Skip to main content
Glama
Wan 3.0 Prime API MCP Server

Wan 3.0 Prime API MCP Server

Wan 3.0 Prime API — from $0.051/s (480p)

Alibaba Wan 3.0 Prime is live on ArgoLink: $0.051/s at 480p, $0.11/s at 720p and $0.21/s at 1080p, 21–25% below Alibaba Cloud's international list price. Prime is the faster lane of Wan 3.0: a prompt, optionally with reference images, clips and audio, becomes a 4–30 second video with its own soundtrack.

Wan 3.0 Prime model page → · Prices · Install · Prime vs Wan 3.0 · MCP server · FAQ

A small Python client (wan_api.py), an MCP server for agent tools (mcp_server.py), curl scripts in examples/ and offline tests. It speaks the async /v1/videos protocol: submit, poll, download.

Last checked: 2026-10-07 against the pages linked in the tables.

At a glance

Model ID

wan-3-prime

Modes

text to video · reference to video (images, video, audio). No first or last frame and no video edit on this route

Duration

4–30 s in whole seconds, default 5

Resolution

480p · 720p · 1080p, default 720p

Aspect ratio

16:9 · 1:1 · 9:16, default 16:9

References

≤ 10 images, ≤ 5 videos, ≤ 5 audio clips, ≤ 20 in total. Clips 1–15 s each and 15 s per kind; output plus reference video ≤ 30 s. Audio needs an image or video beside it

Prompt

required, up to 20,000 characters; name assets @Image 1, @Video 1, @Audio 1

Sound

always on (AAC stereo); generate_audio: false returns 400

Output

one 24 fps H.264 MP4 per request

Rejected with 400

start_image, end_image, seed, watermark: true, n other than 1

Related MCP server: Enlace

Price per second

Provider

480p

720p

1080p

10 s at 720p

ArgoLink

$0.051

$0.11

$0.21

$1.10

Alibaba Cloud Model Studio, Singapore (international)

$0.068

$0.14

$0.28

$1.40

Alibaba Cloud Model Studio, US (Virginia) and other global regions

$0.0636

$0.1272

$0.2544

$1.27

WaveSpeedAI

$0.075

$0.15

$0.30

$1.50

MuAPI

$0.068

$0.14

$0.28

$1.40

All pages read 2026-10-07 (the Alibaba page was last updated 2026-09-28 and shows list prices without promotions). Against the Singapore list the ArgoLink rate is 25% lower at 480p and 1080p and 21% lower at 720p; against the global-region list it is 20%, 14% and 17% lower.

Install

git clone https://github.com/augustusrenfield6/wan-3-0-prime-api
cd wan-3-0-prime-api
python -m pip install -e .          # client: Python 3.9+, requests
python -m pip install -e ".[mcp]"   # adds the MCP server: Python 3.10+, mcp 2.x
export WAN_API_KEY=your-key         # an ArgoLink API key

WAN_BASE_URL (default https://argolink.io/v1) points the client at any other server with the same protocol.

Quick start

from wan_api import WanPrimeAPI, estimate_cost

api = WanPrimeAPI()
job = api.text_to_video(
    "A cinematic tracking shot of a red fox crossing a snowy forest at sunrise, breath steaming",
    duration=8,
    resolution="720p",
    aspect_ratio="16:9",
)
result = api.wait_for_completion(job["request_id"], on_progress=lambda s: print(s.get("progress"), "%"))
api.download(job["request_id"], "fox.mp4")
print(result["usage"], estimate_cost(8, "720p"))   # 8 billed seconds, $0.88

Reference to video

job = api.reference_to_video(
    "The woman in @Image 1 walks into the café from @Video 1 and orders, in time with @Audio 1",
    reference_images=["https://example.com/woman.jpg"],
    reference_videos=["https://example.com/cafe-6s.mp4"],
    reference_audios=["https://example.com/voice.mp3"],
    duration=10,
    aspect_ratio="9:16",
)
# billed seconds = 10 output + 6 reference video = 16 -> 16 x $0.11 = $1.76 at 720p

Local files go through a free upload ticket first:

media = api.upload_file("woman.jpg", kind="image")      # PUTs to a signed URL, no bearer token
job = api.reference_to_video("@Image 1 waves at the camera", reference_images=[media["media_url"]])

Upload limits: JPEG or PNG up to 20 MiB; MP4 or MOV up to 100 MiB and 1–15 s; WAV or MP3 up to 15 MB and 1–15 s. The upload_url is valid for 15 minutes and the media_url for seven days.

API surface

Method

Does

text_to_video(prompt, duration, resolution, aspect_ratio)

submit a prompt-only job, return {"request_id"}

reference_to_video(prompt, reference_images, reference_videos, reference_audios, ...)

submit with HTTPS references

upload_file(path, kind)

upload a local asset, return its media_url

get_result(request_id)

read the status once

wait_for_completion(request_id, max_wait_seconds, on_progress)

poll until done; raise on failed / expired

download(request_id, path)

stream the MP4 to path.part, then rename

estimate_cost(duration, resolution, reference_video_seconds)

dollars at the rates above

image_to_video(...)

raises: frames are not accepted on wan-3-prime

Every method validates locally first (ratio, duration, tier, counts, HTTPS URLs), so a bad request fails before it reaches the API. Submits are never retried by the client: a POST that timed out may still have created a job, so poll before you resend.

curl

BASE=https://argolink.io/v1
ID=$(./examples/submit-text.sh "Paper lanterns rise over a river at dusk" 6 720p 16:9)
./examples/poll-and-download.sh "$ID" lanterns.mp4

submit-reference.sh and upload-and-submit.sh cover references; all four scripts need curl and jq.

Wan 3.0 Prime vs Wan 3.0

Both are Alibaba Wan 3.0 on the same endpoint; the model ID picks the lane.

wan-3-prime

wan-3

Positioning

faster turnaround

full feature set

Duration

4–30 s

2–30 s

First / last frame

not on this route (400)

yes

Edit an existing video

no

yes (omni_reference_task_type: "edit")

Aspect ratios

16:9, 1:1, 9:16

21:9, 16:9, 4:3, 1:1, 3:4, 9:16, adaptive

Audio as the only reference

no

yes

seed

rejected

accepted

Silent output

no

generate_audio: false

Price 480p / 720p / 1080p

$0.051 / $0.11 / $0.21

$0.038 / $0.075 / $0.15

Alibaba Cloud's own Prime documentation lists first-frame and first/last-frame input; the wan-3-prime route described here does not accept them, so send frames to wan-3.

MCP server

mcp_server.py runs over stdio and exposes text_to_video, reference_to_video, get_video_status, download_video and price_table. It reads WAN_API_KEY from its own environment and never takes a key as a tool argument.

Claude Code:

claude mcp add --transport stdio --env WAN_API_KEY=your-key wan-3-prime -- python /path/to/wan-3-0-prime-api/mcp_server.py

Cursor (.cursor/mcp.json or ~/.cursor/mcp.json):

{
  "mcpServers": {
    "wan-3-prime": {
      "command": "python",
      "args": ["/path/to/wan-3-0-prime-api/mcp_server.py"],
      "env": { "WAN_API_KEY": "${env:WAN_API_KEY}" }
    }
  }
}

Codex (~/.codex/config.toml):

[mcp_servers.wan-3-prime]
command = "python"
args = ["/path/to/wan-3-0-prime-api/mcp_server.py"]
env_vars = ["WAN_API_KEY"]

The server needs the MCP Python SDK 2.x. In 1.x the class was FastMCP (mcp.server.fastmcp), which 2.x renamed to MCPServer.

Billing rules

  • Per output second at the tier rate, multiplied by the length.

  • Reference video seconds are added, with the fraction of their total dropped: 5 s output with a 2.4 s clip bills 7 s.

  • Reference images and audio are free; uploads are free.

  • A failed, rejected or expired job is not billed. The finished job's usage holds output_seconds, reference_video_seconds and billed_seconds.

Status values

pending (with progress 0–99 and, once known, estimated_seconds_remaining), done (with video.url and usage), failed (with error.code, error.message, error.retryable) and expired. The content endpoint answers 409 job_video_not_ready until the job is done and 424 job_failed after a failure.

FAQ

Can Wan 3.0 Prime start from my image? Not as a first frame on this route: start_image and end_image return 400. Pass the image as reference_images (it guides the subject without being frame one), or use wan-3 for true first-frame and first/last-frame videos.

Why is 4:3 or adaptive rejected? Prime accepts 16:9, 1:1 and 9:16 only. wan-3 adds 21:9, 4:3, 3:4 and adaptive.

Can I get a silent clip? No, every Prime video carries a generated stereo track. Remove it afterwards with ffmpeg -i in.mp4 -an -c:v copy out.mp4, or use wan-3 with generate_audio: false.

What does a 30-second 1080p Prime clip cost? 30 × $0.21 = $6.30 here, against $8.40 at Alibaba Cloud's Singapore list price.

How long can a reference clip be? 1–15 s each and 15 s in total, and the output plus the reference videos may not exceed 30 s.

The old example used running and api.argolink.io. Which is right? Neither: the documented statuses are pending, done, failed and expired, and the base URL is https://argolink.io/v1.

Tests

python -m pip install -e ".[test]"   # add ",mcp" to also run the MCP server test
python -m pytest

The tests use a fake HTTP session; no key or network is needed.

License

MIT

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Exposes four stdio tools that let an agent research an application's documented interface, produce a validated single-use plan, and execute read-only operations against public HTTP JSON APIs, static HTML/JSON/text sources, and host-configured CLIs. Runs in-process with no listening port, accounts, or model dependency, returning bounded results while keeping inputs and outputs inside a host-enforced research-plan-execute lifecycle.
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables MCP clients to run eight data tools over stdio for product search, ad transparency, company intent, job/ATS lookup, keyword volume, domain SEO, and YouTube transcripts, returning JSON envelopes with item limits, truncation metadata, and structured errors.
      30 PyPI
      MIT
    • A
      license
      Not graded
      quality
      A
      maintenance
      Exposes three stdio tools that let an MCP host pose typed judgments — yes/no, choice, and score — and receive calibrated probabilities rather than prose, running offline against a mock unless a credential and live provider are explicitly configured, with every outbound transmission reported on stderr.
      66 npm
      Apache 2.0