来源：Cursor 路由器发布文章：https://cursor.com/blog/router，Cursor 路由器更新日志：https://cursor.com/changelog/router，Grok 4.5 公告：https://cursor.com/blog/grok-4-5 以及 X 上的 @cursor_ai：https://x.com/cursor_ai/status/2079993729532989500。
Michal Sutter 是一名数据科学专业人士，拥有意大利帕多瓦大学的数据科学理学硕士学位。凭借在统计分析、机器学习和数据工程方面的坚实基础，Michal 擅长将复杂的数据集转化为可操作的洞察。
创建一个能动事件场地运营者 [完整代码]：https://pxllnk.co/twdn5
谢谢！我们的团队会尽快联系你 🙌
Cursor has made Cursor Router：https://cursor.com/blog/router generally available for Teams and Enterprise plans. The system is a classifier that inspects each request before a model runs, then dispatches it to the model best suited to that specific task. The cursor team reports frontier-quality performance at 60% savings in online A/B tests, and 30–50% savings for early-access enterprise accounts.
The problem it targets is a spend pattern rather than a capability gap. Cursor states that roughly 60% of its developers pick a single model as a daily driver . Routine work therefore gets completed at frontier prices, and AI spend grows faster than output quality. Routing is Cursor’s answer to that mismatch.
Cursor Router is not a fallback chain or a retry mechanism. It is a classifier trained on 600k+ live requests , evaluated in an online A/B test across millions of live requests, and optimized for user satisfaction (AFC) as its reward signal.
For each request, the router analyzes four inputs: query, context, task complexity, and domain . It combines these with learned knowledge of each model’s behavior. Cursor publishes three routing rules that follow from that classification:
That third rule carries the weight of the cost argument. The savings do not come from downgrading hard problems. They come from removing routine work from frontier pricing while the difficult tier stays intact.
One implementation detail deserves attention from anyone who has built a router. Cursor Router is cache-aware in both training and evaluation . It is trained on a dataset where routing produces cache misses, and the reported cost savings include the cost of those cache misses. Switching models mid-conversation invalidates prompt cache, and that cost is real. Routers that ignore it overstate their savings.
The classifier was also designed for model churn. Cursor states it can update the router as newer models ship, which matters in a market where the frontier moves monthly.
Every figure below is taken from Cursor’s launch post and changelog (July 22, 2026). Values Cursor did not publish are marked as such.
Cursor deliberately avoided offline evals as its primary measurement. Its stated reasoning is that offline evals suffer from small sample size, distance from real-world usage, and the difficulty of reducing success to a rubric. They also omit the cache-miss cost incurred when switching models.
Real routing happens across a conversation, not a single turn. Developers write code, ask follow-ups, hit errors, and continue, often across hundreds of requests in a week. The router must decide both which model to pick and when to switch.
Two quality metrics carry the evaluation:
Cursor team states it has used both metrics to evaluate every model launch and harness improvement for the past nine months. This is a meaningful credibility marker: the metrics predate the product they are now being used to justify.
Auto mode now exposes three optimization settings that move the user along the cost–intelligence Pareto frontier.
Cost per request is only part of the picture, so Cursor also measured cost per commit :
GPT-5.6 Sol matched the cost of Intelligence mode but produced lower user satisfaction. Cursor did not publish an exact per-commit figure for it.
Cursor Router ships across desktop, web, iOS, CLI, and the Cursor SDK. It is on by default for Teams plans . Enterprise admins enable it from the dashboard.
The changelog：https://cursor.com/changelog/router specifies the admin surface: per-team and per-group enablement, restrictions on which optimization modes members can select, a configurable default mode, and model allow and block lists. Soft and hard enforcement options exist for standardizing on Auto. The routed model can be displayed or hidden, and it is hidden by default — teams that want routing transparency must opt in.
Two constraints are important for procurement. First, Grok 4.5 is required as a price-efficient routing option , so the model block list cannot be used to exclude it. Grok 4.5：https://cursor.com/blog/grok-4-5, released July 8, is priced at $2/M input and $6/M output tokens, with a fast variant at $4/M and $18/M. Second, Balance and Intelligence bill at the routed model’s rate , so unit cost varies with each routing decision rather than settling at a flat price.
Sources: Cursor Router launch post：https://cursor.com/blog/router, Cursor Router changelog：https://cursor.com/changelog/router, Grok 4.5 announcement：https://cursor.com/blog/grok-4-5 and @cursor_ai on X：https://x.com/cursor_ai/status/2079993729532989500.
Michal Sutter is a data science professional with a Master of Science in Data Science from the University of Padova. With a solid foundation in statistical analysis, machine learning, and data engineering, Michal excels at transforming complex datasets into actionable insights.
Build an Agentic Event Venue Operator [Full Codes]：https://pxllnk.co/twdn5
扫码直达文章详情