GPT-4 Token Counter & Cost Calculator
Count tokens for GPT-4 and estimate the exact API cost — $30.00
per 1M input tokens, $60.00 per 1M output tokens — using a real
o200k_base BPE tokenizer. Everything runs in your browser; nothing is uploaded.
Counts are exact for OpenAI models (o200k_base is GPT-4o/4.1/5's tokenizer). For Claude, Gemini and other vendors — whose tokenizers are not public — treat the count as a close estimate (typically within ±15%).
Model price data failed to load — cost estimates are unavailable right now. Token counts above still work; try reloading the page.
Cost of this text across popular models
| Model | Input $/1M | Output $/1M | This text (input) | +500 output tokens |
|---|
Exact: o200k_base is OpenAI's own tokenizer, the same encoding its API bills GPT-4 against.
Cost lookup — GPT-4
| Tokens | Cost on GPT-4 |
|---|---|
| 1K input tokens | $0.0300 |
| 10K input tokens | $0.3000 |
| 100K input tokens | $3.00 |
| 1M input tokens | $30.00 |
| 1K output tokens | $0.0600 |
| 10K output tokens | $0.6000 |
FAQ
How accurate is the GPT-4 token count?
Exact: o200k_base is OpenAI's own tokenizer, the same encoding its API bills GPT-4 against. Paste your own text above to see the exact number for your prompt.
How is GPT-4 API cost calculated?
Cost = (input tokens ÷ 1,000,000) × $30.00 + (output tokens ÷ 1,000,000) × $60.00 — GPT-4's official per-1M-token prices from Artificial Analysis.
See full GPT-4 pricing & benchmarks, or the main token counter for every model.