All-in-one video generation up to 30 seconds with native audio, omni-modal references (images, video, audio, files, web links), and a fast Prime tier.
Alibaba Cloud视频生成发布日期 2026年8月6日Singapore专有端点新All-in-one video generation up to 30 seconds with native audio, omni-modal references (images, video, audio, files, web links), and a fast Prime tier.
也称为 Alibaba Cloud Wan 3.0
wan-3-0/v1/videos/generationsalibaba/wan-3.0wan-3.0wan3.0wan3.0-videowan3.0-video-prime来自 EmpirioLabs 目录的实时按量计费价格。只为实际用量付费，没有月度最低消费。
Wan 3.0 通过 POST /v1/videos/generations 运行。请求会立即返回 job_id；轮询 GET /v1/jobs/{job_id} 直到任务完成，再从结果中读取输出 URL。 在EmpirioLabs 控制台获取 API 密钥。
curl https://api.empiriolabs.ai/v1/videos/generations \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "wan-3-0",
"prompt": "Describe what you want Wan 3.0 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-3-0",
"prompt": "Describe what you want Wan 3.0 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)EmpirioLabs 上 Wan 3.0 API 支持的请求参数。省略字段时使用默认值。
| 参数 | 类型 | 默认值 | 范围 / 值 | 描述 |
|---|---|---|---|---|
| prompt | string | - | - | Scene description, up to 20,000 characters. In reference mode, address inputs in your prompt as Image 1, Video 1, Audio 1. |
| model_tier | enum | standard | standard, prime | standard: full quality at the base rate. prime: significantly faster end-to-end generation at a higher per-second rate. Each tier is billed at its own rate. |
| mode | enum | auto | auto, t2v, i2v, r2v | Auto detects from attachments. t2v: text-to-video. i2v: animate one image, or interpolate between two (first and last frame). r2v: omni reference from images,... |
| resolution | enum | 1080p | 480p, 720p, 1080p | Output resolution. Each resolution bills at its own per-second rate. |
| duration | number | 5 | 2 到 30 | Clip length in seconds. Pass -1 via the API to let the model choose the length. With video references, input plus output stays within 30 seconds. |
| aspect_ratio | enum | adaptive | adaptive, 16:9, 9:16, 1:1, 4:3, 3:4 | adaptive recommends an aspect ratio from your inputs and prompt. |
| image | string | - | - | Image URL. i2v uses one or two images (first and last frame); r2v accepts up to 10 references. |
| video | string | - | - | Reference video URL (r2v). Up to 5 clips, 15 seconds combined. |
| seed | number | - | 0 到 2147483647 | Reproducibility seed. |
| audio | boolean | true | - | Generate the soundtrack with the video. Turning it off does not change the price. |
| watermark | boolean | false | - | Add a provenance watermark to the output. |
| prompt_extend | boolean | true | - | Let the service rewrite the prompt for better results. |
| link | string | - | - | Public web page URL used as a reference (r2v). Provide either a link or a file_url, not both. |
| file_url | string | - | - | Document URL used as a reference (r2v): PDF, Office, or text files up to 100 MB and 50 pages. Provide either a file_url or a link, not both. |
Generation can take several minutes on the standard tier; the prime tier is significantly faster end to end. Modes are auto-detected from attachments, or override with the mode parameter. The model_tier parameter picks standard or prime; each tier bills at its own per-second rate.
在 EmpirioLabs，Wan 3.0 按量计费：Standard 480P $0.07 per second; Standard 720P $0.14 per second; Standard 1080P $0.28 per second。本页的实时价格表始终与 API 的实际计费一致。
Wan 3.0 通过 api.empiriolabs.ai 上的 POST /v1/videos/generations 提供，使用标准的 Bearer 令牌认证。
可以。EmpirioLabs Playground在浏览器中以与 API 相同的参数运行 Wan 3.0，你可以在写代码之前先测试提示词。
创建 EmpirioLabs 账户，然后在控制台的 API Keys生成密钥。计费使用按量付费的额度，只为实际发出的请求付费。
