Wan 3.0 Prime · Reference to Video

Generate a video guided by images, videos, audio, a document or a webpage. Learn reference limits, document and webpage compatibility, and input-plus-output video billing.

Developer API pricing

Provider: SeeAPI

USD estimate: $0.0037 / credit · Estimated equivalent, not an additional charge.

480p: 18 credits/sec (≈ $0.067/sec)

720p: 37 credits/sec (≈ $0.14/sec)

1080p: 74 credits/sec (≈ $0.28/sec)

Note: Billable video duration = total input reference video duration + output video duration. Without an input video, only the output duration is billed.

Request

POST/v1/generations

AuthorizationSend your API key in the Authorization header using the Bearer scheme.Authorization: Bearer ****************

Header Params

stringrequired

A unique key for one generation request. Reuse the same key and unchanged request body when retrying a submission.

Use a new key when changing the prompt, parameters or requested output.

max length: 255

Example:: prime-reference-001

Body Params

application/json

stringrequired

Use wan-3-0-prime to select Wan 3.0 Prime.

Allowed:wan-3-0-prime

Default:: wan-3-0-prime
Example:: wan-3-0-prime

stringrequired

Use reference-to-video to generate a video guided by one or more supported references.

Allowed:reference-to-video

Default:: reference-to-video
Example:: reference-to-video

stringoptional

Optional public provider ID. Omit it to use the default provider, seeapi.

Allowed:seeapi

Default:: seeapi
Example:: seeapi

objectrequired

Generation settings and reference URLs for this request.

Provide at least one reference image, video, audio file, document or webpage.
Do not include first_frame_image or last_frame_image.
Use publicly accessible URLs. Media and document URLs must point directly to the files; replace the example URLs with your own assets.

Provider parameters

SeeAPIseeapiDefault Provider

array <uri>optional

An array of up to 10 reference image URLs. Use @image1, @image2 and so on in the prompt, following their array order.

JPEG, PNG, WebP or BMP; up to 20 MB per image.
Each dimension must be 240–8000 pixels. The aspect ratio must not exceed 8:1 in either orientation.

max items: 10

Example:: ["https://client.example.com/reference.png"]

array <uri>optional

An array of up to 5 reference video URLs. Use @video1, @video2 and so on in the prompt, following their array order.

MP4 or MOV; up to 100 MB per video. Each video must be 1–15 seconds and the combined reference video duration must not exceed 15 seconds.
Each dimension must be 240–4096 pixels, with an aspect ratio no greater than 8:1 in either orientation.
Combined reference video duration + duration_seconds must not exceed 30 seconds. Reference video seconds are included in billable duration.

max items: 5

Example:: []

array <uri>optional

An array of up to 5 reference audio URLs. Use @audio1, @audio2 and so on in the prompt, following their array order.

MP3 or WAV; up to 15 MB per audio file. Each file must be 1–15 seconds and the combined audio duration must not exceed 15 seconds.
Audio duration is separate from the reference video duration limit and does not add video seconds to the billing formula.

max items: 5

Example:: []

array <uri>optional

An array containing at most one document URL. The document provides reference content for the generated video.

Supported formats: DOC, DOCX, XLS, XLSX, PPT, PPTX, PDF, TXT, MD, KEY, PAGES and NUMBERS. Maximum file size: 100 MB. Paginated files: up to 50 pages.
reference_file_urls and reference_link_urls cannot be used together. Images, videos and audio may still be included within their respective limits.
Send an array even when supplying one document.

max items: 1

Example:: ["https://client.example.com/reference.pdf"]

array <uri>optional

An array containing at most one publicly accessible webpage URL. The model uses readable content extracted from the page.

reference_file_urls and reference_link_urls cannot be used together. Images, videos and audio may still be included within their respective limits.
The page must be accessible without signing in. If the URL cannot be parsed or no valid content can be extracted, use another accessible page.
Send an array even when supplying one webpage.

max items: 1

Example:: []

stringrequired

Describe the subject, scene, action, camera movement and desired style. Chinese and English prompts are supported.

Reference tokens follow the order of each media array. Describe how each reference should influence the scene.

max length: 20000

Example:: Use the character from @image1 in the scene described by the reference document, with a slow cinematic camera movement.

stringoptional

Output resolution. Higher resolutions use more credits per billable second.

Allowed:480p720p1080p

Default:: 720p
Example:: 720p

stringoptional

Output aspect ratio. Choose adaptive to let the model recommend a suitable ratio.

Allowed:adaptive16:94:31:13:49:16

Default:: adaptive
Example:: 16:9

numberoptional

Requested output video duration in seconds.

Use an integer from 2 to 30.
Combined reference video duration + duration_seconds must not exceed 30 seconds; output duration must remain at least 2 seconds.
Without reference videos: credits = rate × output seconds. With reference videos: credits = rate × (total reference video seconds + output seconds).

min: 2max: 30

Default:: 5
Example:: 5

booleanoptional

Set true to include an audio track in the generated video, or false for silent output.

Default:: true
Example:: true

numberoptional

Optional random seed for reproducibility. Use an integer; omit it when a fixed seed is unnecessary.

min: 0max: 2147483647

string <uri>optional

An absolute HTTPS endpoint that receives the generation's terminal webhook.

Verify the webhook signature and handle repeated deliveries idempotently.

max length: 2048

Example:: https://client.example.com/webhooks/seeapi

Responses

202The request was accepted. Generation continues asynchronously; this response does not contain a finished video.

Bodyapplication/json

Save generation.id and use Get Task Details or the terminal webhook to retrieve the result.

objectrequired

stringrequired

The generation identifier used to query task status and correlate callbacks.

Example:: task_xxx

stringrequired

Example:: wan-3-0-prime

stringrequired

Example:: reference-to-video

stringrequired

Allowed:seeapi

seeapi: SeeAPI

Example:: seeapi

stringrequired

Current generation status. A processing response means the video is not ready yet.

Allowed:processing

Example:: processing

numberrequired

Estimated SeeAPI credits for this request. The example uses no reference video: 5 output seconds at 720p costs 340 credits. If a 5-second reference video is added, the same output costs 680 credits.

Example:: 185

numberrequired

Credits recorded as consumed for this generation; check the terminal task for the final amount.

Example:: 0

numberrequired

Credits returned to the account for this generation, if applicable.

Example:: 0

string <date-time>required

Example:: 2026-08-18T10:00:00Z

string <date-time>required

Example:: 2026-08-18T10:00:00Z

booleanrequired

True when this response replays an existing request with the same idempotency key.

Example:: false

200An existing generation request was returned through idempotency. This is not a second generation.

Bodyapplication/json

A replay does not necessarily mean the original generation has completed. Check its status.

objectrequired

stringrequired

The generation identifier used to query task status and correlate callbacks.

Example:: task_xxx

stringrequired

Example:: wan-3-0-prime

stringrequired

Example:: reference-to-video

stringrequired

Allowed:seeapi

seeapi: SeeAPI

Example:: seeapi

stringrequired

Current generation status. A processing response means the video is not ready yet.

Allowed:processing

Example:: processing

numberrequired

Estimated SeeAPI credits for this request. The example uses no reference video: 5 output seconds at 720p costs 340 credits. If a 5-second reference video is added, the same output costs 680 credits.

Example:: 185

numberrequired

Credits recorded as consumed for this generation; check the terminal task for the final amount.

Example:: 0

numberrequired

Credits returned to the account for this generation, if applicable.

Example:: 0

string <date-time>required

Example:: 2026-08-18T10:00:00Z

string <date-time>required

Example:: 2026-08-18T10:00:00Z

booleanrequired

True when this response replays an existing request with the same idempotency key.

Example:: false

400

The request contains invalid JSON or parameters. Correct the indicated field before submitting again.

401

Authentication failed. Supply a valid SeeAPI API key in the Authorization Bearer header.

402

The account has insufficient credits for this request.

403

The current credentials or account are not permitted to make this request.

404

The requested model, endpoint or generation could not be found.

409

The idempotency key conflicts with another request, or the same request is still being created.

413

The request body is too large. Send supported media URLs instead of embedding file data.

429

Too many requests. Back off before retrying.

503

The service is temporarily unavailable. Retry later, preserving the idempotency key for the same request.

Query Task Status

After submitting a task, use the unified query endpoint to check progress and retrieve results:

Get Task DetailsLearn how to query task status and retrieve generation results

Save generation.id and query the task until it reaches a terminal state. For production integrations, provide callback_url and verify the webhook signature before accepting the result.

Related Resources

Market Overview

Explore all available models

Credits & Billing

View credit balance, plans, and billing activity

Usage

Review API usage and credit consumption

Callbacks

Manage the secret used to verify generation webhook signatures. Callback URLs are supplied when you create each generation.

Webhook flow

Callback URL per generation.

Webhook signing key

Code Examples

Request

const response = await fetch("https://api.seeapi.com/v1/generations", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Idempotency-Key": "prime-reference-001",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
  "model": "wan-3-0-prime",
  "endpoint": "reference-to-video",
  "provider": "seeapi",
  "input": {
    "reference_images": [
      "https://client.example.com/reference.png"
    ],
    "reference_video_urls": [],
    "reference_audio_urls": [],
    "reference_file_urls": [
      "https://client.example.com/reference.pdf"
    ],
    "reference_link_urls": [],
    "prompt": "Use the character from @image1 in the scene described by the reference document, with a slow cinematic camera movement.",
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "duration_seconds": 5,
    "generate_audio": true
  },
  "callback_url": "https://client.example.com/webhooks/seeapi"
})
});

const result = await response.json();

ResponseHTTP 202

{
  "generation": {
    "id": "task_xxx",
    "model": "wan-3-0-prime",
    "endpoint": "reference-to-video",
    "provider": "seeapi",
    "status": "processing",
    "estimated_credits": 185,
    "consumed_credits": 0,
    "refunded_credits": 0,
    "created_at": "2026-08-18T10:00:00Z",
    "updated_at": "2026-08-18T10:00:00Z"
  },
  "idempotent": false
}

const response = await fetch("https://api.seeapi.com/v1/generations", { method: "POST", headers: { "Authorization": "Bearer YOUR_API_KEY", "Idempotency-Key": "prime-reference-001", "Content-Type": "application/json" }, body: JSON.stringify({ "model": "wan-3-0-prime", "endpoint": "reference-to-video", "provider": "seeapi", "input": { "reference_images": [ "https://client.example.com/reference.png" ], "reference_video_urls": [], "reference_audio_urls": [], "reference_file_urls": [ "https://client.example.com/reference.pdf" ], "reference_link_urls": [], "prompt": "Use the character from @image1 in the scene described by the reference document, with a slow cinematic camera movement.", "resolution": "720p", "aspect_ratio": "16:9", "duration_seconds": 5, "generate_audio": true }, "callback_url": "https://client.example.com/webhooks/seeapi" }) }); const result = await response.json();

{ "generation": { "id": "task_xxx", "model": "wan-3-0-prime", "endpoint": "reference-to-video", "provider": "seeapi", "status": "processing", "estimated_credits": 185, "consumed_credits": 0, "refunded_credits": 0, "created_at": "2026-08-18T10:00:00Z", "updated_at": "2026-08-18T10:00:00Z" }, "idempotent": false }

Responses

202The request was accepted. Generation continues asynchronously; this response does not contain a finished video.

Bodyapplication/json

Save generation.id and use Get Task Details or the terminal webhook to retrieve the result.

objectrequired

stringrequired

The generation identifier used to query task status and correlate callbacks.

Example:: task_xxx

stringrequired

Example:: wan-3-0-prime

stringrequired

Example:: reference-to-video

stringrequired

Allowed:seeapi

seeapi: SeeAPI

Example:: seeapi

stringrequired

Current generation status. A processing response means the video is not ready yet.

Allowed:processing

Example:: processing

numberrequired

Estimated SeeAPI credits for this request. The example uses no reference video: 5 output seconds at 720p costs 340 credits. If a 5-second reference video is added, the same output costs 680 credits.

Example:: 185

numberrequired

Credits recorded as consumed for this generation; check the terminal task for the final amount.

Example:: 0

numberrequired

Credits returned to the account for this generation, if applicable.

Example:: 0

string <date-time>required

Example:: 2026-08-18T10:00:00Z

string <date-time>required

Example:: 2026-08-18T10:00:00Z

booleanrequired

True when this response replays an existing request with the same idempotency key.

Example:: false

200An existing generation request was returned through idempotency. This is not a second generation.

Bodyapplication/json

A replay does not necessarily mean the original generation has completed. Check its status.

objectrequired

stringrequired

The generation identifier used to query task status and correlate callbacks.

Example:: task_xxx

stringrequired

Example:: wan-3-0-prime

stringrequired

Example:: reference-to-video

stringrequired

Allowed:seeapi

seeapi: SeeAPI

Example:: seeapi

stringrequired

Current generation status. A processing response means the video is not ready yet.

Allowed:processing

Example:: processing

numberrequired

Estimated SeeAPI credits for this request. The example uses no reference video: 5 output seconds at 720p costs 340 credits. If a 5-second reference video is added, the same output costs 680 credits.

Example:: 185

numberrequired

Credits recorded as consumed for this generation; check the terminal task for the final amount.

Example:: 0

numberrequired

Credits returned to the account for this generation, if applicable.

Example:: 0

string <date-time>required

Example:: 2026-08-18T10:00:00Z

string <date-time>required

Example:: 2026-08-18T10:00:00Z

booleanrequired

True when this response replays an existing request with the same idempotency key.

Example:: false

400

The request contains invalid JSON or parameters. Correct the indicated field before submitting again.

401

Authentication failed. Supply a valid SeeAPI API key in the Authorization Bearer header.

402

The account has insufficient credits for this request.

403

The current credentials or account are not permitted to make this request.

404

The requested model, endpoint or generation could not be found.

409

The idempotency key conflicts with another request, or the same request is still being created.

413

The request body is too large. Send supported media URLs instead of embedding file data.

429

Too many requests. Back off before retrying.

503

The service is temporarily unavailable. Retry later, preserving the idempotency key for the same request.