Original GPT-4 API tier kept for legacy cost audits. Prefer GPT-4.1 or GPT-5 for new builds; use this row when older integrations still call gpt-4.
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 | $30.00 |
| Output / 1M | $60.00 |
Model details
| Detail | Value |
|---|---|
| Provider | OpenAI |
| Context window | 8.2K |
| Tokenizer | Exact (cl100k_base) |
| Last verified | 2026-08-02 |
| API model id | gpt-4 |
Notes
Legacy 8K context; verify availability.