LLM Token Counter

This LLM token counter helps you estimate how many tokens a piece of text uses before you send it to an API. Whether you need a GPT token counter, a Claude token counter, an OpenAI token counter, or a quick AI token calculator for Gemini, paste your text above and the tool will count tokens instantly in your browser. There is no signup, no API key, and nothing is uploaded - your prompts and documents stay completely private.

Tokens are the unit that every large language model uses to read and bill text. As a ChatGPT token counter rule of thumb, one token is about four characters of English, and 100 tokens is roughly 75 words. Longer words, code, and non-Latin scripts split into more tokens, which is why this tool blends character count and word count and nudges the estimate upward when it detects code-like input. For gpt-4o tokens and other modern models the real tokenizer will usually land within 10 to 15 percent of this estimate.

Once you know your token count, the cost table shows what that text would cost as both input and output across GPT-4o, GPT-4o mini, GPT-4.1, Claude Opus, Claude Sonnet, Claude Haiku, Gemini 2.5 Pro, and Gemini 2.5 Flash. Cost is simply tokens divided by one million multiplied by each model's published per-million-token price, so you can compare an expensive frontier model against a cheaper one in seconds. This makes it easy to budget prompts, estimate the cost of a batch job, or decide which model gives the best value for your workload.

Remember that this is a fast estimate and not a substitute for an official tokenizer. Each provider uses its own tokenizer, so the exact count differs slightly between GPT, Claude, and Gemini. When you need exact numbers for billing, use OpenAI tiktoken or the Anthropic token counting endpoint. If you want to model full conversations, batch jobs, or mixed input and output volumes, try our companion LLM pricing calculator to compare API costs across OpenAI, Anthropic, and Google in more detail.