seedance-2.5-flash AI Video API

ByteDance Seedance 2.5 is an audio-video generation model for text-to-video and image-to-video workflows. Use reference media, first/last-frame controls, 4–30-second requests, and optional audio through Flatkey's /v1/videos endpoint.

Image to VideoReference-guided VideoAudio generationShort-form Video
Provider
ByteDance
Flatkey price
480p
from $0.041312/ second · 4s min
720p
from $0.09288/ second · 4s min
Generator setup · Playground (edit before sign-up)

Input

PromptCheck more132 / 10000
Quick Prompts
Reference image0 / 30
Reference videos0 / 10
Reference Audios0 / 10
Start generating

Output

Preview

Request summary

Endpoint
POST /v1/videos
Model ID
seedance-2.5-flash
Aspect ratio
adaptive
Resolution
720p
Duration
5s
Generate audio
On
Reference media
None

Preview only. Sign in to submit this request to Flatkey.

Request preview
{
  "model": "seedance-2.5-flash",
  "content": [
    {
      "type": "text",
      "text": "Create a short video with seedance-2.5-flash: clear subject motion, realistic lighting, stable camera, and production-ready framing."
    }
  ],
  "resolution": "720p",
  "ratio": "adaptive",
  "duration": 5,
  "generate_audio": true
}
Loading...

Pricing

seedance-2.5-flash Pricing

Prices below are calculated from Flatkey pricing data for this model and the visible groups currently returned by our pricing API.

Flatkey price

480p · Price / second

Live catalog model
from $0.041312/ second · 4s min
480p · Price / second
from $0.041312/ second · 4s min
720p · Price / second
from $0.09288/ second · 4s min
Try a prompt
Shared balance

Add credits

Add credits

Use the same Flatkey balance and API key across image, video, audio, and text models.

Model catalog
Model Type
Text to Video
API
/v1/videos
Billing basis
second
Duration
4–30s
Aspect ratio
adaptive · 16:9 · 4:3 · 1:1 · 3:4 · 9:16

Seedance 2.5 AI video generator features for references and audio

The documented contract covers text-to-video and image-to-video inputs, reference media, optional audio, and bounded output settings.

Text-to-video and image-to-video

Start from a written scene or supply reference images for a subject, product, or storyboard you have already designed.

Reference media and frame control

The request can include image, video, and audio references, plus first-frame and last-frame roles for reference-led workflows.

Audio-video generation

Enable audio generation as an explicit request option; do not assume a language list or audio behavior that the selected route does not document.

Duration and output controls

Choose 4–30 seconds, 480p or 720p, adaptive or supported fixed ratios, and the audio setting before submitting the task.

Compare

Compare Seedance 2.5 with Seedance 2.0: documented video fields

This comparison records documented Seedance 2.5 behavior. Seedance 2.0 values are marked as not verified rather than inferred.

CapabilitySeedance 2.0 (not re-audited)Seedance 2.5
Clip lengthNot verified in this audit4–30 seconds per request
Reference inputsNot verified in this auditUp to 50 total: 30 images, 10 videos, and 10 audio
Frame controlNot verified in this auditFirst-frame and last-frame roles are supported
AudioNot verified in this auditAudio generation can be enabled per request
Editing workflowNot verified in this auditReference-guided and first/last-frame workflows

Choose the right request before you integrate

Review the supported workflows, live cost for the current setup, and the exact parameter contract used by Flatkey.

Live cost estimate

Calculated from the current Playground settings and the live catalog rate when a fixed unit price is available.

Current setup
720p · 5s
Live rate
from $0.09288 / second · 4s min
Estimated request
$0.4644
$0.09288 × 5s

The final charge follows the submitted request and your account group. Token-priced or tiered requests cannot be reduced to one fixed estimate.

Workflows and Model ID

Use only the workflows marked available. Flatkey keeps one public model ID while the request body selects the input workflow.

Available

Text to Video

Create a clip from a text prompt and supported output controls.

Model ID
seedance-2.5-flash
Endpoint
/v1/videos
Available

Image to Video

Animate one or more image references while preserving the requested subject and composition.

Model ID
seedance-2.5-flash
Endpoint
/v1/videos
Available

Reference to Video

Guide the result with the documented image, video, or audio reference inputs.

Model ID
seedance-2.5-flash
Endpoint
/v1/videos
Not available on this route

Video Edit

Transform an existing clip when this route exposes video editing.

Model ID
seedance-2.5-flash
Endpoint
/v1/videos
Not available on this route

Video Extend

Continue an existing clip when this route exposes video extension.

Model ID
seedance-2.5-flash
Endpoint
/v1/videos

Parameter compatibility

These values come from the same model configuration used by the Playground and request preview.

resolutionResolution
Accepted

480p · 720p

Default: 720p
ratioAspect ratio
Accepted

adaptive · 16:9 · 4:3 · 1:1 · 3:4 · 9:16

Default: adaptive
durationDuration
Accepted

4–30

Default: 5
generate_audioGenerate audio
Accepted

On · Off

Default: On
imageReference limit
Accepted

30 files

Endpoint: /v1/videos
videoReference limit
Accepted

10 files

Endpoint: /v1/videos
audioReference limit
Accepted

10 files

Endpoint: /v1/videos

From first test to production

Use the same request contract in the Playground and API, then handle validation, balance, task state, and output retrieval explicitly.

Request lifecycle

  1. 1

    Validate the model, prompt, references, and output settings.

  2. 2

    POST the request and retain the returned task ID.

  3. 3

    Poll task status or process the configured callback.

  4. 4

    Fetch the generated file from the content endpoint and store it before expiry.

Production checks

Parameter validation

Reject unsupported sizes, durations, ratios, formats, or reference counts before submitting.

Authentication and balance

Handle invalid keys, insufficient balance, rate limits, and account-group pricing separately.

Input or policy rejection

Surface the rejected prompt or asset clearly so the user can replace only the failing input.

Task failure or timeout

Keep the task ID, use bounded retries, and never treat a timeout as a successful generation.

Prompt library

Seedance 2.5 prompt guide for text-to-video and image-to-video

Use these workflow-specific prompts as starting points. Output depends on the supplied references and request settings.

Micro-drama storyboard

Create a 9:16 micro-drama storyboard from a three-beat comic script: a courier notices a torn envelope, follows a red umbrella through a crowded station, and stops at a silent platform. Keep the same two characters, wardrobe, props, and rainy evening light across the beats; use clear eyelines and no readable text.

View full promptCollapse prompt

Create a 9:16 micro-drama storyboard from a three-beat comic script: a courier notices a torn envelope, follows a red umbrella through a crowded station, and stops at a silent platform. Keep the same two characters, wardrobe, props, and rainy evening light across the beats; use clear eyelines and no readable text.

E-commerce UGC

Create a 9:16 e-commerce UGC video for a reusable travel bottle. Show an adult creator opening the package, filling the bottle, and placing it in a tote bag. Keep the bottle shape and lid color consistent, use a small apartment kitchen, leave space for Portuguese captions added in post, and do not invent logos or readable label text.

View full promptCollapse prompt

Create a 9:16 e-commerce UGC video for a reusable travel bottle. Show an adult creator opening the package, filling the bottle, and placing it in a tote bag. Keep the bottle shape and lid color consistent, use a small apartment kitchen, leave space for Portuguese captions added in post, and do not invent logos or readable label text.

Film previsualization

Create a 12-second film previsualization of a detective entering an empty observatory at dawn. Start with a wide establishing view, track behind the character, then pan to the telescope and hold on the doorway. Keep screen direction, blocking, and the warm-to-cool light transition consistent; no dialogue text or logos.

View full promptCollapse prompt

Create a 12-second film previsualization of a detective entering an empty observatory at dawn. Start with a wide establishing view, track behind the character, then pan to the telescope and hold on the doorway. Keep screen direction, blocking, and the warm-to-cool light transition consistent; no dialogue text or logos.

Game cinematic reference shot example
Game cinematic

Animate a game-cinematic reference board into an 8-second shot: a masked pilot walks across a hangar while a grounded shuttle powers up behind them. Preserve the pilot silhouette, helmet markings, shuttle geometry, and camera-left-to-right movement; use practical hangar lights and restrained smoke, with no new text or logos.

View full promptCollapse prompt

Animate a game-cinematic reference board into an 8-second shot: a masked pilot walks across a hangar while a grounded shuttle powers up behind them. Preserve the pilot silhouette, helmet markings, shuttle geometry, and camera-left-to-right movement; use practical hangar lights and restrained smoke, with no new text or logos.

Creator microphone explainer video example
Creator explainer

Create a 4:5 creator explainer about a compact microphone for an independent video maker. Begin with a talking-head medium shot, cut to a close-up of the cable connection, then return to the same framing for a practical tip. Keep the speaker, microphone, and room layout consistent; leave clean caption space and avoid readable brand text.

View full promptCollapse prompt

Create a 4:5 creator explainer about a compact microphone for an independent video maker. Begin with a talking-head medium shot, cut to a close-up of the cable connection, then return to the same framing for a practical tip. Keep the speaker, microphone, and room layout consistent; leave clean caption space and avoid readable brand text.

Market-research creative variant example
Market-research variant

Create three short, clearly distinct creative variants for a market-research test of a sunscreen product: beach morning, city commute, and family picnic. Keep the same bottle proportions and cap, change only setting and opening action, use neutral props, and leave all claims and captions for post-production. Do not add medical promises or invented labels.

View full promptCollapse prompt

Create three short, clearly distinct creative variants for a market-research test of a sunscreen product: beach morning, city commute, and family picnic. Keep the same bottle proportions and cap, change only setting and opening action, use neutral props, and leave all claims and captions for post-production. Do not add medical promises or invented labels.

Why Flatkey

Use Seedance 2.5 through a unified video API

Use one key for the model catalog, inspect the request contract, and keep pricing tied to the selected settings.

One key for the model catalog

Use the same Flatkey account and API key across video, image, audio, and text workloads.

Documented video contract

Keep Seedance's content[] request, /v1/videos endpoint, and asynchronous task flow explicit in your integration.

Pricing follows the request

Resolution, duration, and video-reference input change the formula; the catalog value is not a universal per-second promise.

Live data only when available

Performance and activity cards show telemetry when enough real Flatkey traffic exists, otherwise they stay unreported.

API

seedance-2.5-flash API

Four ways in, all on the same key and the same model catalog. Pick one to see a runnable example.

Call any model with an OpenAI-compatible API. Copy a ready-to-run example for your model and language.
Use the OpenAI SDK you already know — with Flatkey as the gateway.
Generate images and videos from your terminal. Let your AI assistant drive the workflow.
Connect your coding agent with one command, then use Flatkey from your existing projects.
curl https://router.flatkey.ai/v1/videos \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-***" \
  -d '{"model":"seedance-2.5-flash","content":[{"type":"text","text":"A cinematic product shot of a sports car on a wet track, soft studio lighting, high detail."}],"ratio":"adaptive","resolution":"720p","duration":5,"generate_audio":true}'

# Poll for the result (replace TASK_ID with the returned task id)
curl "https://router.flatkey.ai/v1/videos/TASK_ID" \
  -H "Authorization: Bearer sk-***"
Docs

FAQ

Seedance 2.5
API, pricing, and release-date questions

Pricing, compatibility, limits, and how your prompts and generated files are handled.

What is Seedance 2.5?
Seedance 2.5 is ByteDance's audio-video generation model for text-to-video and image-to-video requests, with reference media and optional audio controls.
How much does Seedance 2.5 cost?
480p · Price / second: from $0.041312 / second · 4s min; 720p · Price / second: from $0.09288 / second · 4s min. Prices below are calculated from Flatkey pricing data for this model and the visible groups currently returned by our pricing API.
What can I use it for?
Use it for micro-drama and comic storyboards, product and UGC variants, film previsualization, game cinematics, creator clips, and market-research creative tests.
How do I use the model in my app?
POST to /v1/videos with the Seedance content[] format, retain the asynchronous task id, and fetch the result from /v1/videos/{task_id}/content.
Can I control output features?
Yes. Set 480p or 720p, 4–30 seconds, a supported ratio, generate_audio, and the documented reference/frame fields.
Is the Flatkey API OpenAI compatible?
Flatkey authentication and the shared catalog use the gateway pattern, while Seedance video requests use content[] and the asynchronous /v1/videos contract.
What limits apply?
A request can include up to 30 images, 10 videos, and 10 audio references, with 50 references total; account rate limits and availability can change.
What is the Seedance 2.5 release date?
The official ByteDance article was published on 2026-07-31; Flatkey's catalog lists released_at as 2026-08-04. These are different metadata fields, so neither date alone represents every launch.
Is Seedance 2.5 free?
No free or unlimited entitlement is promised on this page. Use the live Flatkey pricing data and your account limits before running jobs.