ByteDance

Doubao Seedance 2.5 260628 Max

ByteDanceToken-basedDynamic Pricing
Alias:doubao-seedance-2-5-260628-max
Create API Key

Compare doubao-seedance-2-5-260628-max API pricing, supported endpoints, capabilities and access options on Modelsell.

文生视频图生视频多模态参考镜头控制渠道变体
Starting price
View full pricing
Context
—
Maximum input window
Modalities
→

Pricing by Supplier

Volcengine
-8%
火山引擎官方接口
1080p_video_input
Output$6.87$6.3204/ 1M
1080p_no_video_input
Output$11.49$10.5708/ 1M
480_720p_video_input
Output$6.27$5.7684/ 1M
480_720p_no_video_input
Output$10.45$9.614/ 1M

Capabilities / Supported modalities

Function callingToolsJSON modeStructured outputVision
Input
Output

Provider & data privacy

Provider
ByteDanceDocs
Tokenizer
Doubao tokenizer
License
Proprietary (commercial)Proprietary
Data retention37 daysNot used for upstream training by default

Performance

Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows

Metrics sourced fromArtificial Analysis 2026-09-30·Doubao Seedance 2.5 260628 Max

This model is not included in the current benchmark snapshot.

Missing models or measurements are not zero scores.

Benchmark charts preserve the source model selection and reasoning settings. Missing models or measurements are not zero scores, and benchmark cost or speed is not this site’s service commitment.

About Doubao Seedance 2.5 260628 Max

用镜头讲清楚一个场景

Seedance 2.5 面向有具体创作意图的视频生成:主体怎样出现、相机怎样靠近、光线何时变化,都可以写进提示词。它能从文字构建画面,也能结合图片、视频和音频参考组织视觉与声音,适合制作品牌短片、产品情境展示、故事片段及拍摄提案。

参考素材帮助统一创作方向

人物图可以确定造型,场景图可以提供空间与配色,动作参考可以帮助表达运动节奏。使用多份素材时,先说明各自用途,再讲它们在成片中的关系。例如,让参考角色走进参考房间,同时只借用视频里的缓慢推进镜头。清楚分工,比要求模型同时复刻所有参考内容更容易得到连贯结果。

Seedance 2.5 可以生成与画面同步的声音。写声音时,应把来源和动作对应起来:开门时的门轴声、脚踩碎石的声音、远处驶过的列车声。对白、配乐和环境声应有主次,避免每一层都过于突出,掩盖了画面叙事。

从样片走向可用素材

适合先验证单个镜头,再逐步发展为完整短片。拍产品时重点检查外形、材质和运动过程;拍人物时重点检查表情、手部与转身衔接。需要多个连续镜头时,保留同一组角色参考和光线设定,逐镜明确起点与终点。生成结果可以作为后期剪辑的素材,也可以帮助团队提前讨论镜头是否成立。

Use cases and prompting

品牌故事示例

准备一张原创咖啡师角色图和一张店内照片,提示词写:

“角色参考用于咖啡师外观,场景参考用于店内布局。清晨开店,咖啡师推开木门,走向吧台,把一只白色杯子放到咖啡机下。相机从门口缓慢跟随到吧台,暖色侧光,保留门铃、脚步与杯子轻放声,不加配乐和字幕。”

如何控制参考的影响

若视频参考只用于运镜,明确写出‘仅参考镜头运动,人物和布景按图片参考’。多个主体需要分别说明身份和动作。

声音为什么抢过了画面?

把声音分成主要动作声和背景环境声,并写明背景音轻一些。没有叙事作用的配乐或对白可以先去掉,等画面节奏确定后再补充。

API access

API documentation

doubao-seedance-2-5-260628-max

Use the linked documentation for model-specific request parameters and examples.

Authentication

All requests must include Authorization: Bearer <TOKEN> header. Anthropic-formatted endpoints accept the x-api-key header instead.

Generate tokens from the Tokens page; you can scope them to specific models, groups, IPs, and rate-limits.

Rate limits

SupplierRPMTPMRPD
sd国内特价UnlimitedUnlimitedUnlimited
VolcengineUnlimitedUnlimitedUnlimited

No restriction

Frequently asked questions about doubao-seedance-2-5-260628-max

What is doubao-seedance-2-5-260628-max?

Compare doubao-seedance-2-5-260628-max API pricing, supported endpoints, capabilities and access options on Modelsell.

How do I call doubao-seedance-2-5-260628-max?

Create an API key with access to doubao-seedance-2-5-260628-max, then use the exact model ID and a supported endpoint from the API access section. Request fields depend on the selected endpoint.

How is doubao-seedance-2-5-260628-max priced?

Pricing depends on the selected provider group and the model billing unit. The current input, output, request, or media prices are shown on this page before sign-up.

How should I evaluate doubao-seedance-2-5-260628-max for my project?

Start with the use cases and prompting guidance on this page, then evaluate the model with representative inputs from your project.