Introducing Cursor Router, our intelligent model router that selects the right model for the task at hand. Router delivers frontier-quality results at 60% lower cost.
Cursor launches Cursor Router to cut model costs by 60%
Users can optimize routing for intelligence, balance, or cost.
95612.9K5802.8K1.6M
Original post
Cost Pressure
Internal tests show frontier results without always using the priciest option
A/B tests across millions of requests and early enterprise deployments reported 20% higher user satisfaction alongside 30-50% cost reductions versus routing everything to a single frontier model like Opus 4.8, with example Balance mode costs around $4.63 per commit.
Access Limits
Access remains gated while performance data stays internal
The feature launched today only for Teams and Enterprise customers, with no details released on individual or free plan availability and all performance numbers drawn solely from Cursor's own production traffic rather than independent benchmarks.
Sentiment
Positive users praise Cursor's new router for automatically choosing optimal AI models at lower cost and helping developers, while negative users call the feature unnecessary or overly controlling and insist on choosing models themselves.
Pos
73.2%
Neg
26.8%
140 comments with sentiment.
Cluster Engagement
Digg Deeper
No Digg Deeper questions have been answered for this story yet.
Related links
Posts from X
Most Activity
Most Activity
VIEWS109.5KLIKES582
Select Auto mode and whether you’d like to optimize for Intelligence, Balance, or Cost. Cursor Router analyzes each request and routes to the best model for the job: frontier models when the work demands them and price-efficient models when it doesn't.
Introducing Cursor Router, our intelligent model router that selects the right model for the task at hand. Router delivers frontier-quality results at 60% lower cost.
BOOKMARKS113RETWEETS28REPLIES30
Amazing to see. This is such a hard technical problem. Arguably AI complete ... (i.e. answering the question "what does the smartest model need to answer requires the smartest model to answer"). But the large model capabilities have become so jagged, there is clearly a lot of optimization to offer here. Very cool, excited to try it out.
Introducing Cursor Router, our intelligent model router that selects the right model for the task at hand. Router delivers frontier-quality results at 60% lower cost.
Cursor Router is available today across all surfaces on Teams and Enterprise plans. Admins can enable Router per team, allow or block certain models, set defaults, and disable select optimization modes for users. Learn more: http://cursor.com/blog/router
In early access, customers observed no drop-off in quality with a lower cost per commit vs. routing all requests to Opus 4.8.
All roads lead to: GPT 5.6 Sol
Select Auto mode and whether you’d like to optimize for Intelligence, Balance, or Cost. Cursor Router analyzes each request and routes to the best model for the job: frontier models when the work demands them and price-efficient models when it doesn't.
In early access, customers observed no drop-off in quality with a lower cost per commit vs. routing all requests to Opus 4.8.
Select Auto mode and whether you’d like to optimize for Intelligence, Balance, or Cost. Cursor Router analyzes each request and routes to the best model for the job: frontier models when the work demands them and price-efficient models when it doesn't.
Model routing is a first-class feature now.
Introducing Cursor Router, our intelligent model router that selects the right model for the task at hand. Router delivers frontier-quality results at 60% lower cost.
If you’re incentivized to push certain models, your router is merely a facade.
god no
Recommended reading. Cursor Router routes tasks to the right model. Is anyone building this as open-source? It feels like this is something you don't want to offload to an API. We all work with different trade-offs, so we need the ability to achieve custom routing.
Introducing Cursor Router, our intelligent model router that selects the right model for the task at hand. Router delivers frontier-quality results at 60% lower cost.
Offering an AI router while also building an AI model opens up some intriguing possibilities Imagine you send all idiots to Claude and GPT then keep the smart prompts for yourself
Introducing Cursor Router, our intelligent model router that selects the right model for the task at hand. Router delivers frontier-quality results at 60% lower cost.
i mean i guess that's technically a route. which makes it a router.
Introducing Cursor Router, our intelligent model router that selects the right model for the task at hand. Router delivers frontier-quality results at 60% lower cost.
@cursor_ai i will only execute `git add .` and `git commit -m "shit"` with fable level of intelligence.
In addition, something I have been building in my orchestrator system is to dynamically route to several models at once when needed. Or split the task to be handled by different models. I will share something similar I have been working on sometime this week.
Recommended reading. Cursor Router routes tasks to the right model. Is anyone building this as open-source? It feels like this is something you don't want to offload to an API. We all work with different trade-offs, so we need the ability to achieve custom routing.
wew
@cursor_ai It’s crazy to me that @github is not leading the game here.
Makes so much sense for Cursor to build this. Getting the “intelligent” part of intelligent model routing is going to be key, and I’m excited to try this out
Introducing Cursor Router, our intelligent model router that selects the right model for the task at hand. Router delivers frontier-quality results at 60% lower cost.
@cursor_ai nice!
We desperately need a smart model router. 1. We’re seeing a model explosion: GPT-5.6, Grok 4.5, Muse Spark 1.1, GLM-5.2, and Fable 5 all launched within the past month. 2. Even for a single model family like GPT-5.6, there're 3 (Sol, Terra, Luna) and 5 reasoning-effort levels. That is far too many decisions for users to make manually. The best model should be selected automatically based on the task, latency, quality, and cost.
@cursor_ai Cursor Router delivering frontier-quality results at 60% lower cost while analyzing each request and routing to the best model? Selecting Auto mode to optimize for Cost and seeing no drop-off vs Opus 4.8 is actually wild
@cursor_ai wow one of the best router which can be used to select the most efficient model as per the use case! @cursor_ai is litterally killing it!
@cursor_ai how is this difference to the auto that’s been there forever
Load more posts
@cursor_ai can I see what models end up getting used? the problem with auto mode in the past is I don’t trust you not to nerf me