Prices are current official model rates. Each tier retains its billing unit and conditions; provider prices may differ.
| Field | ||
|---|---|---|
| Organization | OpenAI | |
| Family | GPT | |
| Released | 2025-10-16 | |
| Context window | 400K | |
| Max output | 128K | |
| Input modality | DocumentImageText | |
| Output type | ImageText | |
| Providers | - | |
| Input | - | |
| Output | - | |
| Cache read | - | |
| Cache write | - | |
| Other charges | - | |
| Weights | Closed | |
| Reasoning | Native | |
| Structured | Native | |
| Temperature | Native |
Performance
Scoring rulesText scores use the site’s full-population calibration and scoring method, on a 0–100 scale. Media results stay separate by task and configuration; they do not contribute to the text score.