Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

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

481,433 subscribers

2,670,075 views • 1 month ago •via X (Twitter)

Science & Technology Education Health & Wellness

Anya Rossi• Live Now

Private livecam show

36 Comments

Cursor1 month ago

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.

Cursor1 month ago

In early access, customers observed no drop-off in quality with a lower cost per commit vs. routing all requests to Opus 4.8.

Cursor1 month ago

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:

ThePrimeagen1 month ago

i will only execute `git add .` and `git commit -m "shit"` with fable level of intelligence.

Zac Gottschall1 month ago

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

Elshayib1 month ago

Does it hurt you having it for pro users why only teams and enterprise?

Jaecoo1 month ago

@FreyaWPetersen

Denis Spirin1 month ago

I'll be honest with you guys, I will never use it for fear of a difficult request being routed to a midwit I have the midwit intelligence already, it is in front of the keyboard

Scott Chacon1 month ago

It’s crazy to me that @github is not leading the game here.

Palmer1 month ago

Damn that's neat I shared my router/orchestrator for Cursor I made with yall months ago 👀

Yuchen Jin1 month ago

nice!

Daniel Craft1 month ago

This is really cool! The Cursor Router looks like a great feature. Any chance it could be added for Pro subscribers too?

oscar1 month ago

bro you're just gonna put me on Gemini 3.5 all the time 😭

Aimar Haddadi1 month ago

so a team of 4 has access to it but a user on ultra who pays more than that team combined not? how does this make sense

Hamza1 month ago

why not for Pro will we get it?

Dimabytes1 month ago

What kind of bias are we talking about here? Like, I will see what models you pick and stop using auto or what...

Morgan1 month ago

@Scobleizer Very excited to try this!!

Pedro1 month ago

You can simply add an option where we can make a list of models we want to use, and the router only routes between those models. I don't want to use Grok 4.5 High and see the sub-agent using Fable for some tasks! The best option for me is for the Router to decide between using Grok 4.5 Medium and High and Composer 2.5, which is not possible right now, as it spawns any model it wishes in the middle of the task.

Haseeb Mir1 month ago

Wasnt Auto mode supposed to be doing that already?

NATE SCHNELL1 month ago

Everyone’s got a model router these days

Guney1 month ago

very nice work considering this

Monaco1 month ago

What if the task at hand is profitable trading? Can it help with that too? Asking for... a friend.

Tim Jayas1 month ago

i wont be surprised if all my work is routed to Grok now

Louis Amira1 month ago

lol add it to the list

maxwell1 month ago

how is this difference to the auto that’s been there forever

Entelligence AI1 month ago

Great to see more validation for model routing We've been exploring a similar problem from the infrastructure side, routing every coding task across providers and only escalating to frontier models when needed

X Girls1 month ago

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

Saad1 month ago

only teams and enterprise? what about plan subscribers? :(

Aman Grover1 month ago

When will we get this in the Pro account?

Bindu Reddy1 month ago

ROFL

Dany Boy1 month ago

Been working on @vynarisai for a while.

Robert Beall1 month ago

Please make this available to ultra subscribers and not just teams and enterprise. Walling off features like my machines automations, publishing canvases, and cursor router make me feel like a second class citizen.

Matthew Schwartz1 month ago

Just teams and enterprise?!

LLM Gateway1 month ago

Welcome to the battlefield 👋

Harry Strick1 month ago

but I like to fable max

John Moore1 month ago

Annoyed I can't use this w/ Ultra sub. Just saying!

Related Videos

Introducing Runway Media Router. The first preference-optimized router for generative media. Instead of hand-picking a model for every request, you define what "best" means once, for cost, quality, or latency, and the router selects the right video, image, or audio model automatically. Live now in Runway Dev.

Introducing Runway Media Router. The first preference-optimized router for generative media. Instead of hand-picking a model for every request, you define what "best" means once, for cost, quality, or latency, and the router selects the right video, image, or audio model automatically. Live now in Runway Dev.

Runway

62,291 views • 1 month ago

Introducing the Morph Model Router. It chooses the best model for each task in under 50ms. Keep frontier performance while lowering latency and cost. Available today in our API

Introducing the Morph Model Router. It chooses the best model for each task in under 50ms. Keep frontier performance while lowering latency and cost. Available today in our API

Morph

20,281 views • 3 months ago

Introducing model routing to Factory. Factory Router picks the right model for every task, automatically. Maintain frontier performance while cutting costs by 25%.

Introducing model routing to Factory. Factory Router picks the right model for every task, automatically. Maintain frontier performance while cutting costs by 25%.

Factory

2,262,109 views • 3 months ago

🚨 Frontier Model Router - Mix And Match All the Frontier LLMs Our most popular custom router is our frontier-model router that combines the best LLMs for all your tasks GPT 5.6 sol - data analysis Fable / Opus 4.8 - coding Flash 3.5 - summarization Grok 4.5 - real-time Pick your favorite LLMs for all your tasks. As of today the custom routers can be used in ANY harness - Abacus AI, Claude, Codex, Open-Code....

🚨 Frontier Model Router - Mix And Match All the Frontier LLMs Our most popular custom router is our frontier-model router that combines the best LLMs for all your tasks GPT 5.6 sol - data analysis Fable / Opus 4.8 - coding Flash 3.5 - summarization Grok 4.5 - real-time Pick your favorite LLMs for all your tasks. As of today the custom routers can be used in ANY harness - Abacus AI, Claude, Codex, Open-Code....

Bindu Reddy

4,592,609 views • 2 months ago

Treating every inference request the same is lighting money on fire. DigitalOcean Inference Router sends each request to the right model automatically–lower cost, faster response, and no quality tradeoff. Open-source engine. Drop-in API. Live since April. ✨

Treating every inference request the same is lighting money on fire. DigitalOcean Inference Router sends each request to the right model automatically–lower cost, faster response, and no quality tradeoff. Open-source engine. Drop-in API. Live since April. ✨

DigitalOcean

594,950 views • 3 months ago

Introducing Entelligence AI Model Router, dynamic turn based routing trained on engineering tasks that cuts costs by over 50% Automatically route every coding turn to the model with the best balance of quality, latency, and cost. Escalate to frontier models when they’re actually needed Balanced mode reduces spend by 46% per session Eco mode helps teams save > 76%

Introducing Entelligence AI Model Router, dynamic turn based routing trained on engineering tasks that cuts costs by over 50% Automatically route every coding turn to the model with the best balance of quality, latency, and cost. Escalate to frontier models when they’re actually needed Balanced mode reduces spend by 46% per session Eco mode helps teams save > 76%

Aiswarya Sankar

85,571 views • 1 month ago

Introducing EVO Router - a smart router that continuously optimizes and hill-climbs on your AI inference workloads. It learns from your code, prompts, production traffic, use cases, and SLAs, then searches for the best setup for every workload. That can mean more than choosing just a single model or routing through a classifier. EVO (YC F26) can optimize across model × provider combinations, fusion systems, cascades, routing policies, and prompts — whatever the workload allows, while staying within your quality, latency, and reliability constraints. As open-source models move closer to frontier-model performance, we believe this kind of workload-specific hill-climbing will become an important part of how AI systems are deployed and operated. Our early users have seen 30–60% lower inference costs across use cases ranging from complex multi-turn agents to asynchronous batch workloads. EVO Router has also reached the Pareto frontier on several benchmarks, outperforming existing setups on cost, quality, or both.

Introducing EVO Router - a smart router that continuously optimizes and hill-climbs on your AI inference workloads. It learns from your code, prompts, production traffic, use cases, and SLAs, then searches for the best setup for every workload. That can mean more than choosing just a single model or routing through a classifier. EVO (YC F26) can optimize across model × provider combinations, fusion systems, cascades, routing policies, and prompts — whatever the workload allows, while staying within your quality, latency, and reliability constraints. As open-source models move closer to frontier-model performance, we believe this kind of workload-specific hill-climbing will become an important part of how AI systems are deployed and operated. Our early users have seen 30–60% lower inference costs across use cases ranging from complex multi-turn agents to asynchronous batch workloads. EVO Router has also reached the Pareto frontier on several benchmarks, outperforming existing setups on cost, quality, or both.

Alok Bishoyi

15,996 views • 1 month ago

We shipped a major upgrade to the Auto Router: It now routes based on what the market actually uses for each type of task. When the market migrates a workload to a new model, the router follows within days. Benchmarks & more 👇

We shipped a major upgrade to the Auto Router: It now routes based on what the market actually uses for each type of task. When the market migrates a workload to a new model, the router follows within days. Benchmarks & more 👇

OpenRouter

40,219 views • 1 month ago

DigitalOcean Inference Router is now cache-aware. 🔀 Before, switching models mid-conversation meant losing your cache, and the savings and consistency it bought you. Now, Inference Router weighs that cost before switching. Set a model affinity header or routing budget for full control.

DigitalOcean Inference Router is now cache-aware. 🔀 Before, switching models mid-conversation meant losing your cache, and the savings and consistency it bought you. Now, Inference Router weighs that cost before switching. Set a model affinity header or routing budget for full control.

DigitalOcean

318,366 views • 23 days ago

Today we're releasing Not Diamond… The world’s most powerful AI model router. Not Diamond maximizes LLM output quality by automatically recommending the best LLM on every request at lower cost and latency. And it takes <5m to set up. Watch this to see how to start using it:

Today we're releasing Not Diamond… The world’s most powerful AI model router. Not Diamond maximizes LLM output quality by automatically recommending the best LLM on every request at lower cost and latency. And it takes <5m to set up. Watch this to see how to start using it:

Tomas Hernando Kofman

76,490 views • 2 years ago

Weave is launching the number 1 prompt router in the world. It enables you to get 70% more efficient use of your tokens. We analyzed millions of prompts and found that the vast majority don't need a frontier model. Weave Router fixes that. It analyzes your prompt and routes it to the highest quality model with the lowest cost (across open and closed source models). This all happens in your current workflow on Claude, Cursor or Codex so you don't have to change a thing. Early customers have seen an ~70% reduction in costs without any slowdowns. Source code available.

Weave is launching the number 1 prompt router in the world. It enables you to get 70% more efficient use of your tokens. We analyzed millions of prompts and found that the vast majority don't need a frontier model. Weave Router fixes that. It analyzes your prompt and routes it to the highest quality model with the lowest cost (across open and closed source models). This all happens in your current workflow on Claude, Cursor or Codex so you don't have to change a thing. Early customers have seen an ~70% reduction in costs without any slowdowns. Source code available.

Adam Cohen

26,019 views • 3 months ago

Introducing Smart Routing in Unity AI Gateway. Stop overpaying for AI. Smart Routing matches each coding task to the right model and harness based on what the task needs, so higher-cost models can differentiate on intelligence while lower-cost models differentiate on cost and performance. Match frontier quality and cut task costs by 30%+.

Introducing Smart Routing in Unity AI Gateway. Stop overpaying for AI. Smart Routing matches each coding task to the right model and harness based on what the task needs, so higher-cost models can differentiate on intelligence while lower-cost models differentiate on cost and performance. Match frontier quality and cut task costs by 30%+.

Databricks

125,783 views • 1 month ago

🚨 Same sales data. Same prompt. ~32% estimated lower cost. I put the exact same analysis through: Claude Opus 4.8 → $0.12 vs. GMI Router → Cost Mode → Gemini 3.7 Flash → ~$0.081 The task wasn't simple: 6 months of sales data across 4 products → trends, product performance, returns, anomalies, priorities + recommendations. GMI estimated ~$0.0387 savings (~32.3%) based on estimated token usage. And here's what caught my attention: I didn't choose Gemini. GMI Cloud 's Router did. For this workload, the routed output still covered the key analysis requirements. Same data. Same task. Different model selection. Lower estimated cost.

🚨 Same sales data. Same prompt. ~32% estimated lower cost. I put the exact same analysis through: Claude Opus 4.8 → $0.12 vs. GMI Router → Cost Mode → Gemini 3.7 Flash → ~$0.081 The task wasn't simple: 6 months of sales data across 4 products → trends, product performance, returns, anomalies, priorities + recommendations. GMI estimated ~$0.0387 savings (~32.3%) based on estimated token usage. And here's what caught my attention: I didn't choose Gemini. GMI Cloud 's Router did. For this workload, the routed output still covered the key analysis requirements. Same data. Same task. Different model selection. Lower estimated cost.

Altiam Kabir

32,603 views • 16 days ago

🚨 GMI estimated ~$0.11 in savings on one 3-step Python coding workflow. I gave GMI Router the same e-commerce codebase and split the work into 3 requests: 👉 Code analysis → Cost Mode → DeepSeek-V4-Flash → ~$0.046 saved 👉 Debugging → Balanced Mode → DeepSeek-V4-Flash → ~$0.042 saved 👉 Implementation + testing → Quality Mode → DeepSeek-V4-Flash → ~$0.019 saved Total: ~$0.11 estimated savings vs Claude Opus 4.8, based on GMI's estimated token usage. But here's what caught my attention: Router selected the same model for all 3 tasks — even though I changed the mode each time. And that's actually the point. GMI Cloud 's Router is cache-aware. When the same model can handle the next request, sticking with it can help preserve cache reuse and reduce cost. There's another reason: These tasks weren't especially difficult. So even in Quality Mode, Router didn't need to move to a heavier model. The result: 1 codebase. 3 tasks. 3 routing modes. 1 lightweight model. ~$0.11 estimated savings. This is why request-level routing is more interesting than simply assigning a different model to every task.

🚨 GMI estimated ~$0.11 in savings on one 3-step Python coding workflow. I gave GMI Router the same e-commerce codebase and split the work into 3 requests: 👉 Code analysis → Cost Mode → DeepSeek-V4-Flash → ~$0.046 saved 👉 Debugging → Balanced Mode → DeepSeek-V4-Flash → ~$0.042 saved 👉 Implementation + testing → Quality Mode → DeepSeek-V4-Flash → ~$0.019 saved Total: ~$0.11 estimated savings vs Claude Opus 4.8, based on GMI's estimated token usage. But here's what caught my attention: Router selected the same model for all 3 tasks — even though I changed the mode each time. And that's actually the point. GMI Cloud 's Router is cache-aware. When the same model can handle the next request, sticking with it can help preserve cache reuse and reduce cost. There's another reason: These tasks weren't especially difficult. So even in Quality Mode, Router didn't need to move to a heavier model. The result: 1 codebase. 3 tasks. 3 routing modes. 1 lightweight model. ~$0.11 estimated savings. This is why request-level routing is more interesting than simply assigning a different model to every task.

Anthara Fairooz

28,520 views • 16 days ago

🚨 Announcing Smart Model Router - Create Your Own Custom Router To Route To Your Favorite LLM - Route to GPT Sol, Muse Spark, Grok 4.5 and Fable - Optimize for cost or performance - Use Fable only for hard coding Once you create a router, you can use it on our Chat, Agent or in an API! Coming on Monday - Support for all CLI clients including Code, Claude Code and others

🚨 Announcing Smart Model Router - Create Your Own Custom Router To Route To Your Favorite LLM - Route to GPT Sol, Muse Spark, Grok 4.5 and Fable - Optimize for cost or performance - Use Fable only for hard coding Once you create a router, you can use it on our Chat, Agent or in an API! Coming on Monday - Support for all CLI clients including Code, Claude Code and others

Bindu Reddy

2,572,380 views • 2 months ago

DigitalOcean Inference Router is now available through OpenCode & setup is 3 steps. ☁️🆕🤝 Run/connect & it automatically routes to the right model for the job. No more paying frontier prices for a commit message.

DigitalOcean Inference Router is now available through OpenCode & setup is 3 steps. ☁️🆕🤝 Run/connect & it automatically routes to the right model for the job. No more paying frontier prices for a commit message.

DigitalOcean

20,992 views • 3 months ago

DeepSeek can see now in Codex!! Two days ago that was the only thing our router couldn't do. DeepSeek's API is still text only, so we stopped waiting and built it into the router ourselves. Drop a screenshot into Codex, same picker, same model, it reads it now!!!

DeepSeek can see now in Codex!! Two days ago that was the only thing our router couldn't do. DeepSeek's API is still text only, so we stopped waiting and built it into the router ourselves. Drop a screenshot into Codex, same picker, same model, it reads it now!!!

Ziwen

70,673 views • 1 month ago

We made Fable 5.1 compete against Entelligence Router on the same coding task. Both had the same harness and infra, and had to build a GeoGuessr-style game from scratch, implement the interactions, and verify everything in the browser. Fable 5.1: 21 min, $22.16 Entelligence Router: 21 min, $9 Fable delivered a strong result, although we did run into some overlay bugs along the way. Entelligence got the same task done at 59% lower cost.

We made Fable 5.1 compete against Entelligence Router on the same coding task. Both had the same harness and infra, and had to build a GeoGuessr-style game from scratch, implement the interactions, and verify everything in the browser. Fable 5.1: 21 min, $22.16 Entelligence Router: 21 min, $9 Fable delivered a strong result, although we did run into some overlay bugs along the way. Entelligence got the same task done at 59% lower cost.

Entelligence AI

16,627 views • 11 days ago

I'm excited to share we're shipping a new model router at today! Use 600+ models from 45 providers with a single API 🧵

I'm excited to share we're shipping a new model router at today! Use 600+ models from 45 providers with a single API 🧵

Tyler Barnes

56,369 views • 11 months ago

We built the cheapest AI Router Every model is discounted up to 81%! ZDR is available Try it ->

We built the cheapest AI Router Every model is discounted up to 81%! ZDR is available Try it ->

Fab

23,007,464 views • 13 days ago