Early o1 preview id kept for historical cost audits. Prefer o3 or GPT-5 reasoning paths unless an old integration still pins o1-preview.
Privacy first counting
TokenCALC counts tokens in your browser when an Exact encoding is available. Prompt text does not need to leave your device for local counting.
Pricing snapshot
USD per 1 million tokens. Verify against the provider source before you lock budget.
| Rate | USD |
|---|---|
| Input / 1M | $15.00 |
| Output / 1M | $60.00 |
Model details
| Detail | Value |
|---|---|
| Provider | OpenAI |
| Context window | 128K |
| Tokenizer | Exact (o200k_base) |
| Last verified | 2026-08-02 |
| API model id | o1-preview |
Notes
Legacy preview; confirm availability before budgeting.