GPT-5 (high) Token Counter & Cost Calculator
Count tokens for GPT-5 (high) and estimate the exact API cost — $1.25
per 1M input tokens, $10.00 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-5 (high) against.
Cost lookup — GPT-5 (high)
| Tokens | Cost on GPT-5 (high) |
|---|---|
| 1K input tokens | 0.125¢ |
| 10K input tokens | $0.0125 |
| 100K input tokens | $0.1250 |
| 1M input tokens | $1.25 |
| 1K output tokens | $0.0100 |
| 10K output tokens | $0.1000 |
FAQ
How accurate is the GPT-5 (high) token count?
Exact: o200k_base is OpenAI's own tokenizer, the same encoding its API bills GPT-5 (high) against. Paste your own text above to see the exact number for your prompt.
How is GPT-5 (high) API cost calculated?
Cost = (input tokens ÷ 1,000,000) × $1.25 + (output tokens ÷ 1,000,000) × $10.00 — GPT-5 (high)'s official per-1M-token prices from Artificial Analysis.
Does this cover every reasoning-effort tier of GPT-5 (high)?
Pricing shown is for the merged representative tier. GPT-5 (high) groups 4 reasoning-effort variants: GPT-5 (high), GPT-5 (medium), GPT-5 (low), GPT-5 (minimal).
See full GPT-5 (high) pricing & benchmarks, or the main token counter for every model.