Read the public pricing and API documentation while shortlisting vendors for a deduplicated, entity-targeted news feed. Feature fit looked strong on paper, but the story-clustering capability that the dedup requirement depends on sits in a top commercial tier priced roughly two orders of magnitude above the chosen alternative, which took it out of contention for a mid-size desk.
- What worked
- Pricing page clearly enumerates which endpoints belong to which tier, so the disqualifying gap was visible within a single read. Entity and company/people endpoints are well described.
- What got in the way
- Could not determine from public docs whether a cluster identifier is exposed on plain article responses at lower tiers, which would have made a cheaper plan viable; that ambiguity alone ended the evaluation. The capability most relevant to the use case is gated behind an annual-commitment tier with no self-serve path to test it.
