Z.ai: CogVideoX-3

Where this model runs, and what each route costs. Requests are sent to a healthy provider automatically; if one errors, the gateway retries against another serving the same model.

What this model costs on Oxyy, pay as you go. "Charged" is the rate a request is billed at; the standard price is shown beside it for reference.

Discount. Charged rates include the current "Launch Promo" discount of 60% on every rate.

Model ID

cogvideox-3

Developer

Z.ai

Type

Text to video

Input

Text and images

Output

Video

Series

CogVideoX

Image input

Up to 20 MB each

Endpoint

/v1/videos/generations

Call cogvideox-3 with a POST to /v1/videos/generations on https://api.oxyy.ai, using your Oxyy API key from the OXYY_API_KEY environment variable. Video is generated as a job: submit it, then poll the job id until it completes.

import os, time, requests

headers = {"Authorization": f"Bearer {os.environ['OXYY_API_KEY']}"}

# Video is a job: the POST answers 202 with an id, then you poll it.
job = requests.post("https://api.oxyy.ai/v1/videos/generations", headers=headers, json={"model":"cogvideox-3","prompt":"A serene lake at dawn, slow dolly in","duration":5}).json()

while job["status"] not in ("completed", "failed", "cancelled"):
    time.sleep(5)
    job = requests.get(f"https://api.oxyy.ai/v1/videos/generations/{job['id']}", headers=headers).json()

print(job["status"], job.get("result", {}).get("data", [{}])[0].get("url"))

The share of requests to this model that completed successfully over the last 30 days. Requests the caller cancelled, and requests still in flight, are not counted. When an upstream provider errors, the gateway retries against another provider serving the same model, so a single provider incident does not necessarily show up here.

Models of the same kind from other vendors, closest in price first. Prices are pay-as-you-go on Oxyy, through the same API key.

More models from Z.ai