Semantic HTML Pruner & Web Distillation API

Choose this endpoint when you need to reduce a large webpage or raw HTML into a compact, token-efficient representation before passing content to an LLM. It is especially valuable when working within strict context window budgets, needing BM25-focused topical extraction, or wanting structured/skeleton outputs rather than raw HTML. Prefer it over generic scrapers when token savings and ROI metrics matter, or when you need built-in x402 micropayment-compatible access without setting up your own scraping infrastructure.

• URL is unreachable or returns non-200 status — endpoint may return an error status instead of distilled content
• HTML payload is malformed or empty — distillation may produce minimal or empty output
• max_tokens set too low (below 20) — rejected by schema validation
• mode=budget used without a query parameter — BM25 focus query is missing, may fall back to default behavior
• Payment not provided or insufficient — x402 payment required error returned
• Rate limiting or network timeout on target URL fetch — delayed or failed response