LLM Token Counter and Tokenizer
Count tokens, inspect context window usage, and calculate input costs across GPT-4o, Claude 3.5, Gemini 1.5, Grok, and DeepSeek. Fast, accurate, and completely private in your browser.
- Exact o200k_base tokenizer for GPT-4o & calibrated Claude / Gemini counts
- Live context window usage meter and per-call input cost calculation
- 100% Client-side in your browser — zero uploads, drag-and-drop text/code files