模型详情
dreamina-seedance-2-0-260128
按量付费
动态计价
6 个档位
Seedance 2.0 is a video generation model from ByteDance. It supports text-to-video, image-to-video with first and last frame control, and multimodal reference-to-video. It is particularly strong at preserving character consistency, visual style, and camera movement from reference material. The number of tokens is given by (height of output video * width of output video * duration * 24) / 1024
模型规格
- 上下文长度
- –
- 最大输出
- –
- 输入/输出模态
- –
- 发布日期
- 2026-04
02
API 端点
单一 MixRoute 网关，OpenAI 兼容
-
OpenAI-compatible
/v1/chat/completionsPOST
03
阶梯价格
单位：/unit
| 档位 | 价格 /unit |
|---|---|
| 1080p_video res == "1080p" && has_video | $4.7000 |
| 4k_video (!(res == "1080p" && has_video)) && (res == "4k" && has_video) | $2.4000 |
| lowres_video (!(res == "1080p" && has_video)) && (!(res == "4k" && has_video)) && (has_video) | $4.3000 |
| 1080p (!(res == "1080p" && has_video)) && (!(res == "4k" && has_video)) && (!(has_video)) && (res == "1080p") | $7.7000 |
| 4k (!(res == "1080p" && has_video)) && (!(res == "4k" && has_video)) && (!(has_video)) && (!(res == "1080p")) && (res == "4k") | $4.0000 |
| lowres (!(res == "1080p" && has_video)) && (!(res == "4k" && has_video)) && (!(has_video)) && (!(res == "1080p")) && (!(res == "4k")) | $7.0000 |
单一端点，可验证的决策
使用相同的请求格式测试此模型和备用路由
从真实工作负载开始，再由质量、总成本和故障条件决定是否接入生产流量。