A search API where context depth is a price dial, not a default
- Source
- x.com
- Date
The Perplexity Search API takes the top three spots on the Artificial Analysis Search Index. The medium setting scored five points above the previous leaders, and extended the quality-cost Pareto frontier at about $0.091 per task. https://t.co/en7rs2Wbut
Context
Perplexity Search API lets developers choose how much extracted content each search result carries. In Artificial Analysis's , the medium setting scored 80, compared with 79 for high and 77 for low, using the same answering model and software. More supplied therefore did not produce the highest overall score in this test. Medium and high each cost about $0.091 per completed task, a total that includes model spending rather than a flat price per search request. The evaluator's account supplies the comparison.
- eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
- AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
- context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
Checking sign-in…
Loading comments…