SEEDANCE25APIINDEPENDENT

Scene 01 · Take 01 · Independent API guide

Seedance 2.5 API
You direct. The model shoots.

Seedance 2.5 turns text, images, video and audio references into one continuous take. See real examples, copy a request, and create an EvoLink API key when you're ready to run.

DUR 4-30SRES 480P/720PACCESS EXPECTEDUPDATED 2026-07-09
View examples Get API key
Using a coding agent? Copy the prompt, or view it
You are helping me integrate the Seedance 2.5 API.

Primary context: https://seedance25api.io/llms-full.txt
Request schema: https://seedance25api.io/openapi.json

Rules:
- Do not invent or hardcode an API key.
- Ask me to create EVOLINK_API_KEY before any live call: https://evolink.ai/dashboard/keys?utm_source=seedance25api.io&utm_medium=referral&utm_campaign=home&utm_content=hero-agent-prompt
- Keep the model configurable. Seedance 2.5 API access is expected; verify provider support before production.
- Public rates are not published yet — surface cost as an estimate and flag it.
- Validate duration, resolution, and reference counts before sending.
- Use polling or callback_url for async video jobs.
- Build behind a configurable model parameter so the same code can switch models.
Seedance 2.5 is pre-release. Want to generate today? Try Seedance 2.0 →
EXAMPLESPROMPTS WITH SETTINGS

Examples are API recipes, not just a gallery.

Official launch cases with the prompt attached. Master specs are shown per case; the reusable request clamps to the expected 480p/720p launch tiers. Verify provider support before production.

REQUEST BUILDERSHAPE + HANDOFF

Build the request before you create the key.

Shape a request, copy the payload or an agent prompt, then create a key only when you're ready for live calls.

Duration
Resolution
Audio
References
Image, video, and audio references are supported by the model. This builder prepares the request shape only — add your own reference URLs in code and validate the provider's limits before live calls.
Request preview
 
Copy first. Create a key only when you are ready for live calls. Public rates launch with the API.
TWO PATHSHUMANS AND AGENTS
AGENT CONTEXTMACHINE-READABLE ENTRYPOINTS
Q&ABEFORE YOU INTEGRATE
Q.01What is the Seedance 2.5 API?
The Seedance 2.5 API generates video from a text prompt and optional image, video, and audio references, called through a provider such as EvoLink. This is an independent guide to that API — status, request schema, examples, and key setup — and is not an official ByteDance product.
Q.02How do I use the Seedance 2.5 API?
Send a POST request to the Seedance 2.5 endpoint with a model, prompt, duration, and quality, then poll the returned job id until the video is ready. You supply your own key as EVOLINK_API_KEY. The quickstart has copy-ready cURL and Node examples.
Q.03Is the Seedance 2.5 API available yet?
Seedance 2.5 API access is pre-release, so treat the model id and limits as expected and verify provider support before production. Build behind a configurable model parameter so your integration is ready the moment access is enabled for your account.
Q.04What durations and resolutions does the Seedance 2.5 API support?
The Seedance 2.5 API is expected to generate 4–30 second clips at 480p or 720p launch resolutions, with up to 30 image, 10 video, and 10 audio references per request. Treat 1080p and 4K as pending until provider docs confirm them.
Q.05How do AI coding agents integrate the Seedance 2.5 API?
Point your coding agent at /llms-full.txt and /openapi.json for machine-readable context and the request schema. The agent can generate integration code, then ask you to create an EVOLINK_API_KEY before any live call.

READY TO EXECUTE

Request prepared. Key is the final step.

Create API key