Legacy OpenAI chat model kept for migration cost checks against Mini and Nano tiers. Prefer GPT-4.1 Mini or GPT-5 Mini for new production apps.
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 | $0.500 |
| Output / 1M | $1.50 |
| Batch input / 1M | $0.250 |
| Batch output / 1M | $0.750 |
Model details
| Detail | Value |
|---|---|
| Provider | OpenAI |
| Context window | 16.4K |
| Tokenizer | Exact (cl100k_base) |
| Last verified | 2026-08-02 |
| API model id | gpt-3.5-turbo |
Notes
Legacy; verify availability on OpenAI docs.