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`.
web_searchfile_searchimage_generationcode_interpreterhosted_shellapply_patchskillscomputer_usemcptool_searchhttps://api.openai.com/v1/chat/completionshttps://api.openai.com/v1/responseshttps://api.openai.com/v1/batches| Input | Output | Cached input | 30m write | 12h write | Cache writes | |
|---|---|---|---|---|---|---|
| Standard | $10 | $50 | $1 | $12.5 | $25 | $12.5 |
| Batch | $5 | $25 | $0.5 | $6.25 | $12.5 | — |
| Fast | $20 | $100 | $2 | $25 | $50 | — |
| 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/openai/gpt-6-astraGPT-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`.