Wan 3.0 Prime

Model IDalibaba/wan-3.0-prime/image-to-video

Alibaba
Image to video

Animate a reference image into a video, guided by a text prompt.

Model interface

API

https://open.scenepond.ai/v1

Authenticate every request with Authorization: Bearer and your Scenepond API key. Keep the key on your server.

LLM index

Copy the complete model reference, including every published protocol, for your AI assistant.

API protocol

POST/v1/tasks

Request parameters

Parameter Required Type Description

model

Required

string

Use this exact public model ID.

Constraints

const = "alibaba/wan-3.0-prime/image-to-video"

parameters

Required

object

Generation parameters for this model.

These fields apply when parameters is supplied. A required child does not make its optional parent required.

Fields in parameters
Parameter	Required	Type	Description
`parameters.duration`	Optional	`number`	Requested video duration in seconds. Default `5` Constraints minimum = 2 maximum = 30
`parameters.resolution`	Optional	`string`	Output resolution. Values are case-sensitive and specific to this model. Default `"1080p"` Constraints enum = ["480p","720p","1080p"]
`parameters.seed`	Optional	`integer`	Integer seed for controlling generation randomness. Constraints minimum = 0 maximum = 2147483647
`parameters.enable_prompt_expansion`	Optional	`boolean`	Whether the provider expands the prompt before generation. Default `true`
`parameters.audio`	Optional	`boolean`	Whether audio generation is requested. Default `true`
`parameters.enable_safety_checker`	Optional	`boolean`	Whether the provider safety checker is enabled. Provider policy may reject attempts to disable it. Default `true`
`parameters.aspect_ratio`	Optional	`string`	Requested output width-to-height ratio. Default `"adaptive"` Constraints enum = ["adaptive","16:9","4:3","1:1","3:4","9:16"]
`parameters.enable_thinking`	Optional	`boolean`	Whether the provider uses its thinking option when preparing generation. Default `false`
`parameters.prompt`	Optional	`string`	Describe the subject, scene, and desired generation. Constraints maxLength = 20000
`parameters.image_urls`	Required	`string[]`	Reference image URLs, in first-frame then last-frame order.

Request notes

Images and videos use the same task API. Select a model; channel selection is automatic.
Authenticate every request with Authorization: Bearer and your Scenepond API key. Keep the key on your server.
Submit once, save task_id, then poll until succeeded or failed. Download results from the artifacts endpoint.
Creation returns the task ID after acceptance. Some tasks may already be complete when the ID is returned.
Accepted submissions return HTTP 202 with Location: /v1/tasks/{task_id}.
Generated artifacts are stored for 14 days. Download them before expires_at; expired artifacts cannot be recovered.
Do not automatically resubmit a timed-out POST. It may already have created a billable task.
Parameters and limits vary by model. Only the fields listed for this model are accepted.
Generated images and videos are stored for 14 days. Download and save them before expiry.
Each stored artifact includes expires_at, its expiry time as a Unix timestamp in seconds. Use that value for each file; do not calculate expiry from the task creation time.
Some older results may omit expires_at. This does not mean unlimited storage; download them as soon as possible.
After expiry, content requests authenticated with an API key (without an access query parameter) return HTTP 410 with code artifact_expired. Private access links may return 404 for unavailable content. Expired files cannot be downloaded or recovered.
Keep content_url private. Saving a link does not preserve the file; download the actual bytes to your own storage before expires_at.

Minimum request

1curl --fail-with-body -X POST "https://open.scenepond.ai/v1/tasks" \
2  -H "Authorization: Bearer $SCENEPOND_API_KEY" \
3  -H "Content-Type: application/json" \
4  --data-binary @- <<'JSON'
5{
6  "model": "alibaba/wan-3.0-prime/image-to-video",
7  "parameters": {
8    "image_urls": [
9      "https://example.com/reference.png"
10    ]
11  }
12}
13JSON

Run this example in a shell with cURL installed. Set SCENEPOND_API_KEY before running.

Illustrative responses

Response examples show the structure only. IDs, URLs, and values are placeholders.

Submission response

1{
2  "task_id": "task_EXAMPLE",
3  "model": "alibaba/wan-3.0-prime/image-to-video",
4  "status": "queued",
5  "progress": 0,
6  "created_at": 1700000000,
7  "finished_at": 0,
8  "error": null,
9  "links": {
10    "self": "/v1/tasks/task_EXAMPLE",
11    "artifacts": "/v1/tasks/task_EXAMPLE/artifacts"
12  }
13}

Completed task status

1{
2  "task_id": "task_EXAMPLE",
3  "model": "alibaba/wan-3.0-prime/image-to-video",
4  "status": "succeeded",
5  "progress": 100,
6  "created_at": 1700000000,
7  "finished_at": 1700000060,
8  "error": null,
9  "links": {
10    "self": "/v1/tasks/task_EXAMPLE",
11    "artifacts": "/v1/tasks/task_EXAMPLE/artifacts"
12  }
13}

Artifact listing

1{
2  "task_id": "task_EXAMPLE",
3  "artifacts": [
4    {
5      "key": "video",
6      "type": "video",
7      "mime_type": "video/mp4",
8      "content_url": "https://open.scenepond.ai/v1/tasks/task_EXAMPLE/artifacts/video/content",
9      "expires_at": 1701209660
10    }
11  ]
12}

Expired artifact response (API key authentication)

1{
2  "error": {
3    "message": "Artifact content has expired or is no longer available",
4    "type": "artifact_expired",
5    "code": "artifact_expired"
6  }
7}

Follow-up requests

2. Check task status

Poll every few seconds until succeeded or failed.

1curl --fail-with-body -X GET "https://open.scenepond.ai/v1/tasks/$SCENEPOND_TASK_ID" \
2  -H "Authorization: Bearer $SCENEPOND_API_KEY"

Run this example in a shell with cURL installed. Set SCENEPOND_API_KEY before running.

3. Get the results

After succeeded, list artifacts and download each content_url with the same API key.

1curl --fail-with-body -X GET "https://open.scenepond.ai/v1/tasks/$SCENEPOND_TASK_ID/artifacts" \
2  -H "Authorization: Bearer $SCENEPOND_API_KEY"

Run this example in a shell with cURL installed. Set SCENEPOND_API_KEY before running.

4. Download before expiry

Set SCENEPOND_TASK_ID to task_id and SCENEPOND_ARTIFACT_KEY to artifacts[].key. Download the binary file before expires_at. The content endpoint supports GET, HEAD, and Range requests; saving content_url alone does not save the media.

1curl --fail-with-body --output output.bin -X GET "https://open.scenepond.ai/v1/tasks/$SCENEPOND_TASK_ID/artifacts/$SCENEPOND_ARTIFACT_KEY/content" \
2  -H "Authorization: Bearer $SCENEPOND_API_KEY"

Run this example in a shell with cURL installed. Set SCENEPOND_API_KEY before running.

Error codes

API errors
Status	Next step
`400`	Check the model ID, required fields, types, and allowed parameter values.
`401`	Check the API key and whether it is enabled.
`403`	Check key restrictions and model permissions.
`410`	artifact_expired: the stored media has expired or is no longer available. Use a previously downloaded copy; retrying cannot restore an expired file.
`429`	Respect the returned retry delay and lower your request rate.
`5xx`	Inspect the error response. Avoid blindly retrying paid generation requests.

Generated artifacts are stored for 14 days. Download them before expires_at; expired artifacts cannot be recovered.

A failed task can return generation_failed without a detailed cause. Inspect the returned error and usage record before resubmitting.

API

https://open.scenepond.ai/v1

Authenticate every request with Authorization: Bearer and your Scenepond API key. Keep the key on your server.

LLM index

Copy the complete model reference, including every published protocol, for your AI assistant.

API protocol

POST/v1/tasks

Request parameters

Parameter Required Type Description

model

Required

string

Use this exact public model ID.

Constraints

const = "alibaba/wan-3.0-prime/image-to-video"

parameters

Required

object

Generation parameters for this model.

These fields apply when parameters is supplied. A required child does not make its optional parent required.

Fields in parameters
Parameter	Required	Type	Description
`parameters.duration`	Optional	`number`	Requested video duration in seconds. Default `5` Constraints minimum = 2 maximum = 30
`parameters.resolution`	Optional	`string`	Output resolution. Values are case-sensitive and specific to this model. Default `"1080p"` Constraints enum = ["480p","720p","1080p"]
`parameters.seed`	Optional	`integer`	Integer seed for controlling generation randomness. Constraints minimum = 0 maximum = 2147483647
`parameters.enable_prompt_expansion`	Optional	`boolean`	Whether the provider expands the prompt before generation. Default `true`
`parameters.audio`	Optional	`boolean`	Whether audio generation is requested. Default `true`
`parameters.enable_safety_checker`	Optional	`boolean`	Whether the provider safety checker is enabled. Provider policy may reject attempts to disable it. Default `true`
`parameters.aspect_ratio`	Optional	`string`	Requested output width-to-height ratio. Default `"adaptive"` Constraints enum = ["adaptive","16:9","4:3","1:1","3:4","9:16"]
`parameters.enable_thinking`	Optional	`boolean`	Whether the provider uses its thinking option when preparing generation. Default `false`
`parameters.prompt`	Optional	`string`	Describe the subject, scene, and desired generation. Constraints maxLength = 20000
`parameters.image_urls`	Required	`string[]`	Reference image URLs, in first-frame then last-frame order.

Request notes

Images and videos use the same task API. Select a model; channel selection is automatic.
Authenticate every request with Authorization: Bearer and your Scenepond API key. Keep the key on your server.
Submit once, save task_id, then poll until succeeded or failed. Download results from the artifacts endpoint.
Creation returns the task ID after acceptance. Some tasks may already be complete when the ID is returned.
Accepted submissions return HTTP 202 with Location: /v1/tasks/{task_id}.
Generated artifacts are stored for 14 days. Download them before expires_at; expired artifacts cannot be recovered.
Do not automatically resubmit a timed-out POST. It may already have created a billable task.
Parameters and limits vary by model. Only the fields listed for this model are accepted.
Generated images and videos are stored for 14 days. Download and save them before expiry.
Each stored artifact includes expires_at, its expiry time as a Unix timestamp in seconds. Use that value for each file; do not calculate expiry from the task creation time.
Some older results may omit expires_at. This does not mean unlimited storage; download them as soon as possible.
After expiry, content requests authenticated with an API key (without an access query parameter) return HTTP 410 with code artifact_expired. Private access links may return 404 for unavailable content. Expired files cannot be downloaded or recovered.
Keep content_url private. Saving a link does not preserve the file; download the actual bytes to your own storage before expires_at.

Minimum request

1curl --fail-with-body -X POST "https://open.scenepond.ai/v1/tasks" \
2  -H "Authorization: Bearer $SCENEPOND_API_KEY" \
3  -H "Content-Type: application/json" \
4  --data-binary @- <<'JSON'
5{
6  "model": "alibaba/wan-3.0-prime/image-to-video",
7  "parameters": {
8    "image_urls": [
9      "https://example.com/reference.png"
10    ]
11  }
12}
13JSON

Run this example in a shell with cURL installed. Set SCENEPOND_API_KEY before running.

Illustrative responses

Response examples show the structure only. IDs, URLs, and values are placeholders.

Submission response

1{
2  "task_id": "task_EXAMPLE",
3  "model": "alibaba/wan-3.0-prime/image-to-video",
4  "status": "queued",
5  "progress": 0,
6  "created_at": 1700000000,
7  "finished_at": 0,
8  "error": null,
9  "links": {
10    "self": "/v1/tasks/task_EXAMPLE",
11    "artifacts": "/v1/tasks/task_EXAMPLE/artifacts"
12  }
13}

Completed task status

1{
2  "task_id": "task_EXAMPLE",
3  "model": "alibaba/wan-3.0-prime/image-to-video",
4  "status": "succeeded",
5  "progress": 100,
6  "created_at": 1700000000,
7  "finished_at": 1700000060,
8  "error": null,
9  "links": {
10    "self": "/v1/tasks/task_EXAMPLE",
11    "artifacts": "/v1/tasks/task_EXAMPLE/artifacts"
12  }
13}

Artifact listing

1{
2  "task_id": "task_EXAMPLE",
3  "artifacts": [
4    {
5      "key": "video",
6      "type": "video",
7      "mime_type": "video/mp4",
8      "content_url": "https://open.scenepond.ai/v1/tasks/task_EXAMPLE/artifacts/video/content",
9      "expires_at": 1701209660
10    }
11  ]
12}

Expired artifact response (API key authentication)

1{
2  "error": {
3    "message": "Artifact content has expired or is no longer available",
4    "type": "artifact_expired",
5    "code": "artifact_expired"
6  }
7}

Follow-up requests

2. Check task status

Poll every few seconds until succeeded or failed.

1curl --fail-with-body -X GET "https://open.scenepond.ai/v1/tasks/$SCENEPOND_TASK_ID" \
2  -H "Authorization: Bearer $SCENEPOND_API_KEY"

Run this example in a shell with cURL installed. Set SCENEPOND_API_KEY before running.

3. Get the results

After succeeded, list artifacts and download each content_url with the same API key.

1curl --fail-with-body -X GET "https://open.scenepond.ai/v1/tasks/$SCENEPOND_TASK_ID/artifacts" \
2  -H "Authorization: Bearer $SCENEPOND_API_KEY"

Run this example in a shell with cURL installed. Set SCENEPOND_API_KEY before running.

4. Download before expiry

1curl --fail-with-body --output output.bin -X GET "https://open.scenepond.ai/v1/tasks/$SCENEPOND_TASK_ID/artifacts/$SCENEPOND_ARTIFACT_KEY/content" \
2  -H "Authorization: Bearer $SCENEPOND_API_KEY"

Run this example in a shell with cURL installed. Set SCENEPOND_API_KEY before running.

Error codes

API errors
Status	Next step
`400`	Check the model ID, required fields, types, and allowed parameter values.
`401`	Check the API key and whether it is enabled.
`403`	Check key restrictions and model permissions.
`410`	artifact_expired: the stored media has expired or is no longer available. Use a previously downloaded copy; retrying cannot restore an expired file.
`429`	Respect the returned retry delay and lower your request rate.
`5xx`	Inspect the error response. Avoid blindly retrying paid generation requests.

Generated artifacts are stored for 14 days. Download them before expires_at; expired artifacts cannot be recovered.

A failed task can return generation_failed without a detailed cause. Inspect the returned error and usage record before resubmitting.

API

Request parameters

Fields in parameters

Request notes

Minimum request

Illustrative responses

Submission response

Completed task status

Artifact listing

Expired artifact response (API key authentication)

Follow-up requests

2. Check task status

3. Get the results

4. Download before expiry

Error codes

API

Request parameters

Fields in parameters

Request notes

Minimum request

Illustrative responses

Submission response

Completed task status

Artifact listing

Expired artifact response (API key authentication)

Follow-up requests

2. Check task status

3. Get the results

4. Download before expiry

Error codes