Seedance 1.0 Pro API

bytedance/seedance-v1-pro

Seedance 1.0 generates 1080P videos with smooth motion, rich detail, and diverse styles, while the pro version adds multi-shot narrative and advanced instruction following for cinematic results.

A4000,RTX4000

Priced by resolution

OpenAPI

Input

Prompt

Text prompt for video generation

Image

Input image for image-to-video generation

Duration

Min: 3 - Max: 12

Video duration in seconds

resolution

Video resolution

aspect_ratio

Video aspect ratio. Ignored if an image is used.

Camera Fixed

Whether to fix camera position

Seed

Random seed. Set for reproducible generation

You need to be logged in to run this model and view results.

Output

{
  "error": "",
  "inferenceTime": 10000,
  "output": "https://media.modelrunner.ai/8oitUYR5Nhvhhxl6QNgk1.mp4",
  "input": {
    "seed": 0,
    "prompt": "A lone traveler in flowing robes walks slowly across an endless desert under a scorching sun. The camera begins with a long aerial shot, emphasizing the vast golden dunes and the traveler’s small figure. Cut to a low-angle shot: heatwaves shimmer around him, and ghostly mirages of oases flicker on the horizon. Camera zooms close on his face as sand blows across, his eyes squinting with determination. The mirages fade, replaced by the real sight of a caravan of camels silhouetted against the sunset. Camera pulls back to capture the breathtaking scale of the desert journey.",
    "duration": 10,
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "camera_fixed": false
  },
  "logs": "seedance status=succeeded"
}

Generated in 10 seconds

Logs (1 lines)

Examples

Pricing

Model pricing varies by the target resolution of your output video.

480p

$0.03

per second of output video

or around 33 seconds for $1

720p

$0.06

per second of output video

or around 17 seconds for $1

1080p

$0.15

per second of output video

or around 7 seconds for $1

Seedance 1.0 Pro API

Seedance 1.0 Pro is a image-to-video AI model by bytedance. On ModelRunner it runs through a REST API or via MCP from any AI assistant, at $0.15 per second of video.

POST https://queue.modelrunner.run/bytedance/seedance-v1-pro

cURL

# Submit a request to the queue. Input fields go at the top level of the
# body. The optional reserved "metadata" object holds your own flat string
# tags — stored on the request, never sent to the model; filter later with
# GET https://queue.modelrunner.run/requests?metadata=<url-encoded JSON>.
curl -X POST https://queue.modelrunner.run/bytedance/seedance-v1-pro \
  -H "Authorization: Key $MRUN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "seed": 0,
    "prompt": "A lone traveler in flowing robes walks slowly across an endless desert under a scorching sun. The camera begins with …",
    "duration": 10,
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "camera_fixed": false,
    "metadata": {
      "project": "my-project"
    }
  }'
# → { "request_id": "...", "status_url": "...", "response_url": "..." }

# Poll status_url until "COMPLETED", then fetch the result
curl "https://queue.modelrunner.run/bytedance/seedance-v1-pro/requests/$REQUEST_ID/status" \
  -H "Authorization: Key $MRUN_API_KEY"
curl "https://queue.modelrunner.run/bytedance/seedance-v1-pro/requests/$REQUEST_ID" \
  -H "Authorization: Key $MRUN_API_KEY"

JavaScript

import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("bytedance/seedance-v1-pro", {
  input: {
    "seed": 0,
    "prompt": "A lone traveler in flowing robes walks slowly across an endless desert under a scorching sun. The camera begins with …",
    "duration": 10,
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "camera_fixed": false
  },
});
console.log(result);

Python

import os
import requests

headers = {"Authorization": f"Key {os.environ['MRUN_API_KEY']}"}

submitted = requests.post(
    "https://queue.modelrunner.run/bytedance/seedance-v1-pro",
    headers=headers,
    json={
      "seed": 0,
      "prompt": "A lone traveler in flowing robes walks slowly across an endless desert under a scorching sun. The camera begins with …",
      "duration": 10,
      "resolution": "720p",
      "aspect_ratio": "16:9",
      "camera_fixed": false
    },
).json()

# Poll submitted["status_url"] until "COMPLETED", then:
result = requests.get(submitted["response_url"], headers=headers).json()

Input parameters

Name	Type	Required	Description
prompt	string	yes	Text prompt for video generation
image	string (uri)	no	Input image for image-to-video generation
duration	integer	no	Video duration in seconds Default: 5.
resolution	enum	no	Video resolution Default: "1080p".
aspect_ratio	enum	no	Video aspect ratio. Ignored if an image is used. Default: "16:9".
camera_fixed	boolean	no	Whether to fix camera position Default: false.
seed	integer	no	Random seed. Set for reproducible generation

Machine-readable: OpenAPI schema · llms.txt

Use Seedance 1.0 Pro from Claude & Cursor (MCP)

Point Claude Code, Claude Desktop, Cursor, or any MCP client at the ModelRunner MCP server and Seedance 1.0 Pro becomes a tool your assistant can call directly — it authorizes via OAuth (no API key in config) and runs this model with the run_model tool using the endpoint bytedance/seedance-v1-pro.

MCP client config (Claude Desktop, Cursor)

{
  "mcpServers": {
    "modelrunner": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.modelrunner.run/mcp"]
    }
  }
}

Claude Code

claude mcp add --transport http modelrunner https://mcp.modelrunner.run/mcp

Then ask your assistant, for example: “Run bytedance/seedance-v1-pro on ModelRunner to generate video”. MCP setup guide.

Model Details

**Seedance 1.0** is a series of video generation models developed by the ByteDance **Doubao Large Model Team**. The **Seedance 1.0 Pro** version represents the large-parameter, high-capability variant of the series.

Key highlights include:

- **Multi-shot narrative support** with seamless transitions between different scenes. - **Advanced semantic understanding**, enabling accurate interpretation of natural language prompts. - **Instruction-following capabilities**, producing results that closely align with prompt details. - Ability to generate **1080P high-definition videos** with smooth motion, rich details, and cinematic qualities. - Broad stylistic versatility ranging from photorealism to artistic styles such as cyberpunk, illustration, or textured media.

In short, Seedance 1.0 Pro is designed for creators who want to bring written descriptions and still images to life in motion, with professional-grade visual quality.

---

## Core Capabilities

### 🎥 Video Generation - **Text-to-Video (T2V):** Convert text descriptions directly into moving video sequences. - **Image-to-Video (I2V):** Animate static images, optionally enhanced with descriptive text prompts. - **Resolution:** Outputs at **1080p full HD** for production-ready clarity.

### ⚡ Motion and Dynamics - Handles **subtle movements** (e.g., facial expressions, gestures) and **large-scale dynamics** (e.g., action scenes, environment changes). - Ensures **physical realism** and stability in sequences, avoiding unnatural distortions. - Robust handling of **multi-agent interactions** and **complex action choreography**.

### 🎬 Multi-Shot Support - Native ability to generate **multi-shot sequences**, enabling cinematic narratives. - Maintains **subject, style, and atmosphere consistency** across multiple shots. - Smoothly transitions across **temporal and spatial scene changes**.

### 🎨 Style and Aesthetics - Wide style coverage: **photorealism, cyberpunk, illustration, felt texture**, and beyond. - Faithful adherence to stylistic prompts, ensuring creators’ intended mood and look are preserved. - Always aims for **cinematic visual richness**, with balanced lighting, textures, and details.

### 📝 Prompt Understanding - Accurately **parses natural language**, reducing ambiguity in interpretation. - Offers **stable camera movement control** and perspective adherence. - Handles **complex multi-layered scene descriptions** with strong adherence to intent.

---

## Technical Specifications

- **Model Version:** 1.0 Pro - **Output Resolution:** 1080p - **Input Types:** - Text prompts - Images (for I2V mode) - **Video Length:** Multi-shot capable (specific limits depend on prompt configuration)

---

## Model Performance

Benchmarks conducted on **SeedVideoBench-1.0** and independent evaluations show:

- **High prompt adherence**, even with detailed multi-part descriptions. - **Strong motion quality** for both human and environmental dynamics. - **Competitive aesthetic quality** against peer video models. - **Consistent visual fidelity** for image-to-video tasks.

---

## Example Use Cases

- **Creative Content:** Storyboarding, short films, music videos, or experimental art. - **Film Prototyping:** Visualizing scripts, animatics, and pre-visualization. - **Commercial Media:** Advertising clips, product showcases, branded content. - **Education & Documentary:** Visualizing complex concepts and narratives. - **Fantasy/Surrealism:** Generating dreamlike or imaginative video content.

---

## Known Limitations

- **Benchmark Bias:** Performance measured against standardized datasets; real-world quality may vary. - **Prompt Dependency:** Complex or vague prompts may reduce generation consistency. - **Multi-Shot Consistency:** Stronger results depend on clarity and specificity of scene descriptions.

Seedance 1.0 Pro API

Model Input

Input

Model Output

Output

Model Example Requests

Examples

Model Pricing

Pricing

Seedance 1.0 Pro API

cURL

JavaScript

Python

Input parameters

Use Seedance 1.0 Pro from Claude & Cursor (MCP)

MCP client config (Claude Desktop, Cursor)

Claude Code

Model Details

Model Details