LLM Token & Context Window Estimator

Estimates LLM prompt token counts, context-window utilization, and remaining capacity before sending text to a language model.

Runs locally in your browser
This is a transparent local estimate—not an exact provider tokenizer. No prompt content is transmitted.
Prompt or message text

Plan input and output together

Context limits usually include system instructions, conversation history, tool messages, prompt text, and generated output. Keep a safety margin for provider-specific framing and tokenizer differences.

Recent tools: