Wan 3.0
Generate 2–30 second videos at 720p or 1080p from text, from one or more images, or from reference videos and audio.
- Asynchronous: the create call returns a task ID; the video arrives when the task succeeds.
- Clips of 2 to 30 seconds in one request;
durationis a whole number of seconds. - Four ways in: text only, one image, several images (up to 10), or reference videos and audio (up to 5 of each). Images and references cannot be mixed.
- Billed by the resolution and the number of seconds you request. A failed task costs nothing.
Opens this model in the API Explorer. Enter your BeatAPI API key to create a task: the call is real and is billed to your own balance.
Model IDs
Two Wan 3.0 models share this endpoint and accept exactly the same request. The values below come straight from the gateway contract.
Endpoint and authentication
POST https://api.beatapi.io/v1/videos/tasks
Authorization
string
Required
Your BeatAPI API key, sent as Bearer <BEATAPI_API_KEY>. Create keys in the Dashboard. Keep keys on your server; never ship them in a browser or mobile app.
Send the body as JSON with Content-Type: application/json. Idempotency-Key is optional: send a unique value (at most 255 characters) per logical request and reuse it only to retry that exact body. Within 24 hours a retry with the same key and body returns the first response again with Idempotent-Replayed: true; the same key with a different body returns 409 idempotency_conflict. Responses other than 2xx are not stored, so a retry after a 400 or 402 runs again.
How a request works
Create the task
POST the parameters below to the endpoint. A 201 means the task was accepted and its price reserved from your balance; the work runs in the background. Save data.id.
Wait for it to finish
Call GET /v1/tasks/{task_id} and wait data.poll_after_seconds between calls (5 s for images, 8 s for videos) until status is succeeded or failed. Or register a webhook for task.succeeded and task.failed; keep polling as the fallback, because a task stopped by the processing timeout sends no event.
Save the result
On succeeded, download every data.output.media[].url and store the files you need; BeatAPI does not promise how long result URLs stay available. On failed, read data.error_code and data.error_message: the reserved amount was returned to your balance, and data.retryable says whether sending the same request again can succeed.
Input modes
Request parameters
model
string
Required
The model to run.
Value: wan-3.0
If the value is wrong
- Missing:
"model" is required - An image model sent to this endpoint:
"model" nano-banana-2 is served by POST /v1/images/tasks, not this endpoint
prompt
string
Required
What happens in the video: the subject, the action and the camera. With references, say what each input is for.
Length: 1–5000 characters
- Length is counted in characters (a CJK character counts as one).
If the value is wrong
- Missing:
"prompt" is required - Empty or longer than the limit:
"prompt" has an unsupported length - Not a string:
"prompt" must be a string
images
string[]
Optional
Pictures to make the video from: one image, or several in the order you want them used.
Items: 1–10
Each item is a public https:// URL. For a local file, upload it first with POST /v1/files and pass the returned data.url.
- Each link must be a public
https://URL. The gateway does not download or measure the files when the task is created. - Cannot be sent together with
reference_videosorreference_audios. aspect_ratioandresolutionkeep their defaults (16:9,720p) when you leave them out, also when you send images: the gateway does not read them from the image. Send the shape you want.
If the value is wrong
- More than 10 links:
"images" accepts at most 10 items - Empty array:
"images" requires at least 1 item - Not an array:
"images" must be an array - Not an https:// link:
"images[0]" must be a public HTTPS URL - Combined with a reference field:
Cannot combine "images" with reference inputs in one task
reference_videos
string[]
Optional
Videos the model uses as reference for the new video.
Items: 1–5
Each item is a public https:// URL. For a local file, upload it first with POST /v1/files and pass the returned data.url.
- Public
https://links, up to 5. The gateway does not download, measure or limit them when the task is created, so a clip the model cannot use fails the task afterwards (refunded). - Cannot be sent together with
images.
If the value is wrong
- More than 5 links:
"reference_videos" accepts at most 5 items - Combined with
images:Cannot combine "images" with reference inputs in one task
reference_audios
string[]
Optional
Music, voice or sound clips the model uses as reference.
Items: 1–5
Each item is a public https:// URL. For a local file, upload it first with POST /v1/files and pass the returned data.url.
- Public
https://links, up to 5. Not downloaded or measured when the task is created. - Cannot be sent together with
images.
If the value is wrong
- More than 5 links:
"reference_audios" accepts at most 5 items
duration
integer
OptionalDefault: 5
Length of the video in seconds, a whole number.
Default: 5
Range: 2–30
- If you leave it out,
5is used and billed. - Seconds are billed (see Billing), so this is the main lever on the price.
-1(a model-chosen length) is not accepted: send a whole number from the range.
If the value is wrong
- Outside 2–30, not a whole number, or sent as a string:
"duration" is outside its supported range
aspect_ratio
string
OptionalDefault: 16:9
Shape of the video as width:height.
Allowed values: 16:9, 9:16, 1:1, 4:3, 3:4
Default: 16:9
- If you leave it out,
16:9is used, also when you send images or references. adaptiveis not offered by this model.
If the value is wrong
- A value not in the list:
"aspect_ratio" must be one of: [16:9 9:16 1:1 4:3 3:4]
resolution
string
OptionalDefault: 720p
Output resolution. 1080p costs more per second than 720p.
Allowed values: 720p, 1080p
Default: 720p
- Lower case only. 480p is not available.
If the value is wrong
- A value not in the list (for example
480por720P):"resolution" must be one of: [720p 1080p]
The gateway also checks these combinations before creating the task:
- images cannot be combined with reference inputs
Input media limits
The gateway reads every input before the task is created and refuses one outside these limits with a 400 bad_request that names the input. Nothing is charged.
- The gateway does not read your image, video or audio files when it creates the task, so no size, resolution, length or format limit is checked for this model; only the field rules above apply.
- A link the model cannot fetch or use fails the task after it was created, usually with
bad_request(orcontent_policy_violationwhen moderation refuses an input), and the task is refunded in full. - Have a local file? Upload it with
POST /v1/files(png, jpg, jpeg, webp, mp3, wav, aac, m4a, mp4 or mov; up to 50 MB, 100 MB for video) and pass the returneddata.url.
Which inputs go together
Fields this model does not accept
Sending one of these is refused before anything is charged, instead of being ignored:
reference_images,generate_audio,seed,quality,sound,task_type,output_format,watermarkand the other fields of other video models →field "seed" is not supported by model wan-3.0(with the field you sent). Put pictures inimages.- Any field the video endpoint does not know at all →
unknown field: <name>.
Request examples
Text to video
A 5-second 720p landscape clip.
Image to video
A 10-second 1080p square clip made from one image.
Several images
Two images, passed to the model in list order.
Reference video and audio
Replace the video link with your own public MP4. A 30-second portrait clip in the style of the reference.
Responses
Create a task (201)
The task object. output is null until the task succeeds. Fields marked “while running” disappear once the task finishes.
Finished task
GET /v1/tasks/{task_id} returns HTTP 200 with status: "succeeded" and the result in data.output.
Output fields
Failed task
A failed task is still HTTP 200 on GET /v1/tasks/{task_id}: the failure is in the body. The reservation is returned in full, so nothing is charged.
Complete example
Create a task, wait for it with the server’s polling hint, and print the result URLs. Set BEATAPI_API_KEY in your environment and install requests.
Billing
- The price follows the resolution and the number of seconds you request (
duration, 5 if you leave it out). 1080p costs more per second than 720p.aspect_ratiodoes not change it. - The table below shows 8-second clips; other lengths are priced per second at the same rate for their resolution.
- The price is reserved when the task is created;
data.usage.billable_duration_secondsshows the seconds it is based on. - A failed task, including one refused by moderation after submission, is refunded in full.
Current list prices, the same as on Pricing. An account with a negotiated discount pays less; data.usage on the task always shows the amount actually charged.
Common errors
HTTP errors at a glance
Errors before a task exists arrive as a non-2xx response, and nothing is charged. Branch on error.code or error.retryable; message names the problem. The full list and retry policy are on Errors.
Authentication
Send your API key as Authorization: Bearer <BEATAPI_API_KEY>.
Headers
Send the body as JSON with Content-Type: application/json. Idempotency-Key is optional: send a unique value (at most 255 characters) per logical request and reuse it only to retry that exact body. Within 24 hours a retry with the same key and body returns the first response again with Idempotent-Replayed: true; the same key with a different body returns 409 idempotency_conflict. Responses other than 2xx are not stored, so a retry after a 400 or 402 runs again.
Request
The model to run.
Value: wan-3.0
If the value is wrong
- Missing:
"model" is required - An image model sent to this endpoint:
"model" nano-banana-2 is served by POST /v1/images/tasks, not this endpoint
What happens in the video: the subject, the action and the camera. With references, say what each input is for.
Length: 1–5000 characters
- Length is counted in characters (a CJK character counts as one).
If the value is wrong
- Missing:
"prompt" is required - Empty or longer than the limit:
"prompt" has an unsupported length - Not a string:
"prompt" must be a string
Shape of the video as width:height.
Allowed values: 16:9, 9:16, 1:1, 4:3, 3:4
Default: 16:9
- If you leave it out,
16:9is used, also when you send images or references. adaptiveis not offered by this model.
If the value is wrong
- A value not in the list:
"aspect_ratio" must be one of: [16:9 9:16 1:1 4:3 3:4]
Length of the video in seconds, a whole number.
Default: 5
Range: 2–30
- If you leave it out,
5is used and billed. - Seconds are billed (see Billing), so this is the main lever on the price.
-1(a model-chosen length) is not accepted: send a whole number from the range.
If the value is wrong
- Outside 2–30, not a whole number, or sent as a string:
"duration" is outside its supported range
Pictures to make the video from: one image, or several in the order you want them used.
Items: 1–10
Each item is a public https:// URL. For a local file, upload it first with POST /v1/files and pass the returned data.url.
- Each link must be a public
https://URL. The gateway does not download or measure the files when the task is created. - Cannot be sent together with
reference_videosorreference_audios. aspect_ratioandresolutionkeep their defaults (16:9,720p) when you leave them out, also when you send images: the gateway does not read them from the image. Send the shape you want.
If the value is wrong
- More than 10 links:
"images" accepts at most 10 items - Empty array:
"images" requires at least 1 item - Not an array:
"images" must be an array - Not an https:// link:
"images[0]" must be a public HTTPS URL - Combined with a reference field:
Cannot combine "images" with reference inputs in one task
Music, voice or sound clips the model uses as reference.
Items: 1–5
Each item is a public https:// URL. For a local file, upload it first with POST /v1/files and pass the returned data.url.
- Public
https://links, up to 5. Not downloaded or measured when the task is created. - Cannot be sent together with
images.
If the value is wrong
- More than 5 links:
"reference_audios" accepts at most 5 items
Videos the model uses as reference for the new video.
Items: 1–5
Each item is a public https:// URL. For a local file, upload it first with POST /v1/files and pass the returned data.url.
- Public
https://links, up to 5. The gateway does not download, measure or limit them when the task is created, so a clip the model cannot use fails the task afterwards (refunded). - Cannot be sent together with
images.
If the value is wrong
- More than 5 links:
"reference_videos" accepts at most 5 items - Combined with
images:Cannot combine "images" with reference inputs in one task
Output resolution. 1080p costs more per second than 720p.
Allowed values: 720p, 1080p
Default: 720p
- Lower case only. 480p is not available.
If the value is wrong
- A value not in the list (for example
480por720P):"resolution" must be one of: [720p 1080p]
Response
The task object. output is null until the task succeeds. Fields marked “while running” disappear once the task finishes.

