doubao-seed-2.0-code-preview-260215
ByteDance
面向 Agent 工作流的代码预览模型,在 SWE-Bench、LiveCodeBench 上跑出接近一线的成绩,适合自主编码智能体与多语言工程任务。
¥5.695/ M
¥34.17/ M
¥0.5695/ M
¥0.0475/ M
Seedance 2.5 是豆包大模型团队推出的新一代多模态视频创作模型,已迈入「长叙事 × 多素材 × 强编辑 × 多语言」的工业级新阶段。
Resolution
480
720
Without video input
¥0.6888/ s
¥1.5484/ s
With video input
¥0.6888/ s
¥1.5484/ s
Input
Text
Output
Video
Reference materials
Optional. Used for image-to-video, first/last frame driving, video style transfer, or audio-driven generation. Click or drag to upload a local file.
Last frame requires a first frame URL
{
"model": "bytedance/seedance-2.5",
"prompt": "An alpine lake at first light: the mirror-like surface reflects snowy peaks and drifting clouds as the camera slowly tracks along the shore. Thin mist hovers over the water, golden sunlight breaks through the clouds onto the forest, and birds glide across the distant sky. Cinematic quality, soft natural light, 4K detail.",
"duration": 5,
"resolution": "480",
"aspect_ratio": "adaptive",
"generate_audio": true,
"seed": -1
}{}API
Drop-in code to call this model with EasyAPI's OpenAI-compatible API.
Create an API key from your dashboard and set it as an environment variable:
Replace sk-xxxxxxxx with your API token from the console (Bearer token).
Create API tokenexport EASYAPI_API_KEY=sk-xxxxxxxxUse bytedance/seedance-2.5 with the EasyAPI API:
curl https://token.easyapi.com/v1/videos \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $EASYAPI_API_KEY" \
-d '{
"model": "bytedance/seedance-2.5",
"prompt": "A golden retriever running on a sunny beach, cinematic camera movement",
"duration": 5,
"resolution": "720p",
"aspect_ratio": "adaptive",
"generate_audio": false,
"seed": -1,
"size": "1280x720",
"input_references": [
{
"type": "image",
"url": "https://cdn.example.com/portrait.jpg",
"role": "first_frame"
}
]
}'Submits a video generation task from a text prompt.
https://token.easyapi.com/v1/videosBearer $EASYAPI_API_KEYapplication/jsonbytedance/seedance-2.5Submit a video generation task from a prompt. The response includes a task ID or result URL. Docs
| Name | Type | Required | Description |
|---|---|---|---|
model | string | Yes | Model ID, e.g. bytedance/seedance-2.0. Currently bytedance/seedance-2.5 |
prompt | string | Yes | Video description; include subject, action, scene, camera and style. Limits vary by model: Sora 500 characters, Hailuo 2000, Wan T2V 1500, I2V 800. EasyAPI sets no hard limit; over-limit requests are rejected upstream and passed through as 502 / 503. |
duration | integer | No | Video duration in seconds, 4–15 |
resolution | string | No | Output resolution: 480p, 720p or 1080p |
aspect_ratio | string | No | Aspect ratio: 16:9, 4:3, 1:1, 3:4, 9:16, 21:9 or adaptive |
generate_audio | boolean | No | Whether to generate audio |
seed | integer | No | Random seed, -1 to 4294967295; the same seed does not guarantee identical output |
size | string | No | Exact output size, e.g. 1280x720 |
input_references | array | No | Optional array of reference assets for image-to-video, first/last-frame control, video style transfer or audio-driven generation |
input_references[].type | string | Yes | Reference asset type: image, video or audio; must match role |
input_references[].url | string | Yes | HTTPS URL of the reference asset |
input_references[].role | string | Yes | Reference asset role: first_frame, last_frame, reference (appearance reference image), reference_video or reference_audio |
metadata | object | No | Pass-through business field for auditing or source tagging |
webhook_url | string | No | Callback URL invoked when the task succeeds or fails |
Official OpenAI and other SDKs work by swapping the base URL. See integration guide
ByteDance
面向 Agent 工作流的代码预览模型,在 SWE-Bench、LiveCodeBench 上跑出接近一线的成绩,适合自主编码智能体与多语言工程任务。
¥5.695/ M
¥34.17/ M
¥0.5695/ M
¥0.0475/ M
ByteDance
Seed 2.0 系列轻量档,延迟低、调用成本可控,智能体、编程与 GUI 任务表现稳定,适合高频交互场景与大批量任务分发。
¥0.5582/ M
¥3.349/ M
¥0.1116/ M
—
ByteDance
Seed 2.0 系列轻量档,延迟低、调用成本可控,智能体、编程与 GUI 任务表现稳定,适合高频交互场景与大批量任务分发。
¥2.8475/ M
¥22.78/ M
¥0.5695/ M
¥0.0475/ M
ByteDance
Seed 2.0系列轻量档,主打高并发与低延迟,支持多级思考强度调节,适合批量处理、内容审核、分类标注等高吞吐场景。
¥0.1861/ M
¥1.8606/ M
¥0.0372/ M
—