Simple per-call math
The tool applies the listed per-million-token rate to the exact local count, so the calculation is easy to inspect.
Token Cost Calculator
Turn a local token count into a clear per-call API cost estimate for GPT, Claude, and Gemini model references.
o200k_base
0 / 1,000,000 characters
Token visualization
Local token pieces update 0.5 seconds after you stop typing.
Paste text above to see how the selected local encoder splits it into tokens.
Local calculation. Your text stays in this browser. Nothing is uploaded or stored by Tokens Calculator.
Compare input cost by configured model
Compare the same text using the available local encodings and current list-price estimates.
| Model | Tokens | Input / 1M | Input cost |
|---|---|---|---|
| GPT-4oOpenAI | 0 | $2.50 | $0.000000 |
| GPT-4OpenAI | 0 | $30.00 | $0.000000 |
| Claude 3.5 SonnetAnthropic | 0 | $3.00 | $0.000000 |
| Claude Sonnet 4.6Anthropic | 0 | $3.00 | $0.000000 |
| Gemini 2.5 FlashGoogle | 0 | $0.30 | $0.000000 |
| Gemini 2.5 ProGoogle | 0 | $1.25 | $0.000000 |
Claude and Gemini counts are useful approximations using cl100k_base; provider tokenizers can differ by model version and text.
One text, multiple references
See how a single text sample changes across the available GPT, Claude, and Gemini configurations.
No budget data leaves the page
Text is counted in your browser only, which keeps internal prompts and drafts out of a server-side log.
Configured API price reference
The calculator reads these standard USD list-price references from a single local configuration file. Provider policies, caching, tools, taxes, and special request modes can change the final bill.
| Model | Input / 1M | Output / 1M | Counting note |
|---|---|---|---|
| GPT-4oOpenAI | $2.50 | $10.00 | Uses the o200k_base encoding. |
| GPT-4OpenAI | $30.00 | $60.00 | Uses the cl100k_base encoding. |
| Claude 3.5 SonnetAnthropic | $3.00 | $15.00 | Legacy model; cl100k_base approximation. |
| Claude Sonnet 4.6Anthropic | $3.00 | $15.00 | cl100k_base approximation. |
| Gemini 2.5 FlashGoogle | $0.30 | $2.50 | cl100k_base approximation for text. |
| Gemini 2.5 ProGoogle | $1.25 | $10.00 | Uses standard pricing for prompts up to 200K; cl100k_base approximation. |
How it works
- 01
Count a representative text sample
Paste a prompt or response that represents the text you expect to send or receive.
- 02
Choose the API model
Pick the provider model whose list price you want to reference.
- 03
Choose input or output cost
Use the mode switch to estimate the correct side of the API interaction.
Token Cost Calculator FAQ
How does the token cost calculator work?
It counts your pasted text with the selected local encoding, divides that count by one million, and multiplies it by the selected model’s configured input or output rate.
Why are input and output estimates separate?
Most providers bill prompt tokens and generated tokens at different rates. Separating them avoids pretending a single pasted string represents both sides of a future API call.
What is not included in the estimate?
The calculator does not add tokens from API message wrappers, system prompts, tool schemas, cached content, images, audio, discounts, taxes, or provider-specific service fees.
Where can I change the configured rates?
All rate references live in src/lib/pricing.ts. That central file keeps model names, encodings, price tiers, and official provider links together.
Explore more token tools
Every tool runs token counting in your browser. Keep your text local while you move between calculators and guides.
Not affiliated with Anthropic, OpenAI or Google.