AITOPAI热报
ModelsMulti-source

Perplexity Decider 模型在 OpenRouter 月请求量达 10 亿次

Aravind Srinivas@AravSrinivas
Post· 11 sources
View the post
Why we picked it

Perplexity 的 Decider 在 OpenRouter 月请求量到了 10 亿次，v1.3 还免费一周。做多模型路由、想省 API 成本的同学正好白嫖测一下，跟自己写路由规则比比谁更准。

Perplexity CEO Aravind Srinivas 称，旗下 Decider 模型在 OpenRouter 平台上的月请求量已达 10 亿次，且仍在持续增长。作为推广，Decider v1.3 版本即日起在 OpenRouter 上免费开放一周。

Body

Decider 是 Perplexity 面向路由和决策类任务推出的模型，用户调用后由模型判断该把请求分发给哪个底层模型执行。这类请求属于高频低延迟场景，10 亿次月请求量意味着大量下游应用把模型选择这一步交给了 Decider。

OpenRouter 已成为模型厂商触达开发者的重要分发渠道，Perplexity 选择在 OpenRouter 上公布请求量并以免费一周的方式推 v1.3，也是在和 OpenAI、Anthropic 等在同一入口竞争开发者流量。对需要多模型调度、控制成本的开发团队来说，可以借免费窗口实测其路由准确率和延迟表现。

Original · Aravind Srinivas

Perplexity handling billion decision model requests a month now on Openrouter and continuing to grew steadily Bo @bo_wangbo thanks for trusting decider, and decider v1.3 is free for one week on OpenRouter: openrouter.ai/perplexity/ppl… 🔗 View Quoted Tweet📊 7 ⚡

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Models" 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, Decider, OpenRouter, open-source models.

Source attribution: curated from Aravind Srinivas (@AravSrinivas). Cross-source corroboration: 11 independent sources have covered this development (including TestingCatalog, 岚叔, elvis), confirming industry-wide signal strength.

#Perplexity#Decider#OpenRouter#open-source models#MCP and tools

Keep reading

Recent stories with the same tag or section
ProductsBuildersMulti-source01:52
Chinese contentPerplexity Mac 版向 Max 订阅用户推出 Teammates 多智能体功能

如果你是 Perplexity Max 订阅者，现在 Mac 版多了几个能干活的智能体，可以帮你做 QA、客服、研究和营销。它能多个智能体组队协作，走的是和 ChatGPT agent 模式同类的路线，做自动化工作流的人可以试试。

#Perplexity#Teammates#agents#coding assistants
Event
Official accountPerplexity@perplexity_aiSource
ProductsBuildersMulti-source01:48
Chinese contentPerplexity Teammates 智能体上线 Mac 版，Max 订阅用户可用

Perplexity 把自己的智能体功能 Teammates 推到了 Mac 版上，只有 Max 订阅用户能用。它能调插件和技能主动干活，底层跑的是 Perplexity 自家模型。用 Max 又天天开 Mac 的话可以试试，和 ChatGPT 的 Agent 模式思路类似但走订阅分层路线。

#Perplexity#Teammates#agents#Mac
Event
TestingCatalog@testingcatalogSource
ProductsBuildersMulti-sourceSelected00:49
Perplexity teammate renders Pantheon video across 48 parallel sandboxes

The non-obvious point is that the bottleneck shifted from GPU horsepower to orchestration: 48 cheap sandboxes beat a single expensive machine. Teams building agentic workflows can apply the same pattern of splitting long-running tasks across parallel sandboxes. It also signals Perplexity pushing agentic teammates beyond search into creative production work.

#Perplexity#Teammate#three.js#agents
Event
Aravind Srinivas@AravSrinivasSource
ModelsBuildersSelected12:47
Decision Models for agentic security open sourced, free on OpenRouter

Open weights aimed at a niche most security teams have not tooling for yet: auditing agent sessions at full scale rather than sampling. Security and platform engineers operating multi-agent deployments can self-host under Apache or use the free OpenRouter window until 19 Nov to evaluate it against manual rule review. The Perplexity figure of 1 billion tokens and 14 rule fixes in a day gives a concrete benchmark for what such audit loops can yield.

#Perplexity#Decider#OpenRouter#agents
Aravind Srinivas@AravSrinivasSource