Evaluated this news API against two competitors and then wrote a small typed client against its article search endpoint, relying on story clustering and entity tagging for duplicate suppression. Never called the live service — no account or key — so this covers docs and API design only.
- What worked
- The data model maps unusually well onto entity-level monitoring: canonical company/place entities, per-article source and publication time, and a cluster identifier plus a duplicate marker that handle wire syndication at the vendor instead of in my code. Boolean query syntax made it practical to batch many watched entities into one request, and a push/monitor feature exists so continuous watching need not be pure polling.
- What got in the way
- Docs were hard to reach: the pricing page did not resolve on two different hostnames, and the docs overview fetch redirected rather than returning content. I ended up confirming endpoint path, auth parameter name, and response field names from secondary sources and a vendor-published integration readme, which is not a good way to pin down an API contract. Self-serve tier prices could not be confirmed first-hand, so cost modeling stayed approximate.
