Video Generation

Text-to-video and image-to-video generation. Because a render takes minutes, video is an asynchronous task: you submit a prompt, receive a task_id, poll until it finishes, then download the MP4. Available models include grok-imagine-video, grok-imagine-video-1.5 and the Multimedia group's Seedance / Wan 3.0 / Berry / MiniMax H3 families (see below) — see the model square for the full list and pricing.

Step 1 · Submit a Task

curl https://cn.chatapi.app/v1/video/generations \
  -H "Authorization: Bearer sk-xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-imagine-video",
    "prompt": "A golden retriever puppy running on grass, 4 seconds"
  }'

import requests

base = "https://cn.chatapi.app"
key  = "sk-xxxxxxxx"
headers = {"Authorization": f"Bearer {key}"}

resp = requests.post(
    f"{base}/v1/video/generations",
    headers=headers,
    json={
        "model": "grok-imagine-video",
        "prompt": "A golden retriever puppy running on grass, 4 seconds",
    },
)
task_id = resp.json()["task_id"]
print(task_id)

The response returns immediately with a queued task:

{
  "id": "task_UrufFh4Ww57Q6XWZ7trGZJajiHGw88Md",
  "task_id": "task_UrufFh4Ww57Q6XWZ7trGZJajiHGw88Md",
  "object": "video",
  "model": "grok-imagine-video",
  "status": "queued",
  "progress": 0
}

Request Parameters

Step 2 · Poll for Status

Poll every 5–10 seconds. status moves through queued → IN_PROGRESS → SUCCESS (or FAILURE). When it reaches SUCCESS, the response carries result_url.

curl https://cn.chatapi.app/v1/video/generations/task_UrufFh4Ww57Q6XWZ7trGZJajiHGw88Md \
  -H "Authorization: Bearer sk-xxxxxxxx"

Completed response (trimmed):

{
  "code": "success",
  "data": {
    "task_id": "task_UrufFh4Ww57Q6XWZ7trGZJajiHGw88Md",
    "status": "SUCCESS",
    "progress": "100%",
    "result_url": "https://cn.chatapi.app/v1/videos/task_UrufFh4Ww57Q6XWZ7trGZJajiHGw88Md/content"
  }
}

Step 3 · Download the Video

Fetch the result_url (or build the content URL from the task_id) to download the rendered video/mp4.

curl -L https://cn.chatapi.app/v1/videos/task_UrufFh4Ww57Q6XWZ7trGZJajiHGw88Md/content \
  -H "Authorization: Bearer sk-xxxxxxxx" \
  -o output.mp4

Full Python Example

import time, requests

base = "https://cn.chatapi.app"
headers = {"Authorization": "Bearer sk-xxxxxxxx"}

# 1. submit
task_id = requests.post(
    f"{base}/v1/video/generations", headers=headers,
    json={"model": "grok-imagine-video",
          "prompt": "A puppy running on grass, 4 seconds"},
).json()["task_id"]

# 2. poll
while True:
    data = requests.get(f"{base}/v1/video/generations/{task_id}", headers=headers).json()["data"]
    if data["status"] == "SUCCESS":
        break
    if data["status"] == "FAILURE":
        raise RuntimeError(data.get("fail_reason"))
    time.sleep(8)

# 3. download
mp4 = requests.get(data["result_url"], headers=headers).content
open("output.mp4", "wb").write(mp4)

Multimedia video models (unreviewed)

Third-party unreviewed pool (NSFW allowed, minors strictly prohibited); callable from keys routed to the Multimedia vendor or in "all models" mode. OpenAI Video API: POST /v1/videos to submit → poll GET /v1/videos/{id} until completed → download the MP4 from GET /v1/videos/{id}/content (kept 7 days). Usually 1–5 minutes. Billed per second by resolution, with a per-run minimum charge. Each mode of a series is a separate model name (e.g. seedance-2.0-text-to-video / seedance-2.0-image-to-video).

curl https://cn.chatapi.app/v1/videos \
  -H "Authorization: Bearer sk-xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{"model":"seedance-2.0-mini-text-to-video","prompt":"a paper boat drifting on a rainy street","seconds":"5","size":"480p","metadata":{"ratio":"16:9"}}'
# → {"id":"task_xxx","status":"queued",...}; poll GET /v1/videos/task_xxx, then download /v1/videos/task_xxx/content