seedance-2.5 API

Use the exact model ID seedance-2.5. The model field must match this page exactly.

Sample outputseedance-2.5POST /v1/videos5.1s

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

Prompt: A small research submersible descends through the deep ocean, its headlights sweeping over a drifting field of bioluminescent jellyfish and a sunken stone archway. Camera follows from behind, particles float in the beams, blue-black water, calm and mysterious, photoreal, no text.

Request that produced this sample

{
  "model": "seedance-2.5",
  "prompt": "A small research submersible descends through the deep ocean, its headlights sweeping over a drifting field of bioluminescent jellyfish and a sunken stone archway. Camera follows from behind, particles float in the beams, blue-black water, calm and mysterious, photoreal, 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": "seedance-2.5",
    "content": [{"type": "text", "text": "A white cat runs through a neon-lit street in the rain, cinematic tracking shot"}],
    "resolution": "720p",
    "duration": 5,
    "generate_audio": 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

Seedance uses content[] for text, frames, and reference media; the separate Seedance asset management contract is documented independently.

Note

Upload virtual-person images to the Seedance asset library first, wait until the status is Active, then reference asset://<ID> in content[]. Modelflare does not provide real-person verification.

Request parameters

Seedance uses one asynchronous multimodal envelope. Put text and media in content[]; media roles select first/last-frame or reference workflows.

Field	Required	Notes
model	Yes	seedance-2.5
content[]	Yes	text, image_url, video_url, and audio_url; use role to identify media purpose
resolution	No	480p / 720p / 1080p
ratio	No	21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16 / adaptive
duration	No	-1 for automatic timing, or 4–30 seconds
generate_audio	No	Generate synchronized dialogue, effects, and background audio
tools	No	Use web_search only where the official model page supports it
watermark	No	Whether to add a watermark
omni_reference_task_type	No	auto / reference / edit / extend; editing and extension impose stricter ratio/duration rules
output_format	No	mp4 / mov
return_last_frame	No	Return the final frame as an image

Input and output limits

This model supports 480p, 720p, and 1080p. Use -1 for automatic timing or choose 4–30 seconds. A request can combine up to 30 images, 10 videos, and 10 audio clips. Ordinary reference generation accepts an explicit ratio or adaptive; editing, extension, and first/last-frame workflows require ratio: "adaptive", and editing requires duration: -1. Virtual-person images must be uploaded to the asset library first; Modelflare does not provide real-person verification.

Documented workflow examples

Seedance 2.5 classifies reference, editing, extension, and frame-guided workflows from the media roles and task type. The examples keep the official contract while using Modelflare’s endpoint and model ID.

Multimodal reference

bash

curl https://modelflare.dev/v1/videos \
  -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2.5",
    "omni_reference_task_type": "reference",
    "content": [
      {"type":"text","text":"@image1 performs the movement from @video1, paced to @audio1"},
      {"type":"image_url","image_url":{"url":"https://example.com/character.jpg"},"role":"reference_image"},
      {"type":"video_url","video_url":{"url":"https://example.com/motion.mp4"},"role":"reference_video"},
      {"type":"audio_url","audio_url":{"url":"https://example.com/music.mp3"},"role":"reference_audio"}
    ],
    "ratio": "16:9", "duration": 15, "output_format": "mp4"
  }'

Video editing

bash

curl https://modelflare.dev/v1/videos \
  -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2.5", "omni_reference_task_type": "edit",
    "content": [
      {"type":"text","text":"Remove the background pedestrians but preserve the main subject"},
      {"type":"video_url","video_url":{"url":"https://example.com/source.mov"},"role":"reference_video"}
    ],
    "ratio": "adaptive", "duration": -1, "output_format": "mov"
  }'

Video extension

bash

curl https://modelflare.dev/v1/videos \
  -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2.5", "omni_reference_task_type": "extend",
    "content": [{"type":"video_url","video_url":{"url":"https://example.com/source.mp4"},"role":"reference_video"}],
    "ratio": "adaptive", "duration": 11, "output_format": "mov"
  }'

First and last frames

bash

curl https://modelflare.dev/v1/videos \
  -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2.5", "content": [
      {"type":"text","text":"The subject smiles while the camera makes a smooth orbit"},
      {"type":"image_url","image_url":{"url":"https://example.com/first.jpg"},"role":"first_frame"},
      {"type":"image_url","image_url":{"url":"https://example.com/last.jpg"},"role":"last_frame"}
    ],
    "ratio": "adaptive", "duration": -1, "return_last_frame": true
  }'

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 token-based 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
seedance-2.5	The model documented on this page.