Available21 endpoints

Wan 3.0 API & Wan 3.0 Prime API — Image & Video Generation

Use the Wan 3.0 API for text-to-video, image-to-video, and reference-to-video generation with synchronized audio, thinking mode, and up to 1080p output. Wan 3.0 Prime runs the same workflows at a higher-fidelity tier.Text-to-image and image-editing endpoints are coming soon. Every live workflow uses Muapi's asynchronous submit-and-poll pattern, so one integration can switch between modes and quality tiers.

Get a Wan API Key Try Text to Video Try Wan 3.0 Prime

Wan 3.0 and Wan 3.0 Prime are available on Muapi

Choose an endpoint, submit a request with your Muapi API key, and poll the returned request ID for the final image or video URL.

Wan 3.0Standard text, image, and reference-to-video workflows3 endpoints

T2VAvailable

Standard

Wan 3.0 Text to Video

Turn a written scene description into generated video with synchronized audio through one Muapi endpoint.

Up to 1080p

Pay per second

Open model page

I2VAvailable

Standard

Wan 3.0 Image to Video

Animate a source image with a motion prompt while keeping the input image as the visual starting point.

Up to 1080p

Pay per second

Open model page

R2VAvailable

Standard

Wan 3.0 Reference to Video

Guide a video with up to 10 reference images, 5 reference videos, and 5 reference audios for consistent scenes.

Up to 1080p

Pay per second

Open model page

Wan 3.0 PrimeHigher-fidelity output for final and client-facing work3 endpoints

PrimeAvailable

Prime

Wan 3.0 Prime Text to Video

Generate premium-quality synchronized-audio video from a written scene description at the higher-fidelity Prime tier.

480p–1080p

$0.068–$0.28/sec

Open model page

PrimeAvailable

Prime

Wan 3.0 Prime Image to Video

Animate a source image with sharper detail and steadier motion than the standard tier.

480p–1080p

$0.068–$0.28/sec

Open model page

PrimeAvailable

Prime

Wan 3.0 Prime Reference to Video

Generate premium reference-guided video from up to 10 images, 5 videos, and 5 audio clips.

480p–1080p

$0.068–$0.28/sec

Open model page

Wan 3.0 SpicyBold, high-contrast, high-motion video variants3 endpoints

SpicyAvailable

Spicy

Wan 3.0 Spicy Text to Video

Create bold, high-contrast, high-motion text-to-video with synchronized audio.

Up to 1080p

Pay per second

Open model page

SpicyAvailable

Spicy

Wan 3.0 Spicy Image to Video

Animate a source image with bold, high-contrast motion and synchronized audio.

Up to 1080p

Pay per second

Open model page

SpicyAvailable

Spicy

Wan 3.0 Spicy Reference to Video

Generate bold reference-guided video from images, videos, and audio references.

Up to 1080p

Pay per second

Open model page

Coming soonText-to-image and image-editing endpoints2 endpoints

T2IComing Soon

Coming soon

Wan 3.0 Text to Image

Generate images from a natural-language prompt through Muapi's asynchronous API. Coming soon.

Image

Coming soon

View Details

EditComing Soon

Coming soon

Wan 3.0 Image Edit

Apply an instruction prompt to a source image and receive an edited image URL. Coming soon.

Image

Coming soon

View Details

What is the Wan 3.0 API?

Wan 3.0 is Alibaba's image and video generation family exposed through Muapi. The live text-to-video, image-to-video, and reference-to-video endpoints generate synchronized audio, support thinking mode, and can reach 1080p output.

Wan 3.0 Prime is a drop-in higher-fidelity tier with the same prompt, resolution, aspect_ratio, and duration shape. Text-to-image and image-editing endpoints are listed as coming soon, while Spicy variants target bolder high-motion content.

Wan 3.0 API capabilities

Text-to-video with audio

Generate a video with synchronized audio directly from a written scene or shot brief.

Image-to-video with audio

Animate a supplied image, with optional end-frame guidance, into video with synchronized audio.

Reference-to-video

Guide a generated video with up to 10 reference images, 5 reference videos, and 5 reference audios.

Thinking mode

Enable a deeper planning pass for complex, multi-subject, or multi-step prompts.

One API key

Use Muapi authentication, billing, and task responses across standard, Prime, and Spicy workflows.

Asynchronous generation

Submit a task, store its request ID, and poll for the completed image or video output.

Wan 3.0 tiers

Tier	Workflows	Resolution	Best For
Wan 3.0	Text, image, and reference to video	Up to 1080p	General production generation
Wan 3.0 Prime	Text, image, and reference to video	480p, 720p, 1080p	Hero content and client deliverables
Wan 3.0 Spicy	Text, image, and reference to video	Up to 1080p	Bold, high-contrast, high-motion scenes

Wan 3.0 API endpoints

Every Wan request uses the same Muapi REST contract: submit JSON with the x-api-key header, receive a request ID, and poll the standard prediction result endpoint.

Submit a Wan 3.0 task

curl -X POST https://api.muapi.ai/api/v1/wan3.0-text-to-video \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"A cinematic aerial shot of mist moving through a mountain valley at sunrise.","resolution":"720p","duration":5}'

# Response: {"request_id":"REQUEST_ID"}

Call the standard endpoint that matches your workflow, such as wan3.0-text-to-video or wan3.0-reference-to-video.

Retrieve the completed result

curl https://api.muapi.ai/api/v1/predictions/REQUEST_ID/result \
  -H "x-api-key: YOUR_API_KEY"

# Prime uses the same request shape at /wan3.0-prime-text-to-video.

Poll until the task completes, then read the generated image or video URL from outputs or the media field.

Wan 3.0 API FAQ

What can I create with Wan 3.0?

Wan 3.0 provides text-to-video, image-to-video, and reference-to-video endpoints through Muapi, each with synchronized audio. Text-to-image and image editing are coming soon.

What is the Wan 3.0 Prime API?

Wan 3.0 Prime is the higher-fidelity tier. It exposes the same text-to-video, image-to-video, and reference-to-video request shape for sharper detail and steadier motion.

How is Wan 3.0 Prime priced?

Prime is billed at $0.068 per second at 480p, $0.14 per second at 720p, and $0.28 per second at 1080p. The completed task response includes charge details.

How do I access Wan 3.0 or Wan 3.0 Prime?

Create a Muapi API key, send it in the x-api-key header, and call the endpoint matching your selected workflow and tier.

Can I use a ComfyUI workflow?

Yes. The Wan 3.0 ComfyUI node pack provides API-key, generation, image-upload, polling, and media-saver nodes.

How are Wan 3.0 requests completed?

Generation is asynchronous. Store the request ID returned by submission, then poll the prediction result endpoint or use a webhook.

Which inputs does Reference to Video require?

Send a prompt plus up to 10 reference images, 5 reference videos, and 5 reference audios. The same limits apply to the Prime reference workflow.

How is Wan 3.0 billed?

Wan 3.0 uses Muapi's pay-per-generation billing model, priced by resolution and duration. The completed response includes exact charge details.

Explore Wan Spicy →See the dedicated Wan Spicy landing page for bold high-motion workflows.Browse video models →Compare Wan with other live text-to-video and image-to-video APIs.Create an API key →Start generating with the Wan family through Muapi.

Ready to build with Wan 3.0?

Use one Muapi integration for standard, Prime, and Spicy image-to-video workflows.

Get an API Key Try Wan 3.0