Alibaba's Wan 2.1 video model with turbo and plus tiers for text-to-video, image-to-video, and first and last frame clips at 480p or 720p.
Alibaba CloudVideo GenerationReleased Feb 25, 2025SingaporeProprietary EndpointAlibaba's Wan 2.1 video model with turbo and plus tiers for text-to-video, image-to-video, and first and last frame clips at 480p or 720p.
Also known as Alibaba Cloud Wan 2.1
wan-2-1/v1/videos/generationsalibaba/wan-2.1wan2.1Live pay-as-you-go rates from the EmpirioLabs catalog. You are billed only for what you use, with no monthly minimum.
Wan 2.1 runs through POST /v1/videos/generations. The request returns a job_id right away; poll GET /v1/jobs/{job_id} until the job completes and read the output URLs from the result. Get an API key from the EmpirioLabs dashboard.
curl https://api.empiriolabs.ai/v1/videos/generations \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "wan-2-1",
"prompt": "Describe what you want Wan 2.1 to generate."
}'curl https://api.empiriolabs.ai/v1/jobs/JOB_ID \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY"import requests
response = requests.post(
"https://api.empiriolabs.ai/v1/videos/generations",
headers={"Authorization": "Bearer YOUR_EMPIRIOLABS_API_KEY"},
json={
"model": "wan-2-1",
"prompt": "Describe what you want Wan 2.1 to generate.",
},
)
job = response.json()
# Generation runs as an async job. Poll until it completes.
import time
while True:
status = requests.get(
f"https://api.empiriolabs.ai/v1/jobs/{job['job_id']}",
headers={"Authorization": "Bearer YOUR_EMPIRIOLABS_API_KEY"},
).json()
if status.get("status") in ("completed", "failed"):
print(status)
break
time.sleep(5)Request parameters supported by the Wan 2.1 API on EmpirioLabs. Defaults apply when a field is omitted.
| Parameter | Type | Default | Range / values | Description |
|---|---|---|---|---|
| prompt | string | - | - | Scene description. |
| mode | enum | auto | auto, t2v, i2v, kf2v | Auto detects from attachments. t2v: text-to-video. i2v: animate one image. kf2v: interpolate between a first and last frame (two images). |
| model_tier | enum | turbo | turbo, plus | turbo: faster and cheaper, 480p or 720p. plus: higher fidelity, 720p only. First-last frame always uses plus. |
| resolution | enum | 720p | 480p, 720p | 480p is turbo-only. |
| aspect_ratio | enum | 16:9 | 16:9, 9:16, 1:1, 4:3, 3:4 | Used for text-to-video; image modes follow the source image. 480p supports 16:9, 9:16, and 1:1 only. |
| image | string | - | - | Source image URL. i2v uses one image; kf2v uses two (first and last frame). |
| duration | number | 5 | 3 to 5 | Clip length in seconds. Only turbo i2v supports 3 to 5; every other mode renders 5. |
| negative_prompt | string | - | - | What to avoid. |
| seed | number | - | - | Reproducibility seed. |
| prompt_extend | boolean | true | - | Let the service rewrite the prompt for better results. |
| watermark | boolean | false | - | Add a provenance watermark to the output. |
Clips render about 5 seconds without audio; turbo image-to-video supports 3 to 5 seconds. Turbo outputs 480p or 720p, plus outputs 720p. Two attached images run first and last frame interpolation on the plus tier.
On EmpirioLabs, Wan 2.1 is billed pay as you go: Turbo $0.036 per second; Plus $0.10 per second. The live rate card on this page always matches what the API charges.
Wan 2.1 is served through POST /v1/videos/generations on api.empiriolabs.ai with standard bearer-token authentication.
Yes. The EmpirioLabs playground runs Wan 2.1 in the browser with the same parameters the API exposes, so you can test prompts before writing code.
Create an EmpirioLabs account, then generate a key under API Keys in the dashboard. Billing is pay-as-you-go credits, so you only pay for the requests you make.
Check out our pricing or reach out if you want your own model deployed on our stack.
