wan3.0-video API

Use the exact model ID wan3.0-video. The model field must match this page exactly.

Sample outputwan3.0-videoPOST /v1/videos5.0s

Parameters: duration=5resolution=1080Pratio=16:9

Prompt: Macro slow-motion shot of steamed milk poured into a ceramic cup of espresso, forming a rosetta latte art pattern. Warm morning light from a window, wooden counter, soft steam rising, shallow depth of field, commercial food photography, no text.

Request that produced this sample

{
  "model": "wan3.0-video",
  "prompt": "Macro slow-motion shot of steamed milk poured into a ceramic cup of espresso, forming a rosetta latte art pattern. Warm morning light from a window, wooden counter, soft steam rising, shallow depth of field, commercial food photography, no text.",
  "seconds": "5",
  "duration": 5,
  "resolution": "1080P",
  "ratio": "16:9",
  "aspect_ratio": "16:9"
}

Authentication and endpoint

Use a Modelflare API key with https://modelflare.dev/v1. The gateway entry point is POST /v1/videos.

HTTP

Authorization: Bearer YOUR_MODELFLARE_API_KEY

Create a task

bash

curl https://modelflare.dev/v1/videos \
  -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan3.0-video",
    "input": {"prompt": "A white cat runs through a neon-lit street in the rain, cinematic tracking shot"},
    "parameters": {"resolution": "1080P", "duration": 5, "audio": true}
  }'

Poll and download

Save the task ID. Poll GET /v1/videos/{task_id} and download with GET /v1/videos/{task_id}/content. Result URLs may expire, so transfer the file promptly.

bash

curl https://modelflare.dev/v1/videos/TASK_ID \
  -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY"

Request notes

Wan commonly uses input and parameters; frame-guided and reference-media modes must not be mixed.

Request parameters

Wan3.0 uses input.prompt or input.media with output controls in parameters. Media may represent frames, references, audio, files, or webpages.

Field	Required	Notes
model	Yes	wan3.0-video
input.prompt	Conditional	Provide this or input.media
input.media[]	Conditional	first_frame, last_frame, reference_*, file, or link
parameters.resolution	No	480P / 720P / 1080P (default 1080P)
parameters.ratio	No	16:9 / 9:16 / 1:1 / 4:3 / 3:4 / adaptive
parameters.duration	No	2–30 seconds, or -1 for automatic duration
parameters.audio	No	Whether to generate synchronized audio
parameters.prompt_extend	No	Set false when this dedicated model contract requires it
parameters.seed	No	Optional random seed
parameters.watermark	No	Whether to add a watermark

Input and output limits

Wan3.0 supports text, first/last frames, up to 10 reference images, 5 reference videos, 5 reference audio clips, and one file or webpage input. Output is 480P, 720P, or 1080P for 2–30 seconds or -1 automatic timing. First/last frames, reference media, files, and webpages are mutually exclusive workflows selected by input.media[].type.

Documented workflow examples

Wan3.0 uses one input/parameters envelope for text, frame guidance, reference media, files, and webpages; these workflows are mutually exclusive.

First and last frames

bash

curl https://modelflare.dev/v1/videos \
  -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan3.0-video",
    "input": {"prompt": "镜头从第一帧平滑推进到最后一帧", "media": [
      {"type": "first_frame", "url": "https://example.com/first.png"},
      {"type": "last_frame", "url": "https://example.com/last.png"}
    ]},
    "parameters": {"resolution": "1080P", "duration": 8, "ratio": "adaptive", "audio": true}
  }'

Reference media

bash

curl https://modelflare.dev/v1/videos \
  -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan3.0-video",
    "input": {"prompt": "保持角色、动作和音色一致", "media": [
      {"type": "reference_image", "url": "https://example.com/character.png"},
      {"type": "reference_video", "url": "https://example.com/motion.mp4"},
      {"type": "reference_audio", "url": "https://example.com/voice.mp3"}
    ]},
    "parameters": {"resolution": "720P", "duration": -1, "ratio": "adaptive"}
  }'

Errors and failed tasks

Invalid model parameters return a 4xx with a request ID. An asynchronous task can also enter failed after creation succeeds; use error_code and error_message from the poll response as the final task reason. Do not retry the same request with a different JSON shape.

Supported scope

This page covers Modelflare model generation and editing calls. Search or map enrichment, voice management, and element-library management are resource APIs outside this public model-call surface and are not required request fields.

Pricing and billing

This model uses per-second video billing. See the model pricing page for the current customer price, reference list price, and complete specification.

Note

This page documents Modelflare’s public interface; the fields and limits shown here are the current contract.

Variants

Model ID	Difference
wan3.0-video	The model documented on this page.