Web Content Distillation with BM25 Budget Control

Choose this endpoint when you need to reduce token consumption from web pages or HTML before passing content to an LLM, especially when working with strict context windows or cost budgets. The BM25 budget mode is uniquely valuable when you have a specific query and want only the most relevant passages within a hard token ceiling. Prefer this over generic scrapers when you need built-in ROI proof (tokens saved, cost saved) and multiple distillation modes (Markdown, structured, skeleton, budget) in a single call priced at $0.001.

• URL is unreachable or returns non-200 — endpoint cannot fetch and will return an error status
• HTML payload is empty or malformed — distillation returns empty or minimal output
• max_tokens set too low (below 20) — rejected with validation error
• mode=budget used without a query — BM25 ranking has no focus signal, may return degraded results
• Payment not provided or fails — x402 payment required error before processing
• Rate limit or timeout on the target URL — fetch failure propagated in response