Perplexity Search debuts on the Artificial Analysis Search Index, with all three context size variants taking top positions on the leaderboard The @perplexity_ai Search API comes with three context settings (low, medium, and high) that control how much extracted content each search result carries. We tested all three variants using our standardized methodology: the same model (GPT-5.6 Luna at medium reasoning), running inside Stirrup, our open-source agent harness, with tools for searching and fetching pages from the web. Only the provider behind the search tool changes. Key results: ➤ Perplexity Search (medium) scores 80 on the Artificial Analysis Search Index, ahead of the previous leaders, Parallel (advanced) and Brave Search (LLM context), at 75. The high and low variants score 79 and 77 respectively. Its lead is concentrated in BrowseComp results, with AA-Omniscience and DeepSearchQA scoring comparably to other leading providers ➤ Efficient search payloads: smaller overall search results mean the model reads less per task, so Perplexity has the lowest model inference cost per task of providers we’ve tested so far, ranging from $0.028 to $0.034 across the three variants vs $0.036 for the next lowest provider ➤ Total cost per task is ~$0.091 for the medium and high context variants, at mid-pack latency. For comparison, Parallel (advanced) costs $0.084 per task and Brave (LLM context) costs $0.13 per task

We tested one API from Perplexity with three different context sizes. The search context size setting controls how much extracted content each search result carries. All three variants have the same search price of $5.00 per 1k queries, so richer context does not cost more per search. Quality plateaus between medium and high, while searches per task (15.4 / 12.5 / 11.4) and total cost per task (~$0.105 / ~$0.091 / ~$0.091) fall with higher search context sizes. Time per task is longer with low context, driven by additional searches and model inference time.

Total cost per task combines search API cost and model inference cost. Perplexity Search (medium) extends the Pareto frontier for Artificial Analysis Search Index vs. Cost per Task: it reaches an Index score of 80 at ~$0.091 per task, where the previous frontier topped out at 75 for $0.084 with Parallel Search (advanced). Parallel (turbo and fast) and Firecrawl Search hold the frontier's lower-cost positions.

Time per task includes both measured search time and model time. Perplexity Search sits mid-pack: ~1.1s per search query, and roughly 27 to 29s per task for the medium and high variants against a board range of about 19 to 62s. The low variant takes about 36s: same per-query speed, more searches. More detailed payloads result in fewer agent actions: 13.1 searches per task for high vs 18.0 for low on BrowseComp.