Create Wan video

Create Wan video tasks via unified POST /v1/videos. Model capabilities are subject to the actual callable range of the current Tikway gateway.

Model	Resolution	Duration	Supported Modes	Audio	Reference Limitations
wan-3.0	480p / 720p / 1080p	2–30 seconds or -1 smart duration	Vincent, first frame, first and last frame, full-modal reference	Supported, enabled by default	10 images / 5 videos / 5 audios; you can also upload 1 file or link
wan-2.7	720p / 1080p	Generate 2–15 seconds; reference/edit 2–10 seconds	Vincent, first frame, first and last frame, continuation, reference, edit	Support	Mode related
wan-2.6	720p / 1080p	Generate 2–15 seconds; reference 2–10 seconds	Vincent, first frame, reference; first and last frames/edit using compatible model	Supported; compatibility mode may be silent	Reference raw video 1–5 images/videos

Source: Alibaba Cloud Video Generation Model Overview. The difference between the official website capabilities and the current unopened capabilities of the gateway can be found in this audit report.

POST https://api.tikway.ai/v1/videos

cURL

Text to video

curl --request POST \
  --url https://api.tikway.ai/v1/videos \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "wan-3.0",
  "prompt": "A golden retriever runs on the beach at sunset. The camera follows smoothly, and the picture has a natural and delicate film quality.",
  "duration": 8,
  "resolution": "1080p",
  "aspect_ratio": "16:9",
  "generate_audio": true
}
'

202

{
  "id": "9552de3d-171f-4cca-b492-7baa56523239",
  "status": "pending",
  "polling_url": "https://api.tikway.ai/v1/videos/9552de3d-171f-4cca-b492-7baa56523239"
}

Authorizations

Authorization · string · header · required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

Create a Wan video task. Parameters are narrowed according to the current Tikway gateway capabilities; for differences between models, see operation description and x-model-capabilities.

model · enum<string> · required

Wan model ID.

Available options: wan-3.0, wan3.0-video, wan-2.7, wan-2.6

prompt · string

Video generation or editing prompt words.

Minimum string length: 1

negative_prompt · string

Wan 2.6/2.7 available. Wan 3.0 does not support top-level negative_prompt; if the upstream extension supports it, please put extra_body.

size · string

Only wan-2.6 supports precise pixel dimensions; use resolution + aspect_ratio for other Wan models.

Pattern: ^[1-9][0-9]*[x*][1-9][0-9]*$

duration · integer string

Video duration (seconds). Wan 3.0 is 2–30 or -1; the upper limit of Wan 2.7/2.6 changes with the generation mode, see the model capability table for details.

Required range: -1 <= x <= 30

aspect_ratio · enum<string>

Video aspect ratio. When producing videos, some models will automatically determine the proportions based on the input material.

Available options: adaptive, 16:9, 9:16, 1:1, 4:3, 3:4

resolution · enum<string>

Output resolution. Available values ​​for different models or modes are shown in the model capabilities table.

Available options: 480p, 720p, 1080p

frame_images · object[]

The first frame or the last frame reference picture; at most one of the same type.

Maximum array length: 2

Hide child attributes

frame_images. type · enum<string> · required

Reference frame position.

Available options: first_frame, last_frame

frame_images. image_url · string<uri> · required

Reference image URL string.

Minimum string length: 1

input_references · object[]

Wan reference material. Different models and modes have different quantity limits; the reference material of Wan 3.0 cannot be mixed with the first and last frames, and file and link are mutually exclusive.

Maximum array length: 21

Option 1

Option 2

Option 3

Option 4

Option 5

Hide child attributes

input_references. image_url · string<uri> · required

Image URL string.

Minimum string length: 1

input_references. type · enum<string>

Optional. Material type; if provided, must be consistent with the corresponding URL field.

Available options: image_url, video_url, audio_url, file_url, link_url

input_references. role · enum<string>

Material usage. When omitted, normal reference material is inferred from the URL field.

Available options: reference_image, reference_video, reference_audio, source_video, first_clip, driving_audio, file, link

input_references. video_url · string<uri>

Video URL string.

Minimum string length: 1

input_references. audio_url · string<uri>

Audio URL string.

Minimum string length: 1

input_references. file_url · string<uri>

File URL string.

Minimum string length: 1

input_references. link_url · string<uri>

Web page URL string.

Minimum string length: 1

input_references. reference_voice · string

Preset patch ID; only used by some models that support patch references.

Minimum string length: 1

generate_audio · boolean

Whether to generate audio. Wan 3.0 is enabled by default; the specific behavior of Wan 2.6/2.7 is determined by the mode.

seed · integer

Random seed. Fixed seeds can only improve reproducibility, but do not guarantee that the output will be completely consistent.

Required range: -1 <= x <= 2147483647

callback_url · string<uri>

User task callback address. Called by Tikway after the task status changes, it is not directly passed to the model upstream.

Pattern: ^https://

extra_body · object

Alibaba Cloud Bailian video model expansion parameters. Fields are merged into upstream parameters.

Hide child attributes

extra_body. prompt_extend · boolean

Whether to enable prompt word rewriting.

extra_body. shot_type · enum<string>

Single lens or multiple lenses.

Available options: single, multi

extra_body. watermark · boolean

Whether to add watermark.

extra_body. audio_setting · enum<string>

Audio processing during video editing.

Available options: auto, origin

Response

202 - application/json

POST /v1/videos Response parameters after the video task is successfully created. The interface returns HTTP 202.

id · string · required

The unique identifier of the video generation task, used for subsequent query of task status.

Minimum string length: 1

Example:

"9552de3d-171f-4cca-b492-7baa56523239"

status · enum<string> · required

Task creation status. pending means that the task has been created and is waiting for submission; queue means that the task has entered the generation queue.

Available options: pending, queue

Example:

"queue"

polling_url · string<uri> · required

Video task query address, the client can poll the task status through GET request.

Pattern: ^https://

Example:

"https://api.example.com/v1/videos/9552de3d-171f-4cca-b492-7baa56523239"