models/Alibaba/Wan 3.0 Video
Alibaba

Wan 3.0 Video

video
Compare
MODALITIES
video
PER SECOND
$0.200

Wan 3.0 Video (alibaba/wan3.0-video) is a video model from Alibaba. Pricing via AIgateway: $0.050–$0.200 per second by resolution. Call it via https://api.aigateway.sh/v1/videos/generations — set model="alibaba/wan3.0-video".

model · alibaba/wan3.0-video

Use this model

model: alibaba/wan3.0-video
curl https://api.aigateway.sh/v1/videos/generations \
  -H "Authorization: Bearer $AIGATEWAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"alibaba/wan3.0-video","prompt":"a slow drone shot over a mountain lake","duration":5,"resolution":"480P"}'

Capabilities

Text to videoImage to videoFirst last frameReference to videoContext to video

Pricing

Per video second — 480P$0.050
Per video second — 720P$0.100
Per video second — 1080P$0.200
You pay pass-through pricing.
See API example →CompareAPI referenceSee usage ranking →

Collections

More video models →More from AlibabaFrontier models →Free-tier models →
API schema

Call Wan 3.0 Video from any OpenAI SDK

POST https://api.aigateway.sh/v1/videos/generations·Content-Type: application/json·Auth: Bearer sk-aig-...

Request body

json
{
  "model": "alibaba/wan3.0-video",
  "prompt": "A drone shot of a mountain lake at golden hour",
  "duration": 5,  // seconds, 2-30, or -1 to let the model choose
  "aspect_ratio": "adaptive",  // adaptive | 16:9 | 9:16 | 4:3 | 3:4 | 1:1
  "resolution": "480P",  // 480P $0.05/s, 720P $0.10/s, 1080P $0.20/s
  "audio": true,  // generate a native audio track (dialogue, ambience)
  "seed": 42  // reproducibility
}
// optional "image_url" to animate a seed image, plus "last_frame_url" to interpolate to a closing frame
//
// Reference-to-video. The prompt cites these positionally as
// "Image 1", "Video 1", numbered per kind in the order you list them:
//   "reference_images": ["https://..."]   up to 10
//   "reference_videos": ["https://..."]   up to 5
//   "reference_audios": ["https://..."]   up to 5
//
// Context-to-video:
//   "file_url": "https://.../deck.pdf"
//   "link_url": "https://example.com/article"
//
// References / file / link cannot be combined with image_url or last_frame_url.

// Response is an async job — poll /v1/jobs/<id> until status === "completed".

Response

json
{
  "id": "job_abc123",
  "status": "queued",        // queued | processing | completed | failed
  "model": "alibaba/wan3.0-video",
  "created": 1776947082
}

// After completion:
{
  "id": "job_abc123",
  "status": "completed",
  "result": {
    "url": "https://media.aigateway.sh/video/abc123.mp4",
    "duration": 5,
    "resolution": "1920x1080"
  }
}

Quickstart

# See docs at https://aigateway.sh/docs

Errors

401authentication_errorInvalid or missing API key
402insufficient_creditsWallet empty (PAYG only)
404not_foundUnknown model or endpoint
429rate_limit_errorOver per-minute limit — see Retry-After header
500server_errorUpstream provider failed (retryable)
503service_unavailableUpstream saturated (retryable)
Full docs →API reference →OpenAPI spec →llms.txt →

Request parameters

promptstringrequired
Text description of the video to generate.
durationintegerdefault 5
Length of the output in seconds (2-30). Pass -1 to let the model choose its own length.
aspect_ratiostringdefault adaptive
Frame shape of the output.
adaptive | 16:9 | 9:16 | 4:3 | 3:4 | 1:1
resolutionstringdefault 1080P
Output resolution; it sets the per-second price (480P $0.05/s, 720P $0.10/s, 1080P $0.20/s).
480P | 720P | 1080P
image_urlstring
Opening frame. Supplying it makes the request image-to-video.
last_frame_urlstring
Closing frame. Requires image_url; the model interpolates between the two.
reference_imagesarray
Up to 10 reference URL(s), cited in the prompt as "Image 1", "Image 2" in the order you list them. Cannot be combined with image_url or last_frame_url.
reference_videosarray
Up to 5 reference URL(s), cited in the prompt as "Video 1", "Video 2" in the order you list them. Cannot be combined with image_url or last_frame_url.
reference_audiosarray
Up to 5 reference URL(s), cited in the prompt as "Audio 1", "Audio 2" in the order you list them. Cannot be combined with image_url or last_frame_url.
file_urlstring
Document to generate video from (context-to-video). Cannot be combined with frames or references.
link_urlstring
URL for the model to read and generate video from. Cannot be combined with frames or references.
audiobooleandefault true
Generate a native audio track (dialogue, ambience). Distinct from reference_audios, which are inputs.
seedinteger
Random seed for reproducibility. Random when omitted.

Frequently asked questions

What is Wan 3.0 Video?
It is a video model from Alibaba, accessible via AIgateway's OpenAI-compatible API at slug alibaba/wan3.0-video.
How much does Wan 3.0 Video cost via AIgateway?
Pass-through pricing. See the pricing panel on this page for exact rates.
How do I call Wan 3.0 Video from my code?
Point the OpenAI SDK at https://api.aigateway.sh/v1 with your AIgateway key and set model to "alibaba/wan3.0-video". The request and response shapes match OpenAI exactly.
Does Wan 3.0 Video support streaming, tool calling, vision, and JSON mode?
Streaming — no. Tool calling — no. Vision — no. JSON mode — no. Prompt caching — no.
Can I bring my own Alibaba API key (BYOK)?
Yes. Attach a Alibaba key in your AIgateway dashboard and this model flips to pass-through — you pay Alibaba directly and AIgateway adds no platform fee on those calls.