RealRelay.ai
ByteDance

Dreamina Seedance 2.5 (260628)

ByteDance video model for extended storytelling, with expanded multimodal references, editing and extension.

Starting at
Input
$11.70/ 1M
Output
$11.70/ 1M
Open dashboard

Channel

Each channel is compared at its lowest input-price tier; output breaks ties. A dash means /api/pricing does not provide that rate. Selecting a channel updates the endpoints and call example below.

byteplus/dreamina-seedance-2-5-260628
Input
$11.70 USD per 1M tokens
Output
$11.70 USD per 1M tokens
Cache read
- USD per 1M tokens
Cache write
- USD per 1M tokens

Prices and availability as published on Oct 12, 2026.

Capabilities

Dreamina Seedance 2.5 (260628) accepts text, image and video input and returns video. Documented modes are text-to-video, image-to-video from a first frame or from first and last frames, and multimodal reference-to-video.

It also supports video editing and video extension, and its expanded multimodal references let several input assets guide a single scene.

Text to videoImage to videoVideo to video
Input
TextImageVideo
Output
Video

Overview

Dreamina Seedance 2.5 (260628) is a video generation model from ByteDance. BytePlus describes it as built for extended storytelling with expanded multimodal references, and lists text-to-video, image-to-video from a first frame or from first and last frames, multimodal reference-to-video, video editing and video extension.

It accepts text, image and video input and returns video. It was released on June 28, 2026.

Pricing

Dreamina Seedance 2.5 (260628) is priced at $11.70 per 1M tokens for both input and output.

BytePlus prices this model by whether the input includes video, and the rate shown is for input and output alike. Dreamina Seedance 2.5 (260628) is available through RealRelay's OpenAI-compatible API.

Use cases

Use Dreamina Seedance 2.5 (260628) for narrative video such as brand stories, where extended storytelling and expanded multimodal references matter most.

With video input for editing and extension, it also fits revising an existing cut or lengthening a sequence while keeping the original assets as references for the scene and the story.

Frequently asked questions

What is Dreamina Seedance 2.5 (260628)?
Dreamina Seedance 2.5 (260628) is a ByteDance video generation model built for extended storytelling with expanded multimodal references, covering text-to-video, image-to-video, editing and extension.
How much does Dreamina Seedance 2.5 (260628) cost?
Dreamina Seedance 2.5 (260628) is priced at $11.70 per 1M tokens for both input and output.
What inputs and outputs does Dreamina Seedance 2.5 (260628) support?
Dreamina Seedance 2.5 (260628) accepts text, image and video input and returns video.
Does Dreamina Seedance 2.5 (260628) accept video as input?
Yes. Dreamina Seedance 2.5 (260628) accepts text, image and video input, which supports its video editing, video extension and multimodal reference modes.
When was Dreamina Seedance 2.5 (260628) released?
Dreamina Seedance 2.5 (260628) was released on June 28, 2026.
How do I call Dreamina Seedance 2.5 (260628) via the API?
Send requests to RealRelay's OpenAI-compatible API with the model ID byteplus/dreamina-seedance-2-5-260628 to use Dreamina Seedance 2.5 (260628).

More from ByteDance

All 17 ByteDance models