Token Counter
Estimate token counts for GPT-4, Claude, Gemini, and Llama models. See context window usage and cost estimates.
Estimate token counts for GPT-4, Claude, Gemini, and Llama models. See context window usage and cost estimates.
A token is a piece of text that AI models process — roughly 3-4 characters or about 0.75 words in English. Models like GPT-4 and Claude use tokenizers to break text into these units. Token counts determine API costs and context window limits.
This tool provides estimates using a characters-per-token heuristic (~3.5-4 chars/token). Actual token counts vary by model tokenizer. For exact counts, use the provider's official tokenizer (e.g., OpenAI's tiktoken). Estimates are typically within 10-15% of actual counts for English text.
The context window is the maximum number of tokens a model can process in a single request, including both input and output. For example, GPT-4o has a 128K context window, while Claude Sonnet 4 has 200K. Going over the limit means the model can't process your full input.