LLM Token Counter
Count tokens for GPT, Claude, Gemini, and other LLMs. Estimate API costs instantly.
Enter text to see token counts
About token counting
Token counts are estimates. Actual counts may vary slightly based on each model's specific tokenizer. For exact counts, use the official tokenizers (tiktoken for OpenAI, etc.).
How Token Counting Works
What is a token?
A token is a chunk of text—roughly 4 characters or 0.75 words in English. Common words are single tokens; longer words are split into multiple tokens.
Why tokens matter
LLM APIs charge per token. Understanding token counts helps you estimate costs and stay within context window limits (e.g., 128K, 200K, 2M tokens).
Quick estimation
Rule of thumb: 1 token ≈ 4 characters ≈ 0.75 words. 1,000 tokens ≈ 750 words ≈ 1.5 pages of text.
Want to compare model outputs?
Test your prompts across GPT, Claude, and Gemini side-by-side to find the best model for your use case.