Alibaba Available on Video Blade

Wan 3.0 Video Prime API

Text to videoImage to videoReference to video

Wan 3.0 Video Prime is the fast version of Wan 3.0 Video: long clips with built-in sound, returned much sooner.

8-second clip from · per second

Live price in USD — you see the exact price before anything runs. Plans start at .

Use from your AI agent Get started

Input image 1 — Example output · first 10 seconds
An Eastern fantasy short in a retro Chinese illustration style: a giant turtle carries palaces above a sea of clouds.
“A 30-second Eastern fantasy short set in a mystical celestial mountain realm. The visual style is inspired by modern Chinese retro calendar illustrations, featuring clean traditional gongbi linework, decorative patterned clouds and waves, aged rice-paper watercolor textures, and a vintage teal-green and peach-orange palette. Avoid photorealism and obvious 3D-rendered aesthetics. A giant celestial turtle floats above an endless sea of clouds, carrying layered mountains and palaces on its back. A fairy rides a golden mythical qilin through the clouds and over a grand celestial festival filled with musicians and dancers, eventually arriving at the central stage as the celebration reaches its climax. Use a third-person cinematic perspective, combining only four main camera techniques: high-speed FPV flight, POV chase shots, match cuts, and slow motion. FPV sequences should feel extremely fast and spectacular, while stylized clouds, ribbons, and waves must retain clean, stable silhouettes without distortion. The pacing begins with a fast establishing sequence, slows slightly for featured performances, accelerates into the climax, then ends with a calm wide shot. Shot 1 — 0–4s High-speed FPV dive through layered clouds, mountain peaks, floating palaces, cranes, and the giant turtle. The camera rapidly descends toward a glowing celestial festival plaza. Shot 2 — 4–11s POV from the fairy riding the golden qilin at extreme speed above the festival. Rush past dancers, musicians, lanterns, and flowing banners. The qilin briefly hovers beneath a glowing sacred tree, creating a sudden moment of stillness, then accelerates toward the main stage. Shot 3 — 11–19s Medium shot to close-up of a pipa musician performing an expressive sequence. Focus on vibrating strings, flowing sleeves, and elegant movement rather than precise finger detail. At the climax, a powerful sweep across the strings transitions into slow motion as the sleeves and strings vibrate dramatically. Shot 4 — 19–21s Brief slow-motion pause over the entire plaza. Hundreds of dancers hold their sleeves suspended in midair while lanterns gradually stop swaying, creating a moment of visual breathing space. Shot 5 — 21–27s A central dancer spins and releases long flame-orange silk ribbons. The ribbons form a huge decorative spiral and finally expand into a glowing flame-like halo. The surrounding dancers raise their sleeves together as the sacred tree brightens. Shot 6 — 27–30s The camera slowly rises into a wide aerial view. The festival, dancers, musicians, and qilin gradually disappear into patterned clouds. End on the celestial mountains floating peacefully above the endless cloud sea. Music & Sound: Blend traditional Chinese instruments—guzheng, konghou, pipa, and bianzhong—with modern ambient electronic music. Begin distant and ethereal, build into energetic percussion during the festival climax, then fade back into quiet guzheng and ambient tones for the ending.”

Input image 2 — Example output · first 10 seconds
An Eastern fantasy short in a retro Chinese illustration style: a giant turtle carries palaces above a sea of clouds.
“A 30-second Eastern fantasy short set in a mystical celestial mountain realm. The visual style is inspired by modern Chinese retro calendar illustrations, featuring clean traditional gongbi linework, decorative patterned clouds and waves, aged rice-paper watercolor textures, and a vintage teal-green and peach-orange palette. Avoid photorealism and obvious 3D-rendered aesthetics. A giant celestial turtle floats above an endless sea of clouds, carrying layered mountains and palaces on its back. A fairy rides a golden mythical qilin through the clouds and over a grand celestial festival filled with musicians and dancers, eventually arriving at the central stage as the celebration reaches its climax. Use a third-person cinematic perspective, combining only four main camera techniques: high-speed FPV flight, POV chase shots, match cuts, and slow motion. FPV sequences should feel extremely fast and spectacular, while stylized clouds, ribbons, and waves must retain clean, stable silhouettes without distortion. The pacing begins with a fast establishing sequence, slows slightly for featured performances, accelerates into the climax, then ends with a calm wide shot. Shot 1 — 0–4s High-speed FPV dive through layered clouds, mountain peaks, floating palaces, cranes, and the giant turtle. The camera rapidly descends toward a glowing celestial festival plaza. Shot 2 — 4–11s POV from the fairy riding the golden qilin at extreme speed above the festival. Rush past dancers, musicians, lanterns, and flowing banners. The qilin briefly hovers beneath a glowing sacred tree, creating a sudden moment of stillness, then accelerates toward the main stage. Shot 3 — 11–19s Medium shot to close-up of a pipa musician performing an expressive sequence. Focus on vibrating strings, flowing sleeves, and elegant movement rather than precise finger detail. At the climax, a powerful sweep across the strings transitions into slow motion as the sleeves and strings vibrate dramatically. Shot 4 — 19–21s Brief slow-motion pause over the entire plaza. Hundreds of dancers hold their sleeves suspended in midair while lanterns gradually stop swaying, creating a moment of visual breathing space. Shot 5 — 21–27s A central dancer spins and releases long flame-orange silk ribbons. The ribbons form a huge decorative spiral and finally expand into a glowing flame-like halo. The surrounding dancers raise their sleeves together as the sacred tree brightens. Shot 6 — 27–30s The camera slowly rises into a wide aerial view. The festival, dancers, musicians, and qilin gradually disappear into patterned clouds. End on the celestial mountains floating peacefully above the endless cloud sea. Music & Sound: Blend traditional Chinese instruments—guzheng, konghou, pipa, and bianzhong—with modern ambient electronic music. Begin distant and ethereal, build into energetic percussion during the festival climax, then fade back into quiet guzheng and ambient tones for the ending.”

What Wan 3.0 Video Prime is good for

Wan 3.0 Video Prime is the high-speed variant of Alibaba's Wan 3.0 Video, built for significantly faster end-to-end turnaround. It can start from a prompt, a first frame or a first and last frame pair, up to 10 reference images, or a single document or webpage, and it creates sound along with the picture. It fits apps, batch runs, and rounds of quick revisions.

Testing many prompt variations quickly before settling on a final cut
Apps and automated pipelines that need videos back fast
Product and marketing clips that start from your own photo
High-volume social content where turnaround time decides the schedule
Longer narrative clips with sound when deadlines are tight

Wan 3.0 Video Prime pricing

Option	Price, USD	Video Blade tokens
480p		tokens
720p		tokens
1080p		tokens

Prices are per second and live from our price list. Tokens are held when a run starts and settled to what was actually used; a failed run costs nothing.

Use Wan 3.0 Video Prime from your AI agent

Create an account on Video Blade and pick a plan — from .
Copy the agent link from your dashboard into Claude Code, Codex or Cursor.
Say the phrase below — the agent shows the price, runs Wan 3.0 Video Prime and saves the result.

Tell your agent

Make an 8-second 9:16 720p clip with Wan 3.0 Video Prime: a florist wraps a bouquet as petals scatter across the counter, soft acoustic guitar playing.

This request ≈ · 720p · 8 s

Wan 3.0 Video Prime FAQ

How much does Wan 3.0 Video Prime cost?

8-second clip from · per second. Prices are live from our price list, and you see the exact price before anything runs.

How is Wan 3.0 Video Prime different from Wan 3.0 Video?

Speed is the main difference. Prime keeps the core abilities of the standard model, including references across text, images, video, and audio, longer story clips, and sound generated with the picture, but it completes each job end to end significantly faster. Choose it when turnaround matters, such as in apps or large batches.

Which inputs can be combined in one Wan 3.0 Video Prime request?

A prompt can be paired either with frames (a first frame, or first and last frames) or with references (images, video clips, and audio), but frames and references cannot be mixed. A document cannot be used together with a webpage link or with frames, and the length of any reference video counts toward the maximum combined duration.

How do I use Wan 3.0 Video Prime from my AI agent?

Create a Video Blade account, paste the agent link from your dashboard into Claude Code, Codex or Cursor, and ask: “Make an 8-second 9:16 720p clip with Wan 3.0 Video Prime: a florist wraps a bouquet as petals scatter across the counter, soft acoustic guitar playing.” The agent runs Wan 3.0 Video Prime (model id wan-3-0-video-prime), shows the price before it starts and saves the result to your dashboard.

How is Wan 3.0 Video Prime billed?

By the second of video: the rate depends on the option you pick (mode, resolution, sound), and a clip costs the rate times its length. Tokens are held when a run starts and settled to what was actually used; a failed run costs nothing. Current prices are shown on this page.

What settings does Wan 3.0 Video Prime support?

Resolution: 480p, 720p or 1080p. Aspect ratio: adaptive, 16:9, 4:3, 1:1, 3:4 or 9:16.

Wan 3.0 Video Prime in the Video Blade API

wan-3-0-video-prime

Your agent sends this model id with the order; the result lands in the project, and every request is in your generation log with its price.

Through Video Blade a clip is ordered from a prompt with an optional start frame (and an end frame where the model takes one), in the lengths and resolutions the model offers.

POST /api/v1/projects/{id}/video-sessions/{item_id}/generate
{"prompt": "…", "model": "wan-3-0-video-prime", "duration": …, "start_url": "https://…"}

Parameters and API reference →Getting started →

Similar models

ByteDance

Wan 3.0 Video Prime API

What Wan 3.0 Video Prime is good for

Wan 3.0 Video Prime pricing

Use Wan 3.0 Video Prime from your AI agent

Wan 3.0 Video Prime FAQ

Wan 3.0 Video Prime in the Video Blade API

Similar models

Seedance 2.5

Wan 3.0 Video

Seedance 2.0

Veo 3.1