All projects on Base matching “count text tokens”

Count the LLM tokens in text for a given model or encoding — exact for OpenAI and open models (Llama, Mistral, Qwen, Gemma, DeepSeek, Command-R); labelled-approximate for Claude & Gemini.

Fetches a web page server-side and returns a clean text extract with token-count estimates. Strips scripts, styles, navigation, ads and boilerplate. Served in JSON. $0.002 per call.

Condense text for token budgets: retained-fact list + dropped-content log + before/after token counts (OpenRouter free-first + approx counter). Audit loss.