Firecrawl
/firecrawl
Firecrawl turns websites into clean, LLM-ready data with best-in-class quality. A single API covers the whole pipeline — scrape a page, crawl an entire site, map its URLs, or pull structured fields against a schema — and returns tidy markdown with navigation and clutter removed by default. Loved across the AI developer community and self-hostable under an open-source license, it’s the standout choice when the quality of the extracted text directly determines how well your model performs.
Call Firecrawl through the gateway
Same paths, parameters and responses as Firecrawl's native API — auxiliar injects the upstream key server-side and debits the provider's metered cost from your credits.
curl https://api.auxiliar.ai/firecrawl/<native-path> \ -H "Authorization: Bearer $AUXILIAR_API_KEY"
Exact endpoints and parameters: docs.auxiliar.ai/firecrawl. An empty balance returns HTTP 402 — no silent degradation; see how billing behaves.
Choose if
You want the highest-quality scrape/markdown and a single surface for scrape, crawl, extract and screenshot.
Avoid if
You're cost-sensitive on hard targets — stealth + JSON stack ~5–9× the base credit.
Evals
How Firecrawl performed on the curator-fleet web-access evals — the real measured numbers behind each composite, ranked best-first. Every provider runs the identical task corpus; each scorecard carries its run date. Latest run: 2026-06-22.