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 custom model routers. Set your own routing rules in plain english: - "Send simple requests to minimax" - "Send planning tasks to Claude" - "Send bug fixes to Kimi k3" And every prompt gets auto-routed to the right model for the job. Here's how to make one:

Warp

57,769 subscribers

200,763 views • 4 days ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Warp now has custom routers 🔀 Automatically route tasks to models based on your own custom rulesets. - Route to your preferred models by complexity (easy through hard) - Or, route based on plain english rules. Ex. use one model for planning and another for well-scoped bugs

Warp now has custom routers 🔀 Automatically route tasks to models based on your own custom rulesets. - Route to your preferred models by complexity (easy through hard) - Or, route based on plain english rules. Ex. use one model for planning and another for well-scoped bugs

Warp

22,087 views • 1 month ago

Experimenting with custom auto routers for models in Warp. Configure with .yml, and describe what tasks should route to what model in plain english. This example routes frontend tasks to GLM 5.2 and complex architecture decisions to GPT 5.5 high. Wdyt?

Experimenting with custom auto routers for models in Warp. Configure with .yml, and describe what tasks should route to what model in plain english. This example routes frontend tasks to GLM 5.2 and complex architecture decisions to GPT 5.5 high. Wdyt?

Zach Lloyd

11,826 views • 1 month ago

Introducing the Send Cash feature on #Binance Pay! Your simple tool to send crypto and receive fiat seamlessly 🤝 Here’s how it works 👇

Introducing the Send Cash feature on #Binance Pay! Your simple tool to send crypto and receive fiat seamlessly 🤝 Here’s how it works 👇

Binance

168,572 views • 2 years 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

2,245,552 views • 2 months ago

Introducing: Auto Private Model Routing on June Choose Low, Balanced, or High. June picks the right model for every request. Defaults to zero data retention and private models. Powered by Venice. Free to try. Open source. MIT. Try June:

Introducing: Auto Private Model Routing on June Choose Low, Balanced, or High. June picks the right model for every request. Defaults to zero data retention and private models. Powered by Venice. Free to try. Open source. MIT. Try June:

OpenSoftware

111,495 views • 20 days ago

Using Google Labs with Veo 3 to make these. I created a GPT to help you get the right prompt to do this kind of stuff (for free). I'll send you the custom GPT I created if you comment SEND. Must be following so I can send it to you. (takes 15 seconds of work per video)

Using Google Labs with Veo 3 to make these. I created a GPT to help you get the right prompt to do this kind of stuff (for free). I'll send you the custom GPT I created if you comment SEND. Must be following so I can send it to you. (takes 15 seconds of work per video)

Murray Frost

101,090 views • 1 year ago

Introducing Pools! Pose a question. Set the buy in. Send to your friends, or share online. Super simple, and super fun! You can download Flipcash at

Introducing Pools! Pose a question. Set the buy in. Send to your friends, or share online. Super simple, and super fun! You can download Flipcash at

Flipcash

28,893 views • 1 year ago

Stop paying for 5 different AI subscriptions. ChatLLM by Abacus AI puts GPT-5.5, Claude 4.7, Gemini 3.1, DeepSeek-V4, Kimi-2.6 in one place. One prompt → routed to the best model → output. Pay once. Use all of them.

Stop paying for 5 different AI subscriptions. ChatLLM by Abacus AI puts GPT-5.5, Claude 4.7, Gemini 3.1, DeepSeek-V4, Kimi-2.6 in one place. One prompt → routed to the best model → output. Pay once. Use all of them.

Abacus.AI

26,751,775 views • 3 months ago

Make yourself useful for once and send for My attention 🤭 You surely don’t want to become one of My many message requests 🤣 Am I right , hand humper? Send. 🫶🏼

Sensitive content

Make yourself useful for once and send for My attention 🤭 You surely don’t want to become one of My many message requests 🤣 Am I right , hand humper? Send. 🫶🏼

.

24,717 views • 2 years ago

introducing SEND reach your perfect customers on every channel, with 1 prompt RIP to clunky dashboards, AI SDRs, and hours of setup :) Comment "SEND" & ill dm you a free month of the paid plan

introducing SEND reach your perfect customers on every channel, with 1 prompt RIP to clunky dashboards, AI SDRs, and hours of setup :) Comment "SEND" & ill dm you a free month of the paid plan

Finn Mallery

259,473 views • 2 months ago

Introducing annotations in v0. Click elements in your preview, add comments, then send them all to the agent as a single prompt.

Introducing annotations in v0. Click elements in your preview, add comments, then send them all to the agent as a single prompt.

v0

17,021 views • 1 month ago

Literally, the first transcription model that you can steer with a prompt. Send audio + a prompt. The model does what you ask. Universal 3 Pro from AssemblyAI is the world's first production model to support this. 2026 is off to a great start!

Literally, the first transcription model that you can steer with a prompt. Send audio + a prompt. The model does what you ask. Universal 3 Pro from AssemblyAI is the world's first production model to support this. 2026 is off to a great start!

Santiago

10,147 views • 5 months ago

this guy just wired kimi k3 directly into codex. the model is insanely good, but the app isn’t. so instead of using the kimi app, he connected his kimi subscription to codex through oauth. now kimi k3 shows up right inside the model picker alongside sol 5.6. no api key needed. no extra subscription either. just sign in with oauth through kimi code, and it’s ready to use. simple guides in the video and links below 👇

this guy just wired kimi k3 directly into codex. the model is insanely good, but the app isn’t. so instead of using the kimi app, he connected his kimi subscription to codex through oauth. now kimi k3 shows up right inside the model picker alongside sol 5.6. no api key needed. no extra subscription either. just sign in with oauth through kimi code, and it’s ready to use. simple guides in the video and links below 👇

MIKE

57,904 views • 21 days ago

Moonshot released Kimi K3 as an open-weight model. Most people saw “2.8 trillion parameters.” Far fewer understand what was actually built. We broke K3 into six visual explainers, simple enough for anyone to follow and detailed enough for engineers. Every video was generated in one shot by Simi, the fastest infra to generate explainer video in the entire world. Brought to you by Lamina Labs. Part 1/6: What Kimi K3 actually is.

Moonshot released Kimi K3 as an open-weight model. Most people saw “2.8 trillion parameters.” Far fewer understand what was actually built. We broke K3 into six visual explainers, simple enough for anyone to follow and detailed enough for engineers. Every video was generated in one shot by Simi, the fastest infra to generate explainer video in the entire world. Brought to you by Lamina Labs. Part 1/6: What Kimi K3 actually is.

Sudip

19,970 views • 12 days ago

How to use chatGPT to apply for jobs. Bookmark it for your next job application or send it to someone that’s job hunting. All the best 🙏

How to use chatGPT to apply for jobs. Bookmark it for your next job application or send it to someone that’s job hunting. All the best 🙏

SK the Plug 🔌 🇬🇧🇬🇧

568,747 views • 1 year ago

Trump is blasting Venezuelan ships out of the water to make himself feel tough. Either send the Coast Guard onto these ships or come to Congress for a declaration of war. Plain and simple.

Trump is blasting Venezuelan ships out of the water to make himself feel tough. Either send the Coast Guard onto these ships or come to Congress for a declaration of war. Plain and simple.

Senator Ruben Gallego

115,163 views • 9 months ago

If you live in the US, please take 30 seconds to send an auto-generated email to your Representative & Senators calling for a ceasefire. Tool at: Here's how easy it is:

If you live in the US, please take 30 seconds to send an auto-generated email to your Representative & Senators calling for a ceasefire. Tool at: Here's how easy it is:

jordan

358,558 views • 2 years ago

This approach has made Sonnet the model of choice for developers worldwide. In addition to our new model, we're launching Claude Code, our first coding tool, in a limited research preview. With Claude Code, you can delegate substantial tasks to Claude—right from your terminal.

This approach has made Sonnet the model of choice for developers worldwide. In addition to our new model, we're launching Claude Code, our first coding tool, in a limited research preview. With Claude Code, you can delegate substantial tasks to Claude—right from your terminal.

Anthropic

1,140,511 views • 1 year ago

Did you know you can stash your prompt in Claude Code? Ctrl+S saves your draft. Allows you to send a different prompt. Your saved draft is then auto-restored. No more copying to Notes. It's like git stash, but for your prompts.

Did you know you can stash your prompt in Claude Code? Ctrl+S saves your draft. Allows you to send a different prompt. Your saved draft is then auto-restored. No more copying to Notes. It's like git stash, but for your prompts.

Ado

171,310 views • 6 months ago