Tokens & Cost

Count tokens for GPT, Claude, and Gemini models — runs entirely in your browser.

Estimate the cost of any prompt or completion across major LLM providers.

Project your monthly AI spend from usage patterns and model mix.

Visualize exactly how much of a model's context window your prompt occupies.

Discover how dense your text is in tokens vs. plain words — useful for tightening prompts.

Estimate cost and runtime for OpenAI and Anthropic batch processing jobs.

Trim filler words and tighten phrasing to cut token count without losing meaning.

Side-by-side pricing for every major LLM, sortable by input, output, and cached rates.

Quantify how much prompt caching saves on Anthropic, OpenAI, and Gemini.

Project the training and inference cost of a fine-tune across providers.