Generation speed
High-speed tier
Significantly faster end-to-end than the standard model
High-speed tier · Wan 3.0 Prime
Wan 3.0 Prime: full Wan 3.0 capability, delivered at high speed
The speed-optimized tier of Alibaba Cloud's Wan 3.0 video family — same generation quality, significantly faster end-to-end turnaround.
Wan 3.0 Prime keeps the complete Wan 3.0 feature surface — text-to-video, first/last-frame image-to-video and multimodal reference-to-video, up to 30 seconds at 480P/720P/1080P and 30fps — while cutting waiting time on every task. On APIPod, the prime routes share the standard contract: switching tiers is a one-word change to the model field.
Max duration
30s per clip
2–30s per generation, or -1 for smart duration
Resolution & frame rate
1080P · 30fps
480P / 720P / 1080P output tiers
Public model IDs
3 modes
wan3.0-prime-t2v / i2v / r2v
Generated with Wan 3.0 — Prime shares the same generation quality at higher speed
Prime vs Standard — when to choose which
Same Wan 3.0 model family, same request contract. The only real difference is how fast your video comes back.
Choose Prime when…
- Turnaround drives the experience — interactive products, chat-style generation and in-app previews
- You iterate on prompts and references — faster tasks mean more experiments per hour at the same quality
- You run bulk or pipeline workloads — shorter end-to-end time raises daily throughput per queue slot
- Latency SLAs matter — ad creatives, social content and marketing clips on a deadline
Stay on Standard when…
- Existing wan3.0-t2v / i2v / r2v integrations already meet your timing — nothing to migrate
- You batch overnight or render offline, where queue time is cheaper than speed
- Your cost model is tuned to standard-tier pricing and speed is not the constraint
Spec comparison at a glance
Prime extends the Wan 3.0 contract instead of changing it — the model field is the only change your integration needs.
| Spec | Wan 3.0 Prime | Wan 3.0 Standard |
|---|---|---|
| End-to-end speed | Significantly faster | Standard |
| Task modes | T2V / I2V / R2V | T2V / I2V / R2V |
| Duration per clip | 2–30s, or -1 smart duration | 2–30s, or -1 smart duration |
| Resolution & frame rate | 480P / 720P / 1080P · 30fps | 480P / 720P / 1080P · 30fps |
| Reference inputs (r2v) | 10 images / 5 videos / 5 audios / 1 file / 1 link | 10 images / 5 videos / 5 audios / 1 file / 1 link |
| Generated audio | Yes — on by default | Yes — on by default |
| Aspect ratios | adaptive, 16:9, 4:3, 1:1, 3:4, 9:16 | adaptive, 16:9, 4:3, 1:1, 3:4, 9:16 |
Both tiers share the same asynchronous task lifecycle, parameter schema and media limits on APIPod. Rate limit: 300 RPM per account on the upstream side.
Official list price
Official pricing reference
Wan 3.0 Prime bills per second of generated video on the official side, scaling with output resolution. Your actual rates on APIPod are shown on the pricing page.
| Resolution | Official list price |
|---|---|
| 480P | ¥0.45 / second |
| 720P | ¥0.90 / second |
| 1080P | ¥1.80 / second |
Official example — a 5-second clip at list price: 480P ≈ ¥2.25, 720P ≈ ¥4.50, 1080P ≈ ¥9.00.
List prices from the official Wan 3.0 Prime model page. APIPod applies its own billing — check the pricing page for live rates before shipping.
Three modes, one high-speed surface
Pick the public model ID that matches the assets in your pipeline. Every mode runs on the prime tier end to end.
wan3.0-prime-t2v
Text to video
Start with a prompt and direct the subject, camera, motion, lighting, and scene rhythm in natural language.
Prompt in · Video out
wan3.0-prime-i2v
Image to video
Animate a first frame, or define a transition with first-and-last-frame control for a more deliberate shot.
First frame · Optional last frame
wan3.0-prime-r2v
Reference to video
Combine up to 10 images, 5 videos, 5 audio files, one document, or one public webpage to carry characters, objects, style, sound, and a complete brief into a new scene.
Images · Video · Audio · File/Link
Recommended workflow: iterate at prime speed
1) Draft at 480P
Validate composition, timing and reference roles cheaply — prime speed makes 480P drafts close to interactive.
2) Lock the anchors
Move to i2v with a first/last frame, or r2v with your reference pack, once the prompt reads right.
3) Finalize at 720P / 1080P
Rerun the winning prompt at full resolution with the same inputs; smart duration (-1) lets the model pick the cut length.
4) One API, both tiers
Switch between prime and standard by changing the model field — auth, billing and task polling carry over.
Example request
Wan 3.0 Prime quick start
Public model IDs on one endpoint: wan3.0-prime-t2v for text-to-video, wan3.0-prime-i2v for first/last-frame animation and wan3.0-prime-r2v for multimodal references.
Tasks are asynchronous; poll the returned task ID until completed. Duration defaults to 5 seconds, resolution to 1080P, and generated audio is on by default.
curl -X POST https://api.apipod.ai/v1/videos/generations \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d {
"model": "wan3.0-prime-t2v",
"prompt": "A cyclist cuts through a rain-lit city at blue hour, handheld camera, reflections on asphalt.",
"duration": 5,
"resolution": "720P",
"aspect_ratio": "16:9",
"generate_audio": true
}Wan 3.0 Prime FAQ
What is Wan 3.0 Prime?
Wan 3.0 Prime is the high-speed tier of Alibaba Cloud's Wan 3.0 video generation model. It keeps the full standard capability set — text-to-video, first/last-frame image-to-video, and reference-to-video — while delivering significantly faster end-to-end generation.
What is the difference between Wan 3.0 Prime and Wan 3.0 Standard?
Capabilities, parameters and output specs are aligned: both support 480P/720P/1080P at 30fps, 2–30 second durations (or -1 for smart duration), generated audio, and the same reference-media limits. The difference is speed — Prime returns completed videos significantly faster, at a different price per second.
Which public model ID should I use?
Use wan3.0-prime-t2v for text-only prompts, wan3.0-prime-i2v when you have a first frame or first-and-last frames, and wan3.0-prime-r2v when you want to guide the render with reference images, videos, audio, a document file, or a public webpage.
What duration and resolution are supported?
Duration supports 2–30 seconds, or -1 for intelligent duration selection. Resolution can be 480P, 720P, or 1080P at 30fps, with 1080P as the default. Aspect ratio supports adaptive, 16:9, 4:3, 1:1, 3:4, and 9:16.
How is Wan 3.0 Prime billed?
The official list price bills per second of output: ¥0.45/s at 480P, ¥0.90/s at 720P and ¥1.80/s at 1080P. APIPod applies its own rates — see the pricing page for the live configuration.
How do I call Wan 3.0 Prime through the API?
POST to /v1/videos/generations with model set to wan3.0-prime-t2v, wan3.0-prime-i2v or wan3.0-prime-r2v. The task is asynchronous — poll the returned task ID until status is completed. The request schema is identical to the standard tier.
Ship Wan 3.0 videos at prime speed
Full Wan 3.0 capability, significantly faster end-to-end generation, one unified API — your first high-speed clip is one request away.