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.

OpenRouter now runs inside Render Workflows. Stop putting LLM batches in your web service. Each prompt becomes its own task run, queued, retried, and fanned out by Render, with the model call routed by OpenRouter.

OpenRouter

140,361 subscribers

121,013 views • 9 days ago •via X (Twitter)

Science & Technology Education News & Politics

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

MiniMax H3 Max is now live on OpenRouter: faster and cheaper than H3. Same prompt, side by side: ready in ~30 seconds instead of ~3.5 minutes, and $0.40 for the clip instead of $0.65.

MiniMax H3 Max is now live on OpenRouter: faster and cheaper than H3. Same prompt, side by side: ready in ~30 seconds instead of ~3.5 minutes, and $0.40 for the clip instead of $0.65.

OpenRouter

28,381 views • 8 days ago

A highly-requested feature: web search now returns citations in the API 🌐 We've standardized them for all models, including native online models like OpenAI's web tool and Perplexity:

A highly-requested feature: web search now returns citations in the API 🌐 We've standardized them for all models, including native online models like OpenAI's web tool and Perplexity:

OpenRouter

17,451 views • 1 year ago

The new open-weights Hailuo AI (MiniMax) H3 is live on OpenRouter thanks to MiniMax (official)! H3 is a lightweight video model for text, image, audio, & video input, with native audio-visual output. Built for instruction-led edits, text/brand rendering, and video-2-video motion transfer.

OpenRouter

22,767 views • 1 month ago

Claude Sonnet 4.5 is live on OpenRouter! Substantial gains on coding and math over Opus 4.1, but at normal Sonnet prices. More info and benchmarks 👇

Claude Sonnet 4.5 is live on OpenRouter! Substantial gains on coding and math over Opus 4.1, but at normal Sonnet prices. More info and benchmarks 👇

OpenRouter

38,208 views • 11 months ago

Introducing "create-agent-tui" A skill for building your own agent harness + terminal UI (TUI). The skill walks you through 4 different ways of customizing the look, and supports dozens of optional features 👇

Introducing "create-agent-tui" A skill for building your own agent harness + terminal UI (TUI). The skill walks you through 4 different ways of customizing the look, and supports dozens of optional features 👇

OpenRouter

227,401 views • 4 months ago

We are launching a new stealth model - "Andromeda Alpha" This is a smaller reasoning model that has been trained to be really good at image understanding.

We are launching a new stealth model - "Andromeda Alpha" This is a smaller reasoning model that has been trained to be really good at image understanding.

OpenRouter

42,403 views • 10 months ago

Here are the steps to create this animation: 1. Design and model your own mech in Plasticity. 2. Import the model into the animation software 3ds Max. 3. Create the animation on your own. 4. Render and export the monochrome model animation. 5. Make the final render for reference. 6. Use Seedance 2 to re-render your monochrome model animation according to the reference render you provided. Summary: In this workflow, Seedance 2 acts as a renderer that saves you hours of rendering time. All other work has to be done manually by yourself. Don’t blindly believe that AI can fully produce mech animations for you — it simply cannot do that.

Here are the steps to create this animation: 1. Design and model your own mech in Plasticity. 2. Import the model into the animation software 3ds Max. 3. Create the animation on your own. 4. Render and export the monochrome model animation. 5. Make the final render for reference. 6. Use Seedance 2 to re-render your monochrome model animation according to the reference render you provided. Summary: In this workflow, Seedance 2 acts as a renderer that saves you hours of rendering time. All other work has to be done manually by yourself. Don’t blindly believe that AI can fully produce mech animations for you — it simply cannot do that.

LAS91214

47,667 views • 3 months ago

Introducing a ludicrous-speed provider: Watch an animation generate instantly for ~$0.001, at over 1.8k TPS 🤯

Introducing a ludicrous-speed provider: Watch an animation generate instantly for ~$0.001, at over 1.8k TPS 🤯

OpenRouter

115,225 views • 1 year ago

Real-time image editing is insanely good for architecture. You can take a sketch, render a photorealistic building, and then change the materials, weather, or environment by simply adjusting the prompt. Done with the new KREA AI model in seconds 🤯

Real-time image editing is insanely good for architecture. You can take a sketch, render a photorealistic building, and then change the materials, weather, or environment by simply adjusting the prompt. Done with the new KREA AI model in seconds 🤯

Justine Moore

181,851 views • 7 months ago

Seedance 2.5 is now available on CapCut. Create and edit AI videos in one seamless workflow. What stands out: • More controllable video generation and editing • Timestamp-based storyline control • Support for up to 50 reference images • Generate videos up to 90 seconds • Viewport render and green screen workflows • Enhanced multilingual performance From your first prompt to the final edit, everything stays inside CapCut. Try it here: 🌐 Web: 📱 App: #CapCut #Seedance25 #CapCutai #CapCutDidThat

Seedance 2.5 is now available on CapCut. Create and edit AI videos in one seamless workflow. What stands out: • More controllable video generation and editing • Timestamp-based storyline control • Support for up to 50 reference images • Generate videos up to 90 seconds • Viewport render and green screen workflows • Enhanced multilingual performance From your first prompt to the final edit, everything stays inside CapCut. Try it here: 🌐 Web: 📱 App: #CapCut #Seedance25 #CapCutai #CapCutDidThat

Akash

16,037 views • 1 month ago

1/3 🤖 Meet AgentOS: A Token-efficient, Microkernel AI agent with on-device model routing across CLI, Web UI, and chat. A local router reads every message on your device and sends it to the cheapest model that can still do the job well. You stop overpaying for AI. ⚡ What makes it stand out: ■ Smart on-device model routing across 20+ providers ( bankrbot LLM Gateway, OpenRouter, OpenAI, Anthropic, Ollama, and more). ■ Persistent local memory that survives restarts. ■ A layered security sandbox (Standard, Strict, Locked). ■ 37 built-in skills plus MCP, loaded only when a task needs them, and more ■ One unified gateway for CLI, Web UI, Slack, Telegram, Discord, and more Remember this: AgentOS has been integrated with the Bankr LLM Gateway since day one. That means any Bankr user with Bankr API key can start using AgentOS in minutes. Let the router cook.

1/3 🤖 Meet AgentOS: A Token-efficient, Microkernel AI agent with on-device model routing across CLI, Web UI, and chat. A local router reads every message on your device and sends it to the cheapest model that can still do the job well. You stop overpaying for AI. ⚡ What makes it stand out: ■ Smart on-device model routing across 20+ providers ( bankrbot LLM Gateway, OpenRouter, OpenAI, Anthropic, Ollama, and more). ■ Persistent local memory that survives restarts. ■ A layered security sandbox (Standard, Strict, Locked). ■ 37 built-in skills plus MCP, loaded only when a task needs them, and more ■ One unified gateway for CLI, Web UI, Slack, Telegram, Discord, and more Remember this: AgentOS has been integrated with the Bankr LLM Gateway since day one. That means any Bankr user with Bankr API key can start using AgentOS in minutes. Let the router cook.

AgentOS

204,440 views • 1 month ago

Gemini Omni doesn’t just allow you to render text more accurately — but to create it in sync with your visuals. 🎥 Choose your type, placement, animation, exposure and more. Prompt for this video: Word by word, one word on the screen at a time: did, you, know, that, this, model, can, do, pretty, good, text!? each word appears with a different animated style, perfect pacing to a rhythm, sizzle reel.

Gemini Omni doesn’t just allow you to render text more accurately — but to create it in sync with your visuals. 🎥 Choose your type, placement, animation, exposure and more. Prompt for this video: Word by word, one word on the screen at a time: did, you, know, that, this, model, can, do, pretty, good, text!? each word appears with a different animated style, perfect pacing to a rhythm, sizzle reel.

Google

153,685 views • 3 months ago

🚨BREAKING: China just released an AI employee that runs on your own computer. It can search the web, write code, build websites, make slides, and create videos. All by itself. It even comes with its own built-in computer. 100% Open Source.

🚨BREAKING: China just released an AI employee that runs on your own computer. It can search the web, write code, build websites, make slides, and create videos. All by itself. It even comes with its own built-in computer. 100% Open Source.

Hasan Toor

20,679 views • 5 months ago

/agent can now run thousands of queries simultaneously 🔥 With Parallel Agents, powered by our newest model Spark-1 Fast, you can batch enrich massive datasets in minutes. Just write your prompt, hit run, and watch as data populates in real-time in our playground.

/agent can now run thousands of queries simultaneously 🔥 With Parallel Agents, powered by our newest model Spark-1 Fast, you can batch enrich massive datasets in minutes. Just write your prompt, hit run, and watch as data populates in real-time in our playground.

Firecrawl

20,731 views • 7 months ago

I mastered this in 10 minutes. Now you can too. Hyper-realistic, "product-in-hand" UGC with natural motion—built entirely via AI. The Setup: - Tech: VEO + Kling AI - Cost: $0 - Speed: Minutes to render Stop paying creators. Start scaling workflows that clone viral aesthetics and swap in your product seamlessly. Want the full workflow? RT this post, Comment "VEO" below

I mastered this in 10 minutes. Now you can too. Hyper-realistic, "product-in-hand" UGC with natural motion—built entirely via AI. The Setup: - Tech: VEO + Kling AI - Cost: $0 - Speed: Minutes to render Stop paying creators. Start scaling workflows that clone viral aesthetics and swap in your product seamlessly. Want the full workflow? RT this post, Comment "VEO" below

Cas.Fyn

21,560 views • 4 months ago

AN ANTHROPIC SYSTEM TURNS ONE PROMPT INTO A COMPLETE GRAPH MODEL BUILT ENTIRELY ON ITS OWN One prompt is enough to spin up the full architecture, no schema written by hand, no roles assigned in advance. Parallel workers process every branch of the graph at once, each one handling its own slice independently. As each worker finishes, its output compacts straight into a single unified project instead of scattered fragments. Nothing needs stitching together manually, the compaction step folds every worker's result into one file automatically. The whole build runs end to end without a single manual step between the prompt and the finished project. See the full build and compact pipeline below👇

AN ANTHROPIC SYSTEM TURNS ONE PROMPT INTO A COMPLETE GRAPH MODEL BUILT ENTIRELY ON ITS OWN One prompt is enough to spin up the full architecture, no schema written by hand, no roles assigned in advance. Parallel workers process every branch of the graph at once, each one handling its own slice independently. As each worker finishes, its output compacts straight into a single unified project instead of scattered fragments. Nothing needs stitching together manually, the compaction step folds every worker's result into one file automatically. The whole build runs end to end without a single manual step between the prompt and the finished project. See the full build and compact pipeline below👇

wast3

18,442 views • 1 month ago

Tired of manual prompt tweaking? Watch the latest Llama tutorial on how to optimize your existing GPT or other LLM prompts for Llama with `llama-prompt-ops`, the open-source Python library! In this video, Partner Engineer Justin Lee demonstrates installation, project setup, migrating your first prompt, and analyzing performance gains. Watch now to discover: ✨ Why systematic prompt optimization is crucial for migrating from GPT to Llama. 💻 A live code walkthrough of `llama-prompt-ops` in action for a customer service classification task. Watch the full tutorial here:

Tired of manual prompt tweaking? Watch the latest Llama tutorial on how to optimize your existing GPT or other LLM prompts for Llama with `llama-prompt-ops`, the open-source Python library! In this video, Partner Engineer Justin Lee demonstrates installation, project setup, migrating your first prompt, and analyzing performance gains. Watch now to discover: ✨ Why systematic prompt optimization is crucial for migrating from GPT to Llama. 💻 A live code walkthrough of `llama-prompt-ops` in action for a customer service classification task. Watch the full tutorial here:

Meta for Developers

38,166 views • 1 year ago

🚨 JUST IN: CHINA just released an AI EMPLOYEE that works 24X7 on its own. 100% OPEN SOURCE. It researches, codes, builds websites, creates slide decks, and generates videos. All by itself. All on your computer. It's called DeerFlow. You give it a task. It makes a plan, spins up its own team of sub-agents, and gets to work. You come back and there's a finished deliverable waiting. Not a draft. Not a summary. The actual thing. Not a chatbot. Not a research assistant. An AI with its own computer that works while you sleep. Here's what it does on its own: → Spawns multiple sub-agents in parallel, each tackling a different piece of your task, then combines everything into one finished output → Writes real code, runs it, reads the results, and fixes its own mistakes without asking you once → Builds slide decks, websites, full research reports, and data dashboards from scratch → Remembers you across sessions. Your writing style. Your tech stack. Your preferences. Gets better every time. → Reads files you upload, works with them inside its own filesystem, hands you clean finished outputs → Searches the web, runs commands, calls any tool you plug in Here's how it thinks: You give one instruction. The lead agent makes a plan. Sub-agents fan out and work in parallel. Results come back. Everything gets synthesized. You get a deliverable. A single research task might split into a dozen sub-agents, each exploring a different angle, then converge into one finished website with generated visuals. Here's the wildest part: DeerFlow 2.0 launched on February 28th 2026 and hit number 1 on all of GitHub Trending the same day. Version 2.0 was a complete rewrite. Zero shared code with version 1. Because users kept using it for things the team never intended. Data pipelines. Dashboards. Entire content workflows. The community told them what it needed to become. So they burned it down and rebuilt it. 22.7K GitHub stars. 2.7K forks. Built by ByteDance 100% Open Source. MIT License.

🚨 JUST IN: CHINA just released an AI EMPLOYEE that works 24X7 on its own. 100% OPEN SOURCE. It researches, codes, builds websites, creates slide decks, and generates videos. All by itself. All on your computer. It's called DeerFlow. You give it a task. It makes a plan, spins up its own team of sub-agents, and gets to work. You come back and there's a finished deliverable waiting. Not a draft. Not a summary. The actual thing. Not a chatbot. Not a research assistant. An AI with its own computer that works while you sleep. Here's what it does on its own: → Spawns multiple sub-agents in parallel, each tackling a different piece of your task, then combines everything into one finished output → Writes real code, runs it, reads the results, and fixes its own mistakes without asking you once → Builds slide decks, websites, full research reports, and data dashboards from scratch → Remembers you across sessions. Your writing style. Your tech stack. Your preferences. Gets better every time. → Reads files you upload, works with them inside its own filesystem, hands you clean finished outputs → Searches the web, runs commands, calls any tool you plug in Here's how it thinks: You give one instruction. The lead agent makes a plan. Sub-agents fan out and work in parallel. Results come back. Everything gets synthesized. You get a deliverable. A single research task might split into a dozen sub-agents, each exploring a different angle, then converge into one finished website with generated visuals. Here's the wildest part: DeerFlow 2.0 launched on February 28th 2026 and hit number 1 on all of GitHub Trending the same day. Version 2.0 was a complete rewrite. Zero shared code with version 1. Because users kept using it for things the team never intended. Data pipelines. Dashboards. Entire content workflows. The community told them what it needed to become. So they burned it down and rebuilt it. 22.7K GitHub stars. 2.7K forks. Built by ByteDance 100% Open Source. MIT License.

Kanika

738,832 views • 5 months ago

Grok 4.5 in Grok Build created an FPS game in under an hour. The prompt was simple. I told it to write a game design document and pull free assets from the web. Then I had it create a TODO.md with implementation phases and run a loop to build out each phase. SpaceXAI and Cursor cooked here. This model is insane.

Grok 4.5 in Grok Build created an FPS game in under an hour. The prompt was simple. I told it to write a game design document and pull free assets from the web. Then I had it create a TODO.md with implementation phases and run a loop to build out each phase. SpaceXAI and Cursor cooked here. This model is insane.

tetsuo

1,815,578 views • 2 months ago

New open-source agent harness just landed! I got early access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the model, and open source matters here because you can inspect the loop, run it on your own infrastructure, and swap to the latest or cheaper models. TrueForge handles the runtime work that makes an agent reliable. It drives the tool-calling loop, manages context, coordinates subagents, and executes code in a sandbox, with any model you choose. Every tool call re-sends the growing context to the model, so in practice the harness controls most of what an agent costs to run. A few things stood out from my testing and their published benchmarks. Vendor-Neutral by design. It runs OpenAI, Anthropic, and Google models alongside open-weight models like Kimi, GLM, and DeepSeek. Model routing is a setting, and you can send each task to the model that fits it. On a 14-task enterprise agent benchmark, it matched the accuracy of Claude Managed Agents running the same Opus 4.8 model at roughly 30% lower cost per run (3.8M tokens vs 10M for the same answers). Routing the same tasks to GLM-5.2 held accuracy and brought cost down by about 75%, around $3 per run instead of $12. Fully self-hosted and Open Source (MIT License). I had it running locally with one command, with sandboxed code execution working out of the box. It's time to own your agent harness. Thanks to TrueFoundry for partnering on this post.

New open-source agent harness just landed! I got early access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the model, and open source matters here because you can inspect the loop, run it on your own infrastructure, and swap to the latest or cheaper models. TrueForge handles the runtime work that makes an agent reliable. It drives the tool-calling loop, manages context, coordinates subagents, and executes code in a sandbox, with any model you choose. Every tool call re-sends the growing context to the model, so in practice the harness controls most of what an agent costs to run. A few things stood out from my testing and their published benchmarks. Vendor-Neutral by design. It runs OpenAI, Anthropic, and Google models alongside open-weight models like Kimi, GLM, and DeepSeek. Model routing is a setting, and you can send each task to the model that fits it. On a 14-task enterprise agent benchmark, it matched the accuracy of Claude Managed Agents running the same Opus 4.8 model at roughly 30% lower cost per run (3.8M tokens vs 10M for the same answers). Routing the same tasks to GLM-5.2 held accuracy and brought cost down by about 75%, around $3 per run instead of $12. Fully self-hosted and Open Source (MIT License). I had it running locally with one command, with sandboxed code execution working out of the box. It's time to own your agent harness. Thanks to TrueFoundry for partnering on this post.

elvis

11,303 views • 22 days ago