OpenAI reasoning model for harder problems where extra thinking tokens are worth the bill. Watch output cost: reasoning tokens are billed at the output rate.
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 | $2.00 |
| Output / 1M | $8.00 |
| Cached input / 1M | $0.500 |
| Batch input / 1M | $1.00 |
| Batch output / 1M | $4.00 |
Model details
| Detail | Value |
|---|---|
| Provider | OpenAI |
| Context window | 200K |
| Tokenizer | Exact (o200k_base) |
| Last verified | 2026-08-02 |
| API model id | o3 |
Notes
Reasoning tokens are billed at the output rate.