Make a Runway Clone in one shot, or something else!

Backboard.io co-founder Jon announced that video generation models are now live on the Backboard platform, including ByteDance's Seedance family served through OpenRouter alongside models like Veo 3.1, Wan 3.0, Kling 3.0, Hailuo 3 and Grok Imagine. The integration handles provider job APIs, polling and storage server-side so developers can generate video through the same add_message call used for text, with clips returned in generated_media and persisted in the conversation thread.

i'm jon, i co-founded backboard.io https://backboard.io . this is a launch post. it's short and there's code. video models are live on backboard. Here is a video of me and my dog rapping if you don't believe me. ByteDance's Seedance family is in, served through OpenRouter, along with the rest of the OpenRouter video catalog. that's the news. here's why you should care. text you've figured out. images, mostly. video is where it gets ugly. every provider has its own job api. submit. get an id. poll. poll again. time out. retry. download the file. store it somewhere. pass a url back to your agent. hope the agent remembers what it made two turns ago. that's a whole service. for one feature. and it's different for every model. so we built it once. same way we did memory, rag, routing, voice and image. ByteDance Seedance bytedance/seedance-2.5 up to 30s, with audio bytedance/seedance-2.0 bytedance/seedance-2.0-fast bytedance/seedance-2.0-mini the rest of the OpenRouter video catalog Veo 3.1, Wan 3.0, Kling 3.0, Hailuo 3, Grok Imagine and more client.list video models shows exactly what's live and what each model supports. client.get video model model id gives you one model's limits. six ways in: text to video first frame to video animate an image first and last frame video to video edit, extend, upscale references images, audio or video as a guide mixed references it's the add message call you already make. four extra keys. python import asyncio import os from backboard import BackboardClient settings = { "llm provider": "openai", "model name": "gpt-4.1", "video generation": "auto", "video model provider": "openrouter", "video model name": "bytedance/seedance-2.0-fast", "video config": {"duration": 5, "aspect ratio": "16:9", "resolution": "720p"}, } async def main : client = BackboardClient api key=os.environ "BACKBOARD API KEY" , timeout=1900 assistant = await client.create assistant name="video assistant" thread = await client.create thread assistant.assistant id thread id = str thread.thread id result = await client.add message thread id, content="a paper boat drifting down a rainy city gutter, golden hour", stream=False, settings, for message in result.messages: for media in message.get "generated media" or : print media "document id" , media "url" asyncio.run main no job queue. no polling loop. we poll for you, for up to 30 minutes, and hand back the clip. every clip comes back in generated media with a document id and a url. it lives in the thread. next to the memory. next to everything else your agent already knows. want to animate an image instead? add a file. result = await client.add message thread id, content="slow push in, steam rising off the coffee", files= "start.png" , stream=False, settings, two files is first frame plus last frame. an .mp4 is video to video. the clip isn't a loose file. it's in the conversation. so the next turn can just be: await client.add message thread id, content="same shot, but at night. neon reflections in the water.", stream=False, settings, no re-uploading. no passing urls around. the agent knows what it made, because it made it in the same thread. video generation="auto" hands your assistant a generate video tool. it calls it when the ask needs a video. it won't render one because you said hi. stream=True and a long client timeout. we use 1900 seconds. video config covers duration, resolution, aspect ratio, size, audio, seed, upscale and provider routing. only where the model supports it. check get video model first. operation="generate video" . swap bytedance/seedance-2.0-fast for google/veo-3.1-fast . one string. nothing else moves. that's the whole backboard thing. the model is a parameter. text, voice, image and now video, behind one key, with memory under all of it. so your agent doesn't forget what it just made. you were going to write that polling loop this weekend. don't. get a key: app.backboard.io https://app.backboard.io video docs: docs.backboard.io/sdk/video-tool https://docs.backboard.io/sdk/video-tool