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)→
More from Infra
- DayOne data center IPO on hold as investors doubt AI infrastructure valuations — SumitGup · 2026-11-21
- Cathie Wood predicts orbital compute will undercut terrestrial data centers within two years — XFreeze · 2026-11-21
- Self-hosted cloud GPUs beat Higgsfield and Runway APIs on cost and flexibility — Al_Grigor · 2026-11-21
- NVIDIA GTC DC lineup: Ian Buck, Catanzaro and Lebaredian sessions on infra, agents, physical AI — nvidia · 2026-11-21
- KV cache economics: why a $200 Claude plan can hand out $14,000 of API-equivalent tokens and still profit — rachittshah · 2026-11-21
- Baseten breaks down its security threat model as agent swarms accelerate attacks — baseten · 2026-11-21