Video model
Wan 2.2 video on Apple silicon Macs
Released
Makes short video clips from a description. Smarty Pants serves a pinned, quantized bf16 build on qualified Macs with 48 GB of memory or more, through an OpenAI-compatible API.
$0.011 a 480p clip
$0.011 a 480p clip
Listed price on November 19, 2026. Current price: GET /v1/models.
Wan 2.2 video at a glance
What Smarty Pants serves, from its public catalog, and what the model's developer publishes about it.
- API name
smartypants/wan2.2-5b-video- Endpoint
- POST /v1/videos
- Build served
- bf16 (fastwan2.2-ti2v-5b-mlx-bf16-r2446162)
- Mac memory needed
- 48 GB or more
- Developer
- FastVideo team (on Wan-AI's Wan2.2-TI2V-5B)
- Parameters
- 5B
- License
- Apache-2.0
- First released
- August 2025
- Status
- Released
Smarty Pants catalog checked November 19, 2026. Upstream facts from the developer's model card (sources below).
What Wan 2.2 video is good for
Makes short video clips from a text prompt in 3 steps instead of dozens, which makes it practical on a Mac.
Trained at 704x1280; Smarty Pants serves 480p clips (832x480 or 480x832).
Use it for
- Short 2, 3 or 5 second clips at 480p (832x480 or 480x832)
- Concept and mood clips
Look elsewhere for
- Long or high-resolution video
- Sexual or nude content of real people, or fakes meant to fool people about real people (not allowed by the use rules)
- Anything that must not be labeled as AI-made
How to call Wan 2.2 video
Smarty Pants works with OpenAI's libraries: change the base URL and the key, and keep the rest. Get a key at smartypants.network/api.
import time, requests
H = {"Authorization": "Bearer YOUR_SMARTY_PANTS_KEY"}
job = requests.post("https://smartypants.network/v1/videos", headers=H,
json={"model": "smartypants/wan2.2-5b-video", "prompt": "A paper boat on a rainy street", "size": "832x480", "seconds": 3}).json()
while (job := requests.get(f"https://smartypants.network/v1/videos/{job['id']}", headers=H).json())["status"] in ("queued", "in_progress"):
time.sleep(10)
print(job["status"]) # completed clips are held up to 30 minutes Before sending real traffic, check is_ready for this model on GET /v1/models. A 429 or 503 means no Mac can take the request right now: wait the Retry-After seconds or use your fallback provider.
Which Macs can serve Wan 2.2 video
Smarty Pants serves this model only on Macs with 48 GB of unified memory or more. These Apple silicon chips were sold with at least one memory size that big (memory options from Apple's tech specs).
| Chip | Memory sizes that fit | Memory sizes too small |
|---|---|---|
| M1 Max | 64 GB | 32 GB |
| M1 Ultra | 64 GB, 128 GB | None |
| M2 Max | 64 GB, 96 GB | 32 GB |
| M2 Ultra | 64 GB, 128 GB, 192 GB | None |
| M3 Max | 48 GB, 64 GB, 96 GB, 128 GB | 36 GB |
| M3 Ultra | 96 GB, 256 GB, 512 GB | None |
| M4 Pro | 48 GB, 64 GB | 24 GB |
| M4 Max | 48 GB, 64 GB, 128 GB | 36 GB |
| M5 Pro | 48 GB, 64 GB | 24 GB |
| M5 Max | 48 GB, 64 GB, 128 GB | 36 GB |
| M5 Ultra | 96 GB, 256 GB, 512 GB | None |
No memory option is big enough on: M1, M1 Pro, M2, M2 Pro, M3, M3 Pro, M4, M5, M6.
Frequently asked questions
What is the API name for Wan 2.2 video on Smarty Pants?
Use "smartypants/wan2.2-5b-video" as the model with the OpenAI-compatible base URL https://smartypants.network/v1.
How much does Wan 2.2 video cost on Smarty Pants?
The listed price on November 19, 2026 was $0.011 a 480p clip. Prices can change; GET https://smartypants.network/v1/models returns the current price, and you are not charged for a request Smarty Pants can't serve.
How much memory does a Mac need to serve Wan 2.2 video?
Smarty Pants serves this bf16 build only on qualified Apple silicon Macs with 48 GB of unified memory or more.
Is Wan 2.2 video available right now?
On November 19, 2026 it was released. How many Macs have it online changes through the day; check is_ready on https://smartypants.network/v1/models before sending real traffic, and keep a fallback provider.
Can I send private data to Wan 2.2 video on Smarty Pants?
Requests on the general network run on Macs other people own, and a serving Mac decrypts a request in memory to answer it. Keep secrets, personal and confidential data off the general network; companies can run work on their own Macs with a Group.
Sources
Try a pinned open model on real Macs.
See every model, its listed price and the code to call it. Smarty Pants works with the OpenAI SDK you already use: change the base URL and the key.
Requests run on Macs owned by other people. Owners agree not to read requests and the app doesn't show them, but a serving Mac decrypts each request in memory to answer it, so that is a rule and a design, not a technical guarantee. Don't send sensitive data on the general network.