Video model by Alibaba
Wan 2.7 Spicy API
model: wan-2.7-i2v-spicy
Call Wan 2.7 Spicy with your KeelRouter API key, the same key you use for every other model. From $0.13 per second, paid per call from a prepaid balance. Failed calls are free.
Pricing
| Option | Price |
|---|---|
| 720p | $0.13 per second |
| 1080p | $0.19 per second |
Call it
Async: POST /v1/video/generations returns a taskId; poll the same path with ?task_id= or pass a callback_url.
curl https://api.keelrouter.com/v1/video/generations \
-H "Authorization: Bearer $KEELROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "wan-2.7-i2v-spicy",
"prompt": "A paper boat drifting down a rainy street, slow camera follow",
"resolution": "720p"
}'Parameters
| Name | Type | Notes |
|---|---|---|
| model | string | Required. wan-2.7-i2v-spicy |
| image | string | Required. |
| prompt | string | Required. |
| negative_prompt | string | |
| audio_url | string | |
| audio | boolean | Default true. |
| duration | number | Range 2–15. Default 5. |
| resolution | string | One of 720p, 1080p. Default 1080p. |
| seed | number | Range 0–2147483647. |
| prompt_extend | boolean | Default true. |
| callback_url | string | Optional https URL; we POST the result when the task ends |
FAQ
- How much does the Wan 2.7 Spicy API cost on KeelRouter?
- From $0.13 per second. You pay per call from a prepaid USD balance; failed calls are not charged.
- How do I call Wan 2.7 Spicy?
- POST to /v1/video/generations with model "wan-2.7-i2v-spicy". You get a taskId back; poll the same endpoint with ?task_id= or pass a callback_url.
- Is this the official Wan 2.7 Spicy API?
- No. KeelRouter is an independent API gateway. Requests run on Wan 2.7 Spicy through our upstream providers, and the video model keeps its own safety filters.
- How long are results kept?
- Result files are kept for 30 days, then deleted. Download what you want to keep.
More from Alibaba
KeelRouter is an independent service and is not affiliated with Alibaba. Wan 2.7 Spicy is a trademark of its owner, used here only to name the model a request runs on.