Wan 3.0 Video API reference
Check Wan 3.0 Video availability, inputs, parameters, file requirements, credit pricing, and request examples for Rivya Public API v1. Model ID: wan-3-0-video.
wan-3-0-video
text, file
Required for reference modes
Credit rate: 8–50.4 per second of total video duration (input + output) The final cost is rounded up to whole credits.
Video
METERED
20000 characters
Credit pricing
| Options | Credit pricing |
|---|---|
| Standard / 480P | Credit rate: 8 per second of total video duration (input + output) |
| Standard / 720P | Credit rate: 16 per second of total video duration (input + output) |
| Standard / 1080P | Credit rate: 32 per second of total video duration (input + output) |
| Prime / 480P | Credit rate: 12.2 per second of total video duration (input + output) |
| Prime / 720P | Credit rate: 25.2 per second of total video duration (input + output) |
| Prime / 1080P | Credit rate: 50.4 per second of total video duration (input + output) |
Request fields
Set model at the top level. Put model-specific controls and reference inputs in params, using the format documented for this model.
| Key | Type | Required | Default | Description |
|---|---|---|---|---|
| model | string | Yes | wan-3-0-video | Set model to wan-3-0-video. |
| prompt | string | Yes | - | Maximum 20000 characters for this model. |
| params | object | No | - | The model-specific params object. Use the documented keys and reference-file format for this model. |
| client_request_id | string | No | - | Optional ID for tracing this request in your system. It does not replace Idempotency-Key. |
Model parameters
| Key | Type | Required | Default | Range | Options | Description |
|---|---|---|---|---|---|---|
| seedance_scene | select | No | text | - | text, frames, reference | Choose one exclusive input contract before uploading media. |
| variant | select | No | standard | - | standard, prime | Standard and Prime use the same controls but different per-second rates. |
| resolution | select | No | 1080P | - | 480P, 720P, 1080P | The reservation is the variant-and-resolution rate multiplied by verified input-video seconds plus reserved output seconds, rounded up once. Intelligent duration reserves 30 output seconds and is unavailable with reference video. |
| aspect_ratio | select | No | adaptive | - | adaptive, 16:9, 4:3, 1:1, 3:4, 9:16 | Choose adaptive framing or one fixed output ratio. |
| duration | number | No | 5 | min -1 / max 30 / step 1 | - | Choose -1 for intelligent duration or a whole number from 2 through 30 seconds. Intelligent duration reserves 30 output seconds and cannot be used with reference video. |
| audio | select | No | true | - | true, false | Choose whether the generated video should include model-created audio. |
| seed | number | No | - | min 0 / max 2147483647 / step 1 | - | Keep the prompt, reference inputs, and settings unchanged when reusing a seed. Allowed seed values and defaults depend on the model, and identical results are not guaranteed. |
Upload policy
Upload reference files through Files API first. Keep the original URLs, verified metadata, and tokens. Follow this model's request example: some models use params.referenceMediaItems, while others use different fields.
Guide frames or signed multimodal references: Frames accepts a required first image and one optional last image. Reference accepts up to 10 JPEG, non-transparent PNG, WebP, or BMP images at 20 MB each, 5 MP4/MOV videos at 95 MB and 1-15 seconds each, and 5 MP3/WAV audio clips at 15 MB and 1-15 seconds each; video and audio totals are each capped at 15 seconds.
20
image, video, audio
When duration verification is required, use duration_token from /api/v1/files as durationToken in the request. Keep any additional signed metadata this model requires.
| kind | Max size | MIME types |
|---|---|---|
| image | 20 MB | image/jpeg, image/png, image/bmp, image/webp |
| video | 95 MB | video/mp4, video/quicktime |
| audio | 15 MB | audio/mpeg, audio/wav, audio/x-wav |
Minimal request
{
"model": "wan-3-0-video",
"prompt": "A camera slowly circles a product bottle on a studio table.",
"params": {
"seedance_scene": "text",
"variant": "standard",
"resolution": "1080P",
"aspect_ratio": "adaptive",
"duration": 5,
"audio": "true",
"seed": 0
}
}Reference-file request
{
"model": "wan-3-0-video",
"prompt": "A camera slowly circles a product bottle on a studio table.",
"params": {
"seedance_scene": "reference",
"variant": "standard",
"resolution": "1080P",
"aspect_ratio": "adaptive",
"duration": 5,
"audio": "true",
"seed": 0,
"referenceMediaItems": [
{
"url": "https://cdn.example.com/reference-image.png",
"kind": "image",
"name": "reference-image.png",
"mimeType": "image/png",
"width": 1024,
"height": 1024,
"sizeBytes": 1048576,
"imageDimensionsToken": "image_dimensions_token_from_original_files_api_upload_response"
}
]
}
}Example response
An accepted generation request returns a task ID. Poll the status endpoint until the task succeeds or fails. A status request failure does not mean generation failed.
{
"id": "task_wan_3_0_video_example",
"status": "queued",
"model": "wan-3-0-video",
"reserved_credits": 160,
"final_credits": 0,
"settlement_status": "RESERVED",
"created_at": "2026-05-11T00:00:00.000Z",
"updated_at": "2026-05-11T00:00:00.000Z",
"result": null,
"error": null
}Common errors
validation_failed, insufficient_credits, idempotency_conflict, rate_limited, not_found
Some modes require Files API reference uploads.