Observed arrival · 2026-09-16
What Does My Prompt Cost?
A browser-based toolkit for counting tokens and estimating LLM costs across major providers and open models.
Field notes
The toolkit separates exact tokenizer counts from character-ratio estimates when a public tokenizer is unavailable. Its batch mode accepts multiple local files, while the open-model section downloads real tokenizers once from Hugging Face and then runs them offline in the browser. The API returns token count, input cost, and context-fit fields, but remains beta with no published request limits. A team dashboard shown elsewhere is a design exercise using randomly generated data, not connected usage reporting.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
One card from the complete issue