今天我们正式推出 Cursor Router——这是我们面向团队和企业打造的智能模型路由系统。
Cursor Router 让团队能够自动将每个请求路由到最适合该任务的高性能模型,以更低成本获得前沿智能能力。
我们在数千名企业开发者的生产流量上观察到了极为强劲的效果。在与数十家企业合作的早期试用阶段,客户以大约 30%–50% 的成本降幅获得了前沿性能。


在覆盖数百万次请求的在线 A/B 测试中,Cursor Router 以节省 60% 成本的表现交付了前沿质量的性能。
Cursor 每周在各类模型和提供商之间路由数亿次编码请求,对用户偏好以及代码库中真正沉淀下来的内容拥有独特的洞察。模型中立一直是 Cursor 运作方式的核心,而今天我们把这些数据和专业能力应用到你的团队中。
借助 Cursor Router,我们的目标是为团队提供每项任务的最佳性能与体验,同时不必支付超出工作本身所需的成本。
工作原理
大约 60% 使用 Cursor 的开发者会选择单一模型作为日常主力。这导致常规工作以前沿价格完成,而 AI 支出增速远超输出质量的提升。Cursor Router 通过在模型运行之前对每个请求进行分类来解决这一问题。
从核心来看,Cursor Router 是一个分类器,它根据用户的查询将请求路由到最佳模型选项。我们在 60 万+ 条实时请求上训练了 Cursor Router,并在由 Cursor Router 引导的数百万条实时请求上进行了在线 A/B 测试来评估性能,以用户满意度(AFC)作为奖励进行优化。
Cursor Router 会基于查询内容、上下文、任务复杂度和领域来分析每个请求,并结合我们对每个模型行为特征的了解。我们学习每个模型最擅长的方面,并将请求路由到最有效的选项。简单工作交给性价比最高的模型,UI 更新交给品味最佳的模型,而更复杂、需要长周期推进的问题则交给前沿推理模型。
我们设计路由分类器时,所面向的是一个新版模型频繁快速发布的世界。这样一来,当更新、更强大的模型发布时,我们就能轻松更新 Cursor Router,让体验持续提升。
Cursor Router 在训练和评估两个环节都具备缓存感知能力。它训练所用的数据集包含因路由决策导致缓存未命中的情况,而在生产环境中的评估则意味着,我们所报告的成本节省已包含路由决策中缓存未命中的成本。
以更低成本获得前沿智能
Cursor Router 提供三种模式:Intelligence(智能)、Balance(均衡)和 Cost(成本),让你可以在成本与智能的帕累托前沿上自行选择所处位置。
我们发现,Auto Intelligence 模式在输出用户满意度上接近 Fable,同时为团队节省约 60% 的成本,并且在几乎相同的成本下,其满意度比 Opus 4.8 还高出约 15%。
同样,Auto Balance 模式在结果用户满意度上高于 Opus 4.8,同时成本降低约 36%。与 GPT-5.6 Sol 相比,Auto Balance 在更低花费下实现了相当的满意度。
我们选择通过大规模在线 A/B 测试而非离线评测来衡量路由器的效能。虽然离线评测是衡量质量的有效代理指标,但它们受限于样本规模小、与实际使用场景存在距离,以及难以将成功简化为一套评分标准等问题。
离线评测还忽略了因切换模型而产生的额外缓存未命中成本。真实的路由决策发生在整个对话过程中:选择哪个模型,以及何时切换。
在线 A/B 测试将 Cursor Router 置于真实世界中,经受数百万个任务和对话的检验。工程师们编写代码、追问后续问题、遇到报错、继续推进,一周内往往要经历数百次请求。这些才是模型路由器需要表现出色的真实场景。
在输出质量方面,我们衡量了以下指标:
- 用户满意度:根据用户反馈对智能体成功与否进行分类。用户继续推进下一个功能是强烈的正向信号,而纠正智能体则是强烈的负向信号。
- 留存率(Keep rate):即智能体生成的代码在一段时间后仍保留在代码库中的比例。
过去九个月里,我们一直依靠这些指标来评估每一次模型发布和工具链改进。
客户看到的效果
过去两周,Cursor Router 已面向部分企业客户开启早期访问。我们将他们实际支付的费用,与同等流量完全按 Opus 4.8 API 价格计费的情况进行了对比。
在早期访问中,三个拥有数千用户的高用量账户,在自动路由请求上相比全部路由到 Opus 4.8 节省了 30%–50% 的成本,且质量没有任何下降。


单次请求成本只是故事的一半。工程负责人更关心这些节省是否体现在实际交付的工作中,因此我们考察了单次提交(commit)的成本,结论依然成立。
就单次提交而言,我们观察到 Cursor Router 在 Intelligence 模式下的单次提交成本更低,为 6.76 美元;Balance 模式为 4.63 美元。
GPT-5.6 Sol 的成本与 Intelligence 模式相当,但用户对输出结果的满意度较低。与此同时,Fable 5 和 Opus 4.8 的提交成本相比 Cursor Router 存在溢价,分别为 12.69 美元和 7.34 美元。


这一差距正是路由的实际价值所在。Cursor Router 将困难任务保留给最强模型,同时把常规工作从前沿模型的定价中移开。
你来选择权衡
Cursor 在设计路由器时充分考虑了团队和大型组织的需求。路由器采用数据驱动的分类体系,同时管理员和终端用户仍可选择它在成本—智能帕累托前沿上的位置。
在模型选择器中选择 Auto 模式,并从三种优化模式中选取一种,即可沿前沿曲线移动:
- Intelligence:前沿质量,性能媲美最昂贵、最强大的模型——这些模型日常使用可能难以企及。
- Balance:扎实的质量,性能媲美大多数人喜欢日常使用的前沿模型。
- Cost:良好的质量,在优化 token 消耗的同时,达到可用的最高智能水平。
管理员可以决定 Cursor Router 如何在团队中推广。你可以按团队或分组启用它,选择成员可选的模式,设置默认模式,并允许或屏蔽特定模型。
接下来是什么
Cursor Router 是 Cursor 提升 token 效率的手段之一。选对模型固然重要,但前提是智能体本身保持精简,因此我们持续削减其运行框架中的冗余消耗。
动态工具调用是另一个典型案例:大多数原生工具描述不再被加载进每一条提示词中。模型在首次需要某个工具时才去查找其描述,这与我们处理 MCP 的方式一致。这样既能保持 read、edit 这类常用工具的热度,又让不常用的工具只在智能体真正调用时才进入提示词。
在推出 Cursor Router 的同时,我们也在不断提升模型池的下限与上限:Grok 4.5 拓宽了 Cursor Router 在更困难、更高成本任务上的可选范围。Composer 在日常路径上持续进步,让低成本调用也能接近前沿质量,而无需支付前沿价格。
Cursor Router 现已面向 Teams 和 Enterprise 套餐开放,覆盖桌面端、网页端、iOS、CLI 以及我们的 SDK。
更多详情请参阅我们的文档和更新日志。
相关文章
使用 Cursor for iOS 随时随地构建
Chris、Rikki 与 Kevin
为 Cursor Enterprise 推出组织功能
Today we're launching Cursor Router, our intelligent model router for teams and enterprises.
Cursor Router lets teams automatically route every request to the most capable model for the task, delivering frontier intelligence at a lower cost.
We've observed incredibly strong results on production traffic across thousands of enterprise developers. During our early access period with dozens of enterprises, customers got frontier performance at approximately 30–50% lower cost.


In online A/B tests across millions of requests, Cursor Router delivered frontier-quality performance at 60% savings.
Cursor routes hundreds of millions of coding requests each week across every model and provider, with unique visibility into what users like and what stays in the codebase. Model neutrality has always been core to how Cursor works, and today we're putting that data and expertise to work for your team.
With Cursor Router, our goal is to provide teams with the best performance and experience for every task, without spending more than the work requires.
How it works
Roughly 60% of developers using Cursor pick a single model as their daily driver. This results in routine work being completed at frontier prices, and AI spend growing much faster than output quality. Cursor Router fixes that by classifying each request before a model runs.
At its core, Cursor Router is a classifier that routes users to the best model option based on their query. We trained Cursor Router on 600k+ live requests and evaluated performance in an online A/B test across millions of live requests directed by Cursor Router, optimizing for user satisfaction (AFC) as a reward.
Cursor Router analyzes each request on query, context, task complexity, and domain, combined with what we know about each model's behavior. We learn what each model is best at, and route to the most effective option. Simple work goes to the most price-efficient models, UI updates go to the model with the best taste, and more complex, long-horizon problems go to frontier reasoning models.
We designed our routing classifier for a world in which updated models get shipped early and often. This way as newer and more powerful models are released, we can easily update Cursor Router, so the experience keeps improving.
Cursor Router is cache-aware in both how it is trained and evaluated. It is trained on a dataset where routing results in cache misses, and evaluated in production where our reported cost savings include the cost of cache misses in routing decisions.
Frontier intelligence at lower cost
Cursor Router has three modes: Intelligence, Balance, and Cost which let you adjust where you are on the cost-intelligence Pareto frontier.
We found that Auto Intelligence mode lands near Fable on user satisfaction of output at about 60% lower cost for teams, while also lifting satisfaction about 15% over Opus 4.8 at nearly the same cost.
Similarly, Auto Balance lands above Opus 4.8 on user satisfaction with the results at about 36% lower cost. Against GPT-5.6 Sol, Auto Balance delivers comparable satisfaction at a lower spend rate.
We chose to measure the efficacy of our router using large online A/B tests instead of offline evals. While offline evals are useful proxies for quality, they're limited by their small size, their distance from real-world usage, and the difficulty of reducing success to a rubric.
Offline evals also omit the extra cache-miss cost that comes from switching models. Real routing happens across a conversation: which model to pick, and when to switch.
Online A/B tests put Cursor Router to test in the real world across millions of tasks and conversations. Engineers write code, ask follow-ups, hit errors, and keep going, often across hundreds of requests in a week. Those are the conditions under which a model router needs to perform well.
In terms of quality of output, we measured:
- User satisfaction, classifying agent success based on user responses. Moving on to the next feature is a strong positive signal, while correcting the agent is a strong negative one.
- Keep rate, or how much of the agent-generated code remains in the codebase over time.
We have relied on these metrics to evaluate every model launch and harness improvement in the past nine months.
What customers are seeing
Over the past two weeks, Cursor Router has been in early access with a selection of enterprise customers. We compared what they actually paid against the same traffic, priced entirely at Opus 4.8 API rates.
In early access, three high-volume accounts with thousands of users saved 30%–50% on Auto-routed requests versus routing everything to Opus 4.8, with no decrease in quality.


Cost per request is only half the story. Engineering leaders care whether those savings show up in real shipped work, so we looked at cost per commit, and the pattern held.
For a single commit, we observed Cursor Router had a lower cost per commit of $6.76 for Intelligence mode and $4.63 for Balance.
GPT-5.6 Sol matched the cost of Intelligence but had lower user satisfaction with the output. Meanwhile, Fable 5 and Opus 4.8 produced commits at a cost premium to Cursor Router at $12.69 and $7.34 respectively.


That gap is the practical case for routing. Cursor Router keeps hard tasks on the most capable models and moves routine work off of frontier pricing.
You choose the tradeoff
Cursor designed our router with teams and large organizations in mind. The router uses a data-driven taxonomy, while admins and end users can still choose where it sits on the cost-intelligence Pareto frontier.
Select Auto mode in the model picker, and choose from three optimization modes that move you along the frontier:
- Intelligence: Frontier quality, with performance matching the most expensive and powerful models that might be out of reach for daily use.
- Balance: Strong quality, with performance matching the frontier models that most people like to daily drive.
- Cost: Good quality, reaching the highest available intelligence while optimizing token spend.
Admins can decide how Cursor Router rolls out across teams. You can enable it per team or group, choose which modes members can select, set the default, and allow or block specific models.
What’s next
Cursor Router is one piece of how Cursor drives token efficiency. Choosing the right model only matters if the agent itself stays lean, so we keep cutting waste in the harness around it.
Dynamic tool calling is another clear example where most native tool descriptions are no longer loaded into every prompt. The model looks them up the first time it needs them, following the same pattern we already use for MCPs. This keeps common tools like read and edit hot while less commonly used tools only enter the prompt when the agent actually calls them.
Alongside Cursor Router, we keep raising the floor and the ceiling of the model pool: Grok 4.5 widens what Cursor Router can draw from on harder, higher-cost work. Composer keeps getting better on the everyday path, so lower cost turns stay close to frontier quality without paying frontier prices.
Cursor Router is available today for Teams and Enterprise plans across desktop, web, iOS, CLI, and our SDK.
Read more in our docs and changelog.
Related posts
Build from anywhere with Cursor for iOS
Chris, Rikki & Kevin
Introducing organizations for Cursor Enterprise