Video models
Wan 3.0 Video Prime
On this page
Wan 3.0 Video Prime — high-quality AI video generation.
| modelId | wan-3-0-video-prime |
| Modality | video |
| Pricing | See this model on the Pricing page for the current per-call price (with your markup). |
Operations
| Operation | modelId | Endpoint | Required input |
|---|---|---|---|
| Default | wan-3-0-video-prime | POST /api/v1/generate | first_frame_url, prompt, aspect_ratio |
| Poll task | — | GET /api/v1/task/{id}?model=wan-3-0-video-prime | — |
Input parameters
| Field | Type | Required | Values / example |
|---|---|---|---|
| first_frame_url | string | Yes | Image URL |
| last_frame_url | string | No | Image URL |
| prompt | string | Yes | Text prompt used to describe the desired video content. Supports both Chinese and English, with a maximum length of 20,000 characters. Max 20000 characters. (example: Create a 24-second cinematic international hip-hop music video with photorealistic visuals, premium street-fashion aesthetics, confident energy, and fast… — full value in the request example) |
| reference_image_urls | string[] | No | Maximum 10 images. Mapped in array order to Image1, Image2, ... in the prompt. Specifications are the same as first_frame_url. Cannot be used together with first frame / last frame. (image URL) |
| reference_video_urls | string[] | No | Maximum 5 clips. Each clip: 1–15s; total combined duration ≤ 15s. Mapped in array order to Video1, Video2, ... in the prompt. Formats: mp4, mov. Single side: [240, 4096] px; aspect ratio ≤ 8:1; file size per clip ≤ 100MB. Additionally, on the output side: total input video duration + output duration (duration parameter) must not exceed 30 seconds. (image URL) |
| reference_audio_urls | string[] | No | Maximum 5 clips. Each clip: 1–15s; total combined duration ≤ 15s. Mapped in array order to Audio1, Audio2, ... in the prompt. Formats: wav, mp3; file size ≤ 15MB per clip. When not used as the sole media input, it is still recommended to pair with images or videos. (image URL) |
| reference_link_urls | string | No | Maximum 1 publicly accessible webpage (no login required). Cannot be used together with reference_file_urls, nor with first frame / last frame. |
| reference_file_urls | string | No | Maximum 1 file. Cannot be used together with reference_link_urls, nor with first frame / last frame. Supported formats: docx, doc, xlsx, xls, pptx, ppt, pdf, txt, key, pages, numbers, md. File size ≤ 100MB. For file types such as pdf, docx, ppt, key, pages, etc., page count ≤ 50 pages. |
| resolution | string | No | Preset resolution levels for video generation. (options: 480P | 720P | 1080P) (default: 1080P) |
| aspect_ratio | string | Yes | Aspect ratio for generated video. "Adaptive" auto-recommends a ratio based on input media proportions and intent. (options: adaptive | 16:9 | 4:3 | 1:1 | 3:4 | 9:16) (default: 16:9) |
| duration | number | No | Duration of the generated video, in seconds (2-30). With a reference video attached, the input video duration plus this duration must not exceed 30 seconds. (range 2-30) (default: 5) |
| audio | boolean | No | Whether the output video includes audio. true (default): Includes audio; false: No audio track. (true/false) (default: true) |
Example request
bash
curl -X POST https://you.bot/api/v1/generate \
-H "Authorization: Bearer $YOUBOT_API_KEY" \
-H "Content-Type: application/json" \
-d '{"modelId":"wan-3-0-video-prime","input":{"prompt":"Create a 24-second cinematic international hip-hop music video with photorealistic visuals, premium street-fashion aesthetics, confident energy, and fast pacing.\n\nReferences:\nImage 1 defines the fixed four-person group: female lead singer front-center, male DJ rear-center, two hype performers left/right. Image 2 defines the singer’s face, hair, makeup, silver-black techwear outfit, and microphone. Image 3 defines the rooftop stage. Keep all characters, outfits, identities, and location consistent throughout.\n\nMusic:\nOriginal international hip-hop anthem, ~106 BPM. Start with a strong groove immediately: punchy kick, crisp snare, syncopated bass, catchy synth/brass hook. Eight languages flow naturally as one rap performance. Beat drop at 21s.\n\nShots:\n0–3s: Aerial city → descend to rooftop → low-angle push-in. “One beat.”\n3–6s: Front close-up. “同一个节拍。”\n6–9s: DJ controls → tilt up to singer. “ひとつのリズム。”\n9–12s: 3/4 singer shot, smooth lateral move. “하나의 리듬.”\n12–15s: Low-angle tracking as singer walks forward. “Um só ritmo.”\n15–18s: Singer + right performer turn toward camera. “จังหวะเดียวกัน.”\n18–21s: Strong frontal push-in. “Un mismo ritmo.”\n21–24s: Side-lit close-up. “إيقاع واحد.” Beat drops, pull back to heroic group wide shot. Singer: “Different voices, one beat.” Group: “One beat.”\n\nPrecise multilingual lip-sync with the same singer and voice throughout. Keep singer front-center, DJ behind, performers left/right. Use smooth pushes, pullbacks, lateral moves, hard cuts, and natural wipes. Deep blue, silver, warm gold, subtle magenta neon; cinematic 24/35/50mm lenses, shallow DOF, film grain, realistic skin.\n\nNo subtitles, text, logos, UI, or watermark. No character duplication, identity changes, distorted hands, floating objects, or unstable equipment.","resolution":"720P","aspect_ratio":"16:9","duration":5,"audio":true}}'