ByteDanceByteDance video model

Seedance 2.5 Flash. Long takes at a draft price.

The faster, lower-cost tier of Seedance 2.5: clips from 4 to 30 seconds, six formats, native audio and reference images, for about two thirds of the full model's price.

  • 4 to 30 second clips
  • 6 aspect ratios
  • Native audio
  • First and last frame control
  • Reference images

Seedance 2.5 Flash keeps what makes Seedance 2.5 useful for production, any exact length from 4 to 30 seconds in one take, six aspect ratios and sound generated with the picture, and lowers the price per second. ByteDance lists it at 7e-6 per video token against 1.07e-5 for Seedance 2.5, so the same clip costs about two thirds as much. It renders at 480p or 720p, with 720p when no resolution is set.

That makes it the model for the many takes before the one that ships: prompt variants, timing passes and storyboard drafts. On Treza it is one node on a canvas or one request in chat. Draft a scene on Flash, then re-render the winning prompt on Seedance 2.5 at 1080p by switching the model on the same node.

4 to 30 second clips

Pick the exact second. A whole Short or product beat fits in one generation, with no stitching.

Six formats

16:9, 4:3, 1:1, 3:4, 9:16 and 21:9, so one model covers feed, story and banner placements.

Native audio

Ambience and effects come back with the clip, so drafts are watchable as soon as they land.

Keyframes and references

Pin a first or last frame, or wire reference images in to keep a product or character the same across shots.

What to make with Seedance 2.5 Flash

Real prompts, and what comes back. Every one runs as a node on the canvas, and most run in chat.

“A barista pours steamed milk into a latte in a sunlit cafe, slow push-in, 9:16”

A vertical 4 second draft with cafe ambience, ready to judge in the feed.

“The same folded navy shirt from this photo on a white marble counter, slow orbit”

The product from the reference image, placed in a new scene.

“Five versions of a 12 second opener for a skincare launch, 1:1”

Five drafts to choose from before the final render.

“A 30 second walk through a night market, handheld, rain sounds”

One continuous take at the full length the model offers.

“Start on this logo frame, end on the packed product shot (both attached)”

A clip that opens and lands on your brand art.

“Ultrawide 21:9 drone pass over a coastline at golden hour”

A banner-ready landscape shot.

Seedance 2.5 Flash is one node on a canvas

Chain it with language, image, and video models, then publish the whole pipeline as an API. See how a full AI video pipeline fits together.

  1. Step 01

    Draft the brief

    A language model node expands a one-line idea into a detailed, on-brand prompt before it ever reaches the model.

  2. Step 02

    Generate with Seedance 2.5 Flash

    Run variants in parallel, compare against other models on the same prompt, and keep every result in run history.

  3. Step 03

    Publish it as an API

    The pipeline becomes a versioned endpoint. Your product calls it with the typed /invoke API or any OpenAI SDK.

Seedance 2.5 Flash as an API, priced per clip

The Seedance 2.5 Flash API

Build a pipeline with Seedance 2.5 Flash on a node and publish it. It becomes a versioned HTTP endpoint: the typed /invoke route enqueues a run and returns a run id to poll, and an OpenAI-compatible route works with SDKs you already use. Agents connect over MCP the same way. Your prompt engineering ships inside the pipeline, so every caller gets your quality, and swapping the model later does not change the API your product calls.

Seedance 2.5 Flash pricing

Prepaid credits, no subscription. Each clip is charged at Seedance 2.5 Flash's own rate from your balance, shown before you run, and a failed generation costs nothing. Credit packs start at $5 and never expire, which suits spiky production schedules. Run history records the cost of every generation, per node, so spend is auditable rather than a surprise.

Seedance 2.5 Flash, answered

How is Seedance 2.5 Flash different from Seedance 2.5?

Same clip lengths (4 to 30 seconds), the same six aspect ratios, audio, keyframes and reference images. Flash stops at 720p where Seedance 2.5 also offers 1080p, and costs about two thirds as much per second.

What resolution does Seedance 2.5 Flash output?

480p or 720p. With no resolution set it renders 720p; a 9:16 clip comes back at 720x1280.

Does Seedance 2.5 Flash take reference images?

Yes. Reference images wired into the node are sent as references, not used as the opening frame, so a product or character can appear in a new scene. A first frame and a last frame can be set as well.

How much does Seedance 2.5 Flash cost on Treza?

Treza uses prepaid credits with no subscription. Each clip is charged at Seedance 2.5 Flash's rate from your balance, and only successful generations are charged. Credit packs start at $5 and never expire.

Can I call Seedance 2.5 Flash through an API?

Yes. Build a pipeline that uses Seedance 2.5 Flash and publish it as a versioned HTTP endpoint. Call the typed /invoke API from your product, or point any OpenAI SDK at the OpenAI-compatible endpoint. If a better model ships later, swap it on the node without changing the API your product calls.