wan2.7-i2v API

Use the exact model ID wan2.7-i2v. The model field must match this page exactly.

Sample outputwan2.7-i2vPOST /v1/videos5.0s

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

Prompt: One continuous take, no cuts. The ribbon of film keeps unwinding and speeds up until every frame is lit, tightening into a neon helix that lifts off the deck and climbs past the parapet into the dusk sky, the woman in the cobalt coat turning to follow it up. The camera starts low behind her, is pushed back as the helix rises, then cranes up over the parapet and looks along the coil toward the city. One hard magenta key stays raking across the deck. Real weight and inertia, paper and emulsion catching the light, no text.

Request that produced this sample, with the input media URL replaced

{
  "model": "wan2.7-i2v",
  "prompt": "One continuous take, no cuts. The ribbon of film keeps unwinding and speeds up until every frame is lit, tightening into a neon helix that lifts off the deck and climbs past the parapet into the dusk sky, the woman in the cobalt coat turning to follow it up. The camera starts low behind her, is pushed back as the helix rises, then cranes up over the parapet and looks along the coil toward the city. One hard magenta key stays raking across the deck. Real weight and inertia, paper and emulsion catching the light, no text.",
  "seconds": "5",
  "duration": 5,
  "resolution": "1080p",
  "ratio": "16:9",
  "aspect_ratio": "16:9",
  "image": "https://example.com/input-image.png"
}

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-i2v",
    "input": {"prompt": "The camera moves closer as the lanterns begin to glow in time with the music.", "media": [{"type": "first_frame", "url": "https://example.com/first-frame.png"}]},
    "parameters": {"resolution": "1080P", "duration": 5, "prompt_extend": false, "watermark": 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 I2V uses input.prompt and input.media. Follow the documented combinations for first/last frames, driving audio, and an initial clip.

Field	Required	Notes
model	Yes	wan2.7-i2v
input.prompt	Yes	Motion and scene description
input.media[]	Yes	first_frame, last_frame, driving_audio, or first_clip
parameters.resolution	No	720P / 1080P (default 1080P)
parameters.duration	No	Total duration; includes the input clip for continuation
parameters.prompt_extend	No	Set false when this dedicated model contract requires it
parameters.watermark	No	Whether to add a watermark

Input and output limits

I2V media must follow a supported combination such as first_frame, first_frame + last_frame, first_frame + driving_audio, or first_clip with the documented optional end frame. Each media type appears at most once; output is 720P or 1080P.

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-i2v",
    "input": {"prompt": "镜头从第一帧推进到最后一帧", "media": [
      {"type": "first_frame", "url": "https://example.com/first.png"},
      {"type": "last_frame", "url": "https://example.com/last.png"}
    ]},
    "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-i2v	The model documented on this page.