Perplexity 推出 Monitor、Orchestrator、Context 三个新 API
Perplexity 一口气放出三个 API,事件告警、模型路由、URL 批量转内容,等于把搭智能体最麻烦的搜索和清洗环节包了。他们 API 业务涨了 4.3 倍,年化收入到 9 位数,做 RAG 和 Agent 应用的开发者可以直接试。
Perplexity 在几天内连发三款面向开发者的 API:Perplexity Monitor 提供针对事件的可编程告警,Perplexity Orchestrator 在前沿模型与开源权重模型之间按任务做路由,Perplexity Context 支持以批处理模式把 URL 转成智能体可直接使用的内容。
CEO Arav Srinivas 披露,公司 API 业务同比增长 4.3 倍,年化收入已达到 9 位数(亿美元级)。他同时强调 Perplexity 拥有目前最强的网页搜索能力,其决策模型是 OpenRouter 上增长最快的模型,并为 LLM 与决策模型提供搜索 grounding。
这三个 API 分别覆盖事件监控、模型路由和内容供给三个环节,组合起来基本构成了构建搜索型智能体的完整后端。对做 RAG 或智能体应用的团队来说,这意味着可以不自己搭搜索与清洗管线,直接用其 API 获取实时网页数据并按成本在开源与闭源模型间切换。
Last few days, we launched three new APIs: Perplexity Monitor: programmable alerts on events Perplexity Orchestrator: task based routing across frontier and open-weight models Perplexity Context: batch-mode transformation from URLs to usable content for agents Our API business has grown 4.3x YoY and tracks at a 9-figure annual run rate. Perplexity has the state-of-the-art web search, decision models (fastest growing on Openrouter), and search grounding for LLMs and decision models. We’re just getting started. Follow @perplexitydevs for regular updates.📊 42 ⚡
This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Perplexity, API, RAG, agents.
Source attribution: curated from Aravind Srinivas (@AravSrinivas).