alibaba/wan-2-6-i2v-flash
Wan 2.6 image-to-video flash — faster and cheaper first-frame generation. prompt (<=1500 chars); first_frame_url (req; public https image); audio_url (public https WAV/MP3, 3-30 s); audio (def true: the clip has sound; false renders a silent clip at a lower price); shot_type single (def) | multi; resolution 720p|1080p (def 1080p; no 480p); duration whole seconds 2-15 (def 5); negative_prompt (<=500 chars); seed; prompt_extend (def true); watermark (def false).
The rate depends on whether the clip has sound, as the vendor reports it.
Served via the relay: POST /v1/alibaba/generations, poll GET /v1/alibaba/generations/{task_id}. Per-second pricing (by resolution) billed by the relay from the vendor's reported usage.
Unknown parameters are rejected.
| Slug | alibaba/wan-2-6-i2v-flash |
| Kind | video |
| Vendor | alibaba |
| Endpoint | POST /v1/alibaba/generations |
Charged per job from what the generator reports it rendered — your Logs show the exact figure for each one; see balance and billing.
Calling it
curl https://api.sociaro.com/v1/alibaba/generations \
-H "Authorization: Bearer $SOCIARO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "alibaba/wan-2-6-i2v-flash",
"prompt": "a paper boat on a rain-soaked street",
"resolution": "720p",
"duration": 5
}'
# then poll the job id it returns:
curl https://api.sociaro.com/v1/alibaba/generations/JOB_ID \
-H "Authorization: Bearer $SOCIARO_API_KEY"Parameters
Types, ranges, defaults and what each field does — the list below is the names only.
promptfirst_frame_urlaudio_urlresolutiondurationnegative_promptseedprompt_extendwatermarkshot_typeaudio
Anything not listed here is refused rather than ignored, so a typo fails loudly instead of quietly producing something else.