Price: from 786 credits per request · ≈ $0.393High stability with detailed usage records on the APIAny platform.
Upload images or paste image URLs for frame control.
Start Frame
Upload 1 image or paste an image URL.
Click to upload or drag and drop
Supported formats: JPG, JPEG, PNG, WEBP
Maximum file size: 10MB; Maximum files: 1
End Frame
Upload 1 image or paste an image URL.
Click to upload or drag and drop
Supported formats: JPG, JPEG, PNG, WEBP
Maximum file size: 10MB; Maximum files: 1
Any integer from 2s to 30s.
Video output resolution.
Video aspect ratio.
Generate audio
Generate synchronized audio.
USD estimate ≈ $2.02: $999 tier: $1 = 2,000 credits.
Real image and video examples made through our models. Preview freely; using a preset never starts generation.
Actual generation model: wan3.0-prime-image-to-video
{
"model": "wan3.0-prime-image-to-video",
"prompt": "Animate the supplied celadon teacup photograph with delicate rising steam and subtle natural light changes. Preserve the exact cup, stone tabletop and framing. Almost locked-off camera with a very slight push-in. Realistic slow motion in the steam, stable cup geometry, calm elegant product cinematography. Single continuous shot. No text, logos, labels, subtitles, graphic overlays or watermark. No cuts. Natural coherent movement, stable geometry.",
"duration": 5,
"quality": "720p",
"aspect_ratio": "adaptive",
"generate_audio": false,
"image_start": "https://s.apiany.ai/web-static/mode-infos/v2/2026-09-20/d04-celadon-tea/image.webp"
}History
Saved locally in this browser
0 running · 0 completed
Billing Rules
Authentication
Every request needs a Bearer token in the Authorization header. Create an API key in the console.
Authorization: Bearer YOUR_API_KEYhttps://apiany.ai/v1/videos/generationsRequest parameters
| Parameter | Type | Required | Notes |
|---|---|---|---|
model | string | Required | Model identifier to invoke. Use this model's ID. |
prompt | string | Required | Text prompt describing what you want to generate. |
duration | number | Optional | Any integer from 2s to 30s. · Range: 2–30 · Default: 5 |
quality | string | Optional | Video output resolution. · Options: 480p, 720p, 1080p · Default: 720p |
aspect_ratio | string | Optional | Video aspect ratio. · Options: adaptive, 16:9, 9:16, 1:1, 4:3, 3:4 · Default: adaptive |
generate_audio | boolean | Optional | Generate synchronized audio. · Default: true |
callback_url | string | Optional | Optional webhook URL called when the async task finishes. |
Request example
curl "https://apiany.ai/v1/videos/generations" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "wan3.0-prime-image-to-video",
"prompt": "Animate the supplied celadon teacup photograph with delicate rising steam and subtle natural light changes. Preserve the exact cup, stone tabletop and framing. Almost locked-off camera with a very slight push-in. Realistic slow motion in the steam, stable cup geometry, calm elegant product cinematography. Single continuous shot. No text, logos, labels, subtitles, graphic overlays or watermark. No cuts. Natural coherent movement, stable geometry.",
"duration": 5,
"quality": "720p",
"aspect_ratio": "adaptive",
"generate_audio": true
}'Response example
{
"task_id": "task_abc123",
"status": "pending",
"poll_url": "/v1/tasks/task_abc123",
"request_id": "req_abc123",
"credits": {
"reserved": 1000
}
}This endpoint is asynchronous: it returns a task_id immediately. Poll the task-status endpoint until status becomes succeeded, then read the result. Generated media links stay valid for 24 hours.
Fast multimodal video generation
Wan 3.0 Prime is a speed-oriented Alibaba video model family exposed through three APIAny model IDs. Choose text-to-video for prompt-led creation, image-to-video for a required first frame and optional final frame, or reference-video when several ordered assets must guide the result.
Every route produces a fixed 2–30 second video at 480p, 720p, or 1080p, supports adaptive and common landscape, portrait, and square ratios, and can request synchronized audio. Pricing is calculated from the selected duration and quality before submission, so fixed-length jobs remain predictable.
Wan 3.0 Prime runs asynchronously. Production applications should save the returned task ID, receive a callback or poll task status, persist completed assets promptly, and validate each route's input rules locally. The public routes do not support cancellation, negative prompts, prompt expansion, video editing, or video extension.
Try Wan 3.0 Prime in the playground
Sources
The quotations below are from official API documentation that APIAny implements against.
The Chat Completions API endpoint will generate a model response from a list of messages comprising a conversation.
The Gemini API provides access to Google's most capable generative AI models.
Use cases
The Wan 3.0 Prime API is used for product workflows that need this model's output. Test the same inputs in the playground, compare related models, and choose the route that meets your quality, latency, and budget requirements.
01
Use Wan 3.0 Prime for composed shots, narrative sequences, and atmosphere-led video concepts. Detailed prompts and reference inputs make camera direction, visual continuity, and mood easier to evaluate.
Try Wan 3.0 Prime in the playground
02
Turn product images or written concepts into review-ready motion with Wan 3.0 Prime. Reference-led generation helps teams explore transitions, camera movement, and short demonstrations before final production.
Try Wan 3.0 Prime in the playgroundCore capabilities
Wan 3.0 Prime API features are the input, output, and workflow traits that matter when you evaluate this model. Available request parameters remain visible in the live API reference on this page.
/01
Describe the requested output or task in text and send it through the documented Wan 3.0 Prime API request.
/02
Provide supported image inputs to guide editing, visual identity, composition, or motion in Wan 3.0 Prime workflows.
/03
Create short video results with Wan 3.0 Prime and retrieve completed media from the asynchronous task workflow.
/04
Use supported reference assets to guide subject identity, style, composition, frames, or motion across generated results.
/05
APIAny advantages
Wan 3.0 Prime on APIAny is a production route with one key, live prices, status, and usage records, so you do not maintain a separate provider integration.
Call Wan 3.0 Prime with an APIAny key and a documented request format. Keep your application integration stable while model versions and upstream routes evolve behind the gateway.
Review the live Wan 3.0 Prime pricing rules before a request, estimate credits in the playground, and inspect request-level usage records after the call completes.
Integration
Integrating the Wan 3.0 Prime API is a three-step path from playground test to authenticated production request. The page keeps the model identifier, request schema, pricing, and response examples together. Treat generation as an asynchronous media pipeline with durable task tracking, validation, and asset delivery.
Sign in to APIAny, create a project API key, and assign only the model scope and budget controls your application needs.
Copy the request example from this page, set the model field to the selected Wan 3.0 Prime version, and send it to the documented APIAny endpoint.
Track status, latency, credits, and returned usage. Compare versions or related models with the same workload before shifting production traffic.
FAQ
Practical answers about Wan 3.0 Prime model IDs, inputs, duration, quality, pricing, references, and asynchronous delivery.
Wan 3.0 Prime is a speed-oriented Alibaba video generation family. APIAny exposes separate text-to-video, image-to-video, and multimodal reference-video model IDs so each request has an explicit input contract.
Use wan3.0-prime-text-to-video for prompt-only creation, wan3.0-prime-image-to-video for a required image_start and optional image_end, and wan3.0-prime-reference-video for ordered image_urls, video_urls, audio_urls, or optional document or web context.
Choose an integer duration from 2 to 30 seconds and quality 480p, 720p, or 1080p. Supported aspect ratios are adaptive, 16:9, 9:16, 1:1, 4:3, and 3:4. APIAny does not currently expose automatic duration because fixed duration provides a reliable pre-request credit estimate.
03
Turn a brief into multiple directions with Wan 3.0 Prime, then refine the strongest option through prompt changes or reference inputs. API-based iteration keeps experiments reproducible and easier to evaluate.
Try Wan 3.0 Prime in the playground
Use supported Wan 3.0 Prime variants to create video workflows that can include synchronized sound or audio controls.
/06
Choose a supported frame shape for square, portrait, landscape, or platform-specific Wan 3.0 Prime output.
/07
Select supported quality or resolution tiers when the final Wan 3.0 Prime asset needs more detail for review or delivery.
/08
Create a task, store its identifier, and poll or receive a callback until the Wan 3.0 Prime generation reaches a terminal state.
/09
Use the faster Wan 3.0 Prime route for interactive experiences, rapid iteration, and workloads where response time matters.
Use model status, channel health, retry policy, and usage logs to operate Wan 3.0 Prime as part of a production workflow instead of treating it as an isolated demo.
APIAny calculates credits from output duration and quality. The live price estimator on this page is authoritative; changing from 480p to 720p or 1080p increases the per-second credit cost, while the audio toggle does not add a separate line item.
Send the required first-frame URL as image_start and, when needed, a second URL as image_end. This route does not accept image_urls. The first frame anchors the opening composition, while the optional final frame guides where the motion should finish.
The reference route accepts up to 10 images, 5 videos, and 5 audio tracks. It can also take one document through model_params.file_url or one web page through model_params.link_url, but those two fields cannot be combined. Image 1, Video 1, and Audio 1 refer to positions within their own arrays.
Store the task ID returned at creation, then use an HTTPS callback or poll task status until it reaches a terminal state. Download or copy successful output promptly because generated result links are temporary, and design retries so the same business job is not submitted twice.
These APIAny routes do not support task cancellation, negative_prompt, prompt_extend, video editing, or video extension. Use a standard or editing-focused video route when the workflow needs a capability that is not present here.
