Wan2.7 Text-to-Video

POST /api/v1/services/aigc/video-generation/video-synthesis — Wan2.7 text-to-video

The Wan 2.7 text-to-video model generates a fluid video from a text prompt, with multi-shot storytelling driven straight from the prompt (describe your shots with timestamps).

Models

Model	Notes
`wan2.7-t2v`	Wan 2.7 text-to-video

Create a job

POST/api/v1/services/aigc/video-generation/video-synthesis

curl https://api.modelsite.ai/api/v1/services/aigc/video-generation/video-synthesis \
  -H "Authorization: Bearer $MODELSITE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan2.7-t2v",
    "input": {
      "prompt": "A rainy New York street at night, neon reflections, a detective in a black trench coat walking briskly, cinematic"
    },
    "parameters": {
      "resolution": "720P",
      "ratio": "16:9",
      "duration": 5
    }
  }'

Request body

Field	Type	Notes
`model`	string (required)	`wan2.7-t2v`
`input.prompt`	string (required)	≤5000 characters. Multi-shot storytelling is plain prompt text (e.g. "Shot 1 [0-3s] wide: …")
`input.negative_prompt`	string (optional)	≤500 characters. Lives in `input` in the Wan dialect — not in `parameters`
`input.audio_url`	string (optional)	Audio file URL (wav/mp3, 2–30 s, ≤15MB); the model uses it as the soundtrack and trims to `duration` when longer
`parameters`	object (optional)	Below

parameters

Parameter	Type	Notes
`resolution`	string	`720P` / `1080P` (default). Sellable tiers follow the price configuration
`ratio`	string	`16:9` (default) / `9:16` / `1:1` / `4:3` / `3:4`
`duration`	integer	`[2, 15]`, default 5
`prompt_extend`	boolean	Prompt rewriting, default `true`
`watermark`	boolean	"AI-generated" stamp, default `false`
`seed`	integer	`[0, 2147483647]`

Wan2.7 dropped the older size and shot_type fields — output geometry is expressed by resolution + ratio, and shot types are described in the prompt.

Polling and result

GET/api/v1/tasks/{task_id}

curl "https://api.modelsite.ai/api/v1/tasks/$TASK_ID" \
  -H "Authorization: Bearer $MODELSITE_API_KEY"

Response fields

Field	Meaning
`output.task_id`	Job ID (same value returned at creation)
`output.task_status`	`PENDING` queued / `RUNNING` processing / `SUCCEEDED` done / `FAILED` failed
`output.video_url`	The generated video URL — only on `SUCCEEDED`; download promptly
`output.code` / `output.message`	Present only on failure, with the reason
`usage`	Usage stats (duration, resolution tier, …); counted only on success
`request_id`	Unique request ID — include it when reporting issues

Status flow: PENDING → RUNNING → SUCCEEDED / FAILED.

Billing

Billed by actual generated seconds; the resolution tier affects the rate; failed jobs are not billed. Rates on the Models page.

Error handling

Creation-time errors return {"code": "...", "message": "..."}; mid-job failures surface through the poll's output.code / output.message. General error codes: Errors.