wan2.7-t2v API

Use the exact model ID wan2.7-t2v. The model field must match this page exactly.

Sample outputwan2.7-t2vPOST /v1/videos5.0s

Parameters: duration=5resolution=1080pratio=16:9

Prompt: One continuous take, no cuts. A glasshouse at night, rows of plants and misted panes. A figure in an emerald latex suit presses one palm flat against the glass; every drop of condensation on that wall begins running upward instead of down, gathering as it goes until the whole pane is a moving constellation of green and gold points that spreads to the roof panels overhead. The camera starts on the hand, pulls back through the planting and cranes up to take in the whole roof. One hard warm key from a work lamp on the floor, cold moonlight outside. Real weight and inertia, water surface tension on glass, no text.

Request that produced this sample

{
  "model": "wan2.7-t2v",
  "prompt": "One continuous take, no cuts. A glasshouse at night, rows of plants and misted panes. A figure in an emerald latex suit presses one palm flat against the glass; every drop of condensation on that wall begins running upward instead of down, gathering as it goes until the whole pane is a moving constellation of green and gold points that spreads to the roof panels overhead. The camera starts on the hand, pulls back through the planting and cranes up to take in the whole roof. One hard warm key from a work lamp on the floor, cold moonlight outside. Real weight and inertia, water surface tension on glass, no text.",
  "seconds": "5",
  "duration": 5,
  "resolution": "1080p",
  "ratio": "16:9",
  "aspect_ratio": "16:9"
}

Authentication and endpoint

Use a Modelflare API key with https://modelflare.dev/v1. The gateway entry point is POST /v1/videos.

HTTP

Authorization: Bearer YOUR_MODELFLARE_API_KEY

Create a task

bash

curl https://modelflare.dev/v1/videos \
  -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan2.7-t2v",
    "input": {"prompt": "A white cat runs through a neon-lit street in the rain, cinematic tracking shot"},
    "parameters": {"resolution": "1080P", "duration": 5, "prompt_extend": false}
  }'

Poll and download

Save the task ID. Poll GET /v1/videos/{task_id} and download with GET /v1/videos/{task_id}/content. Result URLs may expire, so transfer the file promptly.

bash

curl https://modelflare.dev/v1/videos/TASK_ID \
  -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY"

Request notes

Wan commonly uses input and parameters; frame-guided and reference-media modes must not be mixed.

Request parameters

Wan2.7 T2V centers on input.prompt and optionally accepts input.audio_url. Describe shot changes in the prompt; do not send shot_type.

Field	Required	Notes
model	Yes	wan2.7-t2v
input.prompt	Yes	Use the limit documented on the official page
input.negative_prompt	No	Negative prompt
input.audio_url	No	Public WAV/MP3; omit to let the model generate audio
parameters.resolution	No	720P / 1080P (default 1080P)
parameters.ratio	No	16:9 / 9:16 / 1:1 / 4:3 / 3:4
parameters.duration	No	Video duration in seconds
parameters.prompt_extend	No	Set false when this dedicated model contract requires it
parameters.watermark	No	Whether to add a watermark
parameters.seed	No	Optional random seed

Input and output limits

T2V outputs 720P or 1080P for 2–15 seconds. Omit input.audio_url to generate synchronized audio; a supplied WAV/MP3 is trimmed or leaves silence to match the requested duration. Describe multi-shot timing in the prompt and do not send shot_type.

Documented workflow examples

bash

curl https://modelflare.dev/v1/videos \
  -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan2.7-t2v",
    "input": {"prompt": "从文字生成一段稳定的电影镜头"},
    "parameters": {"resolution": "1080P", "duration": 8, "prompt_extend": false}
  }'

Errors and failed tasks

Invalid model parameters return a 4xx with a request ID. An asynchronous task can also enter failed after creation succeeds; use error_code and error_message from the poll response as the final task reason. Do not retry the same request with a different JSON shape.

Supported scope

This page covers Modelflare model generation and editing calls. Search or map enrichment, voice management, and element-library management are resource APIs outside this public model-call surface and are not required request fields.

Pricing and billing

This model uses per-second video billing. See the model pricing page for the current customer price, reference list price, and complete specification.

Note

This page documents Modelflare’s public interface; the fields and limits shown here are the current contract.

Variants

Model ID	Difference
wan2.7-t2v	The model documented on this page.