Video Generation

Endpoints

POST https://routerbase.com/v1/videos/generations
GET  https://routerbase.com/v1/videos/generations/{id}

Video generation is asynchronous. The POST returns immediately with an id and status: "pending". Retrieve the result by polling GET /v1/videos/generations/{id} or by setting a callback_url.

Request Headers

Header	Value
`Authorization`	`Bearer sk-rb-xxxxxxxxxxxx`
`Content-Type`	`application/json`

Request Body (POST)

string

required

Video model ID. e.g. bytedance/seedance-2-0, kuaishou/kling-2-1, minimax/hailuo-pro, alibaba/wan-2-7-t2v.

string

required

Text description of the video.

number

Duration in seconds. Model-dependent (commonly 5, 8, 10).

string

e.g. 16:9, 9:16, 1:1.

string

e.g. 720p, 1080p. Model-dependent.

array

Required for image-to-video models (*-i2v, *-image-to-video). Each entry may be a public HTTPS URL or an inline base64 data: URI (e.g. data:image/png;base64,…) — inline images are decoded and hosted automatically. For anything larger than a few MB, prefer uploading via POST /v1/uploads and passing the returned URL.

string

Optional. RouterBase will POST the final result to this HTTPS URL when the task completes. See Async Tasks → Callback.

Submit a Job

curl -X POST https://routerbase.com/v1/videos/generations \
  -H "Authorization: Bearer sk-rb-xxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "bytedance/seedance-2-0",
    "prompt": "A cat playing piano in a sunny living room",
    "duration": 8,
    "aspect_ratio": "16:9"
  }'

import requests

r = requests.post(
    "https://routerbase.com/v1/videos/generations",
    headers={"Authorization": "Bearer sk-rb-xxxxxxxxxxxx"},
    json={
        "model": "bytedance/seedance-2-0",
        "prompt": "A cat playing piano in a sunny living room",
        "duration": 8,
        "aspect_ratio": "16:9",
    },
)
print(r.json()["id"])

Response (POST)

{
  "id": "f47ac10b-58cc-4372-a567-0e02b2c3d479",
  "object": "video.generation",
  "status": "pending",
  "model": "bytedance/seedance-2-0",
  "created": 1776245700
}

Poll Status (GET)

GET /v1/videos/generations/{id}

import time, requests

def wait_for_video(gen_id, api_key, interval=3, timeout=600):
    headers = {"Authorization": f"Bearer {api_key}"}
    url = f"https://routerbase.com/v1/videos/generations/{gen_id}"
    elapsed = 0
    while elapsed < timeout:
        s = requests.get(url, headers=headers).json()
        if s["status"] == "success":
            return s["data"][0]["url"]
        if s["status"] == "failed":
            raise RuntimeError(f"Generation failed")
        time.sleep(interval)
        elapsed += interval
    raise TimeoutError("Generation timed out")

Response (GET)

While running:

{
  "id": "f47ac10b-...",
  "object": "video.generation",
  "status": "pending",
  "model": "bytedance/seedance-2-0",
  "created": 1776245700
}

When complete:

{
  "id": "f47ac10b-...",
  "object": "video.generation",
  "status": "success",
  "model": "bytedance/seedance-2-0",
  "data": [
    { "url": "https://media.routerbase.com/media/<user>/<gen>/0.mp4" }
  ],
  "created": 1776245700
}

`status`	Meaning
`pending`	Task is queued or running
`success`	Generation complete; `data[].url` is populated
`failed`	Generation failed

Image-to-video

For i2v models (e.g. kuaishou/kling-v2-1-master-i2v, bytedance/bytedance-v1-pro-i2v), include image_urls:

{
  "model": "kuaishou/kling-v2-1-master-i2v",
  "prompt": "Camera slowly zooms out",
  "image_urls": ["https://example.com/source.jpg"],
  "duration": 5
}

Get Started

API Reference

Endpoints

Request Headers

Request Body (POST)

Submit a Job

Response (POST)

Poll Status (GET)

Response (GET)

Image-to-video

​Endpoints

​Request Headers

​Request Body (POST)

​Submit a Job

​Response (POST)

​Poll Status (GET)

​Response (GET)

​Image-to-video

Endpoints

Request Headers

Request Body (POST)

Submit a Job

Response (POST)

Poll Status (GET)

Response (GET)

Image-to-video