Brave Search
/brave
Brave Search is one of the few genuinely independent search indexes on the market, built from Brave’s own crawl of tens of billions of pages rather than reselling Google or Bing. That independence pairs with a strong privacy posture and rights designed for AI use, including a Summarizer and a token-efficient context endpoint that ground models in fresh, citable results. For teams that want a credible alternative to the search duopoly — for resilience, principle or product differentiation — Brave is the standout option.
Call Brave Search through the gateway
Same paths, parameters and responses as Brave Search'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/brave/<native-path> \ -H "Authorization: Bearer $AUXILIAR_API_KEY"
Exact endpoints and parameters: docs.auxiliar.ai/brave. An empty balance returns HTTP 402 — no silent degradation; see how billing behaves.
Choose if
You want an index that isn't a Google/Bing scrape, plus a privacy posture and AI grounding.
Avoid if
You need more than ~200 results per query.
Evals
How Brave Search 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: 2026-06-21.