Event ·Official first-hand

Perplexity 发布 Orchestrator API:一个接口调用多家模型

Perplexity 推出 Orchestrator API,把 OpenAI、Anthropic、Google、xAI 以及开源权重模型统一到一个端点调用。 功能上,它提供同模型多供应商自动 failover,上层应用在某一供应商故障时可无缝切换;计费按统一账单结算,免去逐家开户和对账。预览版还包括一个 perplexity/auto 路由器,根据请求内容自动把每个请求发送到描述好的目标路由。 这类统一网关方案与 OpenRouter、LiteLLM 属同一赛道,Perplexity 的差异化在于绑定其搜索基础设施和 auto 路由能力。对需要多模型冗余、降低单点故障风险的开发者和企业接入团队来说,多了一个可对比的选择。

Current read

做 AI 应用的朋友可以看看:Perplexity 这个 API 一个端点就能调 OpenAI、Anthropic、Google 和开源模型,某家挂了自动切到备用供应商,还能用预览版 auto 路由器自动分发请求。和 OpenRouter 思路类似,但多了统一计费,省钱省事。

11 sources62° AI heatLast updated 2026/11/19 17:47:00

Evidence

11 sources
Primary sourcemarktechpost
View source
Related source 1Perplexity
View source
Related source 2shao__meng
View source
Related source 3Claude Code: GitHub Releases
View source
Related source 4claudedevs
View source
Related source 5OpenRouter
View source
Related source 6OpenAI Blog
View source
Related source 7Google Gemini App
View source
Related source 9Techsauce
View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.