Generates video from text, an image, references · 480p to 1080p · 2–30 s · native audio
curl -X POST https://api.open.sume.com/v1/video-router/generate \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"wan-3.0","prompt":"A cinematic tracking shot along a sunlit coastal road","duration":5,"resolution":"480p","aspect_ratio":"16:9","generate_audio":false}'Dollars per unit at each option: the serving route's cost × 1.25, rounded up to $0.0001. The estimate above is the exact charge.
| Option | Price |
|---|---|
| 480p | $0.0625 / s |
| 720p | $0.1250 / s |
| 1080p | $0.2500 / s |
Price, resolution and duration show each model's full range.
| Model | Type | Price | Resolution | Duration |
|---|---|---|---|---|
| Wan 2.2 Speech to Video | lipsync | $0.1250 – $0.2500 / s | 480p – 720p | 3 – 7 s |
| Qwen Image | image | $0.0250 / image | — | — |
| Qwen Image Max | image | $0.0938 / image | — | — |
| Qwen Image Layered | image | $0.0625 / image | — | — |