One page, every integration path. Find your starting point, copy working code, and ship in minutes — not hours.
Choose the approach that matches your stack. Each card links to a full walkthrough.
POST /v1/images/generations — OpenAI SDK compatible
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://api.creativeai.run/v1"
)
response = client.images.generate(
model="gpt-image-1", # or seedream-3, dall-e-3
prompt="A product photo on white background",
size="1024x1024"
)
print(response.data[0].url)POST /v1/video/generations — submit, then poll or use webhooks
import httpx
API_KEY = "YOUR_API_KEY"
BASE = "https://api.creativeai.run"
# 1. Submit job
resp = httpx.post(
f"{BASE}/v1/video/generations",
headers={"Authorization": f"Bearer {API_KEY}"},
json={
"model": "kling-v3", # or seedance-1.5, veo-3.1
"prompt": "Product reveal animation, slow dolly in",
"duration": 5,
},
)
job = resp.json()
task_id = job["id"]
# 2. Poll for result
import time
while True:
status = httpx.get(
f"{BASE}/v1/video/generations/{task_id}",
headers={"Authorization": f"Bearer {API_KEY}"},
).json()
if status["status"] == "completed":
print(status["video_url"])
break
time.sleep(5)import { generateImage } from 'ai';
import { createOpenAI } from '@ai-sdk/openai';
const creativeai = createOpenAI({
apiKey: 'YOUR_API_KEY',
baseURL: 'https://api.creativeai.run/v1',
});
const { image } = await generateImage({
model: creativeai.image('gpt-image-1'),
prompt: 'A minimalist tech startup logo',
});# litellm_config.yaml — add to your existing proxy
model_list:
- model_name: creativeai/gpt-image-1
litellm_params:
model: openai/gpt-image-1
api_key: YOUR_API_KEY
api_base: https://api.creativeai.run/v1
# Then generate images via your proxy:
# litellm --config litellm_config.yaml
# curl http://localhost:4000/v1/images/generations \
# -d '{"model": "creativeai/gpt-image-1", "prompt": "..."}'Submit a video job and receive the result via HMAC-signed callback
import httpx
resp = httpx.post(
"https://api.creativeai.run/v1/video/generations",
headers={"Authorization": "Bearer YOUR_API_KEY"},
json={
"model": "kling-v3",
"prompt": "Product reveal animation",
"duration": 5,
"webhook_url": "https://your-app.com/api/webhook",
"webhook_secret": "whsec_your_secret",
},
)
# CreativeAI will POST the result to your webhook_url
# with an X-Webhook-Signature HMAC-SHA256 header| Model | Type | model parameter |
|---|---|---|
| GPT Image 1 | Image | gpt-image-1 |
| Seedream 3 | Image | seedream-3 |
| DALL-E 3 | Image | dall-e-3 |
| Kling v3 | Video | kling-v3 |
| Seedance 1.5 | Video | seedance-1.5 |
| Veo 3.1 | Video | veo-3.1 |
Use model: "auto" for automatic provider selection with content-filter failover.