Parallel Search uses ~82k tokens per task, second-lowest of 26 search tools benchmarked

ArtificialAnlys · x · 2026-11-21

Artificial Analysis released token-usage data for Parallel Search: the advanced mode consumes 82k tokens per task, 2nd lowest of 26 products, behind only OpenAI's first-party Web Search (medium) at 41k; fast mode uses 116k, comparable to Keenable Search (pro) at 118k and (realtime) at 122k. Usage dropped sharply from August (168k advanced / 292k fast). Nearly all tokens are input tokens — the search results returned to the model.

Related event: Parallel Search Tops AA Search Benchmark at $0.014 per Call(4 posts)→

Original post →

More from Infra

Infra channel →