Glm 5.3 Flash:batch API

Python

import base64, json, time, urllib.request

headers = {"Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json"}
req = urllib.request.Request(
    "https://api.fastinfra.ai/v1/videos",
    data=json.dumps({
        "model": "z-ai/glm-5.3-flash:batch",
        "prompt": "A woman looks at the camera and says, welcome to FastInfra.",
        "seconds": 5,
        "size": "1280x704"
    }).encode(),
    headers=headers,
    method="POST",
)
with urllib.request.urlopen(req, timeout=60) as resp:
    job = json.load(resp)

while True:
    time.sleep(2)
    poll = urllib.request.Request(
        f"https://api.fastinfra.ai/v1/videos/{job['id']}",
        headers={"Authorization": "Bearer YOUR_API_KEY"},
    )
    with urllib.request.urlopen(poll, timeout=60) as resp:
        payload = json.load(resp)
    if payload["status"] == "completed":
        break
    if payload["status"] == "failed":
        raise SystemExit(payload.get("error") or "video job failed")

open("clip.mp4", "wb").write(base64.b64decode(payload["data"][0]["b64_json"]))

curl

curl https://api.fastinfra.ai/v1/videos \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "z-ai/glm-5.3-flash:batch",
    "prompt": "A woman looks at the camera and says, welcome to FastInfra.",
    "seconds": 5,
    "size": "1280x704"
  }'
# HTTP 202 — copy "id", then poll:
curl https://api.fastinfra.ai/v1/videos/JOB_ID \
  -H "Authorization: Bearer YOUR_API_KEY"

How much does the z-ai/glm-5.3-flash:batch API cost?

On FastInfra, z-ai/glm-5.3-flash:batch costs $0.063/1M input, $0.21/1M output tokens ($0 per second of video). Billing is per token used, with no subscription.

Is z-ai/glm-5.3-flash:batch compatible with the OpenAI SDK?

Video models use the same FastInfra API key and base URL (https://api.fastinfra.ai/v1). List SKUs with GET https://api.fastinfra.ai/v1/videos/models, submit with POST https://api.fastinfra.ai/v1/videos (HTTP 202), poll GET https://api.fastinfra.ai/v1/videos/{id} until status is completed. They do not work on POST https://api.fastinfra.ai/v1/chat/completions.

Can I call z-ai/glm-5.3-flash:batch on POST /chat/completions?

No. z-ai/glm-5.3-flash:batch is a video model. Use GET https://api.fastinfra.ai/v1/videos/models to confirm the id, POST https://api.fastinfra.ai/v1/videos with "model": "z-ai/glm-5.3-flash:batch", then poll GET https://api.fastinfra.ai/v1/videos/{id}.

How does routing work for z-ai/glm-5.3-flash:batch?

z-ai/glm-5.3-flash:batch is available on 1 route(s): route-07. Requests use route-07 by default (lowest cost). FastInfra fails over automatically if a route is unavailable.