 |
| > 272K tokens | $20 | $75 | $2 | $25 |
| Model | Context | Max out | Pricing |
|---|---|---|---|
| GPT 6 Luna | 1.1M | 128K | $0.1$0.5 |
| GPT 6 Sol | 1.1M | 128K | $2$10 |
| GPT 6 Astra | 1.1M | 128K | $10$50 |
/v1/models/opencode/gpt-6-astra