Seedance 2.5
⧉Seedance 2.5 是字节跳动的视频模型，一个接口通过参数生成不同类型的视频：不带参考图为文生视频、带参考图（作首帧）为图生视频。时长 4–30 秒逐秒可选，分辨率 480P / 720P，六种画幅，可生成原生音轨。异步任务：提交后轮询任务号获取重托管后的稳定 mp4 直链，按秒计费、失败全额退。
Live Test · Playground
Try out Seedance 2.5 right here (available after login)。
Input
VideoOutput
videoAbout Seedance 2.5
Seedance 2.5 is ByteDance's AI video model and the longest-form video model on NezhaGate. One model, one set of params: omit the reference image for text-to-video, include one (first frame by default) for image-to-video. Duration is any integer 4-30 seconds, resolution 480P / 720P, six aspect ratios (16:9 / 9:16 / 21:9 / 4:3 / 1:1 / 3:4), with an optional generated soundtrack. Async job: POST /v1/videos/generations returns HTTP 202 and a job id immediately; poll GET /v1/videos/jobs/{id} until status=succeeded and read data[0].url. That link is an mp4 re-hosted by us — it will not expire the way the upstream CDN link does.
Use cases
Up to 30 seconds — the only model here that can carry a complete story in one shot, ideal for concept films and product narratives.
Use a reference as the first frame and the subject identity, wardrobe and scene detail carry through — good for animating product shots and character sheets.
Push in, pull out, pan and tilt written in the prompt are followed closely; pick this when the camera language matters.
9:16 for short-video platforms, 21:9 for banners and trailer-style pieces.
How to choose
Choose 2.5 when you need more than 15 seconds or explicit camera control. Within 15 seconds and without strict camera requirements, seedance-2.0-fast is faster and cheaper; for resolution and native audio look at minimax-h3. 480P and 720P cost the same, so use 720P unless you specifically want a smaller file.
FAQ
How does one model make different video types?
Why do 480P and 720P cost the same?
How does image-to-video work?
How is it billed, and am I charged on failure?
Related Models
Explore other models you can integrate.
GPT-5.6 Sol
前沿旗舰 Agentic 编程模型
GPT-5.6 Terra
日常均衡 Agentic 编程模型
GPT-5.6 Luna
快而省的 Agentic 编程模型
GPT-5.5
旗舰对话与推理模型
GPT Image 2
高质量文生图 / 图生图模型
Nano Banana 2
高质量文生图 / 图生图模型
Nano Banana Pro
旗舰级文生图 / 图生图模型
Claude Sonnet 4.6
均衡高效的对话 / 代码模型
Claude Opus 5
Anthropic 新一代旗舰模型
Claude Fable 5
Anthropic Fable 系列 · 叙事与长文特化
Gemini 3.1 Pro
Google 新一代旗舰推理模型
Gemini 3.6 Flash
新一代高速思考模型 · 四档思考预算
Gemini 3.6 Flash High
深度思考档
Gemini 3.6 Flash Low
极速低耗档
Gemini 3.6 Flash Tiered
自动调档
Gemini 3 Flash
高速低延迟，高性价比对话模型
Gemini 3.5 Flash
新一代高速思考模型
Gemini 2.5 Flash
高速低延迟，高性价比对话
Veo 3.1
文生 / 图生视频 · 多档 · 多分辨率
Seedance 2.0
文生 / 图生视频 · 4–15 秒
Seedance 2.0 Fast
低延迟 · 最省
MiniMax H3
1440P · 原生音频
