> ## Documentation Index > Fetch the complete documentation index at: https://docs.playapi.ai/llms.txt > Use this file to discover all available pages before exploring further. # Video generation and tasks > Create, retrieve, download, and remix video tasks. Video generation uses asynchronous tasks. Save the gateway `id` after creation, query it with credentials in the same user/project scope, and download when complete. Do not substitute a private task ID from the provider dashboard. As of 2026-10-14, [OpenAI's official guide](https://developers.openai.com/api/docs/guides/video-generation) states that Sora 2 / the Videos API shut down on 2026-09-24. This page documents the compatibility endpoints retained by this project. Confirm an actually available channel or plugin supporting `openai_video` before use. The presence of a Sora plugin or SDK method does not establish upstream availability. ## Task lifecycle | Status | Application behavior | | - | - | | `queued` / `in_progress` | Wait before querying again; bound attempts and total time | | `completed` | Request content; expiry or download failures can still occur | | `failed` | Stop polling and inspect task errors/logs | | `unknown` or an unrecognized value | Stop automation and investigate; never treat it as success | `progress` is a hint. A value of 100 does not replace `status: completed`. Retrieval may return a snapshot saved by background polling; frequent queries do not guarantee fresher data. ## Python: create, resume, and download Configure the [Python SDK environment](/en/guides/python). `API_MODEL` must identify a video model your administrator has confirmed is available. Save as `videos.py`. The pinned SDK retains compatibility methods but may emit Sora deprecation notices. It targets your configured gateway and cannot restore a discontinued upstream. Run `python videos.py create` and save the returned `id`. Replace `task_example` below with that ID. Each `create` makes a new task: never put creation inside a polling loop. ```sh theme={null} python videos.py status task_example python videos.py wait task_example python videos.py download task_example ``` `wait` queries at most 60 times with 5-second intervals by default. Each request also has a 120-second timeout, so this is not a five-minute wall-clock guarantee. Set `--max-polls` to 1–120 attempts. Reaching the limit, exiting, or a network failure does not cancel the server task; resume later with the same ID. ```python theme={null} import argparse import json import os import re import time from contextlib import ExitStack from pathlib import Path from openai import OpenAI, APIConnectionError, APIStatusError parser = argparse.ArgumentParser() parser.add_argument("action", choices=["create", "status", "wait", "download", "remix"]) parser.add_argument("task_id", nargs="?") parser.add_argument("--max-polls", type=int, default=60) parser.add_argument("--image", help="Reference image to upload when creating a task") args = parser.parse_args() if args.action != "create" and (not args.task_id or not re.fullmatch(r"[A-Za-z0-9_-]+", args.task_id)): parser.error("Provide the public gateway task ID (letters, digits, underscores, or hyphens).") if not 1 <= args.max_polls <= 120: parser.error("--max-polls must be between 1 and 120.") if args.image and args.action != "create": parser.error("--image is only valid with create.") with OpenAI(base_url=os.environ["API_BASE_URL"].rstrip("/"), api_key=os.environ["API_KEY"], timeout=120.0, max_retries=0) as client: try: if args.action == "create": # SDK sends multipart; the gateway also accepts JSON for compatible plugins. with ExitStack() as stack: extra = {} if args.image: extra["input_reference"] = stack.enter_context(Path(args.image).open("rb")) result = client.videos.create( model=os.environ["API_MODEL"], prompt="A paper boat floating on a calm pond, static camera.", **extra, ) elif args.action == "remix": result = client.videos.remix(args.task_id, prompt="Change the scene to sunset.") elif args.action == "download": task = client.videos.retrieve(args.task_id) if task.status != "completed": raise ValueError("Video is not completed.") # A failed transfer may leave a partial file; remove it before retrying download. output = Path("video.mp4") with client.videos.with_streaming_response.download_content(args.task_id) as response: media_type = response.headers.get("content-type", "").split(";")[0].lower() if media_type not in ("video/mp4", "application/octet-stream"): raise ValueError("Expected MP4 bytes for this example.") with output.open("xb") as target: size = 0 for chunk in response.iter_bytes(): size += len(chunk) if size > 256 * 1024 * 1024: raise ValueError("Example download exceeds 256 MiB.") target.write(chunk) if size == 0: raise ValueError("Empty video.") print("Saved video.mp4") raise SystemExit(0) else: for attempt in range(args.max_polls if args.action == "wait" else 1): result = client.videos.retrieve(args.task_id) if result.status not in ("queued", "in_progress") or args.action == "status": break if attempt + 1 == args.max_polls: raise SystemExit("Polling limit reached; resume with the same task ID. The task was not cancelled.") time.sleep(5) if not result.id or result.status not in ("queued", "in_progress", "completed", "failed"): raise ValueError("Unrecognized video response.") print(json.dumps({"id": result.id, "status": result.status, "progress": getattr(result, "progress", None)})) if result.status == "failed": raise SystemExit("Video task failed. Check the task logs before submitting again.") except APIStatusError as error: raise SystemExit(f"Request failed (HTTP {error.status_code}). Keep any task ID; do not automatically create another task.") except APIConnectionError: raise SystemExit("Connection failed. Keep any task ID; do not automatically create another task.") except (ValueError, OSError): raise SystemExit("Invalid video response or output file. Check status, content type, and any partial download.") ``` ## Image-to-video and Remix The [create endpoint](/en/api-reference/videos-create) accepts JSON or multipart, but `input_reference`, duration, and dimensions depend on the executing plugin. Upload a reference image in the multipart `input_reference` field and confirm supported encoding, dimensions, and size. Run `python videos.py create --image /path/to/reference.png` to upload the image to the configured gateway and upstream. A prompt alone requests text-to-video; an image reference is not a video upload for transcription. Use [Remix](/en/api-reference/videos-remix) with an existing task: `python videos.py remix task_example`. The original task's channel and plugin must support it. The gateway resolves the original task and pins submission to its channel. The result is a new task submission summary: save the new `id` and query it. Remix is not universal across video plugins. ## Download and recover [Download content](/en/api-reference/videos-content) returns bytes; [HEAD](/en/api-reference/videos-content-head) inspects headers only. Use the gateway content endpoint with Bearer authentication. Never send the gateway key to arbitrary provider URLs, or put a long-lived API key into a browser `