DOM Stripper – Web Distillation with BM25 Budget Control

Choose this endpoint when you need to reduce the token footprint of web content before passing it to an LLM, especially when working within strict context window budgets. It is ideal for agent pipelines that need to read documentation, news, or product pages without incurring high LLM token costs. Prefer the budget+BM25 mode when you have a specific question and want only the most relevant passage from a page. Use structured mode when the page contains tables or metadata you want as JSON. Prefer this over raw HTTP fetch + manual parsing when you want compression ROI metrics included automatically.

• URL is unreachable or returns a non-200 status — endpoint returns an error status
• URL points to a non-HTML resource (PDF, binary) — distillation may fail or return empty data
• max_tokens set too low (below 20) — rejected by schema validation
• mode=budget used without providing a query — BM25 scoring has no focus signal
• Raw HTML provided is malformed or empty — distillation returns minimal or empty output
• Network timeout fetching the target URL — returns error status
• Payment not included or insufficient — HTTP 402 response blocking execution