SEEDANCE25APIINDEPENDENT

Scene 01 · Take 01 · Independent API guide

Seedance 2.5 API
You direct. The model shoots.

The official Seedance 2.5 API is live. Choose the right workflow ID, build the request, and start with a short production-safe test.

DUR 4–30SRES 480P/720PACCESS CONFIRMEDUPDATED 2026-08-07
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
Integration schema: https://seedance25api.io/openapi.json

Rules:
- Do not invent or hardcode an API key.
- The official Seedance 2.5 API and EvoLink route are live; route status is confirmed.
- Ask me to create EVOLINK_API_KEY before the first live call: https://evolink.ai/dashboard/keys?utm_source=seedance25api.io&utm_medium=referral&utm_campaign=home&utm_content=hero-agent-prompt
- Choose seedance-2.5-text-to-video, seedance-2.5-image-to-video, or seedance-2.5-reference-to-video for the matching workflow.
- Use 4–30 seconds and 480p/720p; do not advertise 4K as an EvoLink API tier.
- For R2V, preserve the documented split of up to 30 images, 10 videos, and 10 audio files.
- Poll GET /v1/tasks/{task_id} for task status.
- Read the current EvoLink console price before scaled traffic; never substitute upstream official pricing.
- Keep the model configurable and retain Seedance 2.0 only as rollback.
Already run Seedance 2.0? Keep it as rollback while you test 2.5. Review the 2.0 fallback →
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 documented 480p/720p launch tiers. Confirm account-level 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
Reference mode supports up to 30 images, 10 videos, and 10 audio files. Switch to the R2V model ID when you add those inputs.
Request preview
 
Generate on EvoLink
Live Seedance 2.5 text-to-video payload. Prepare the request, run a short first test, and keep Seedance 2.0 as rollback.
TWO PATHSHUMANS AND AGENTS
AGENT CONTEXTMACHINE-READABLE ENTRYPOINTS
Q&ABEFORE YOU INTEGRATE
Q.01What is the Seedance 2.5 API?
Seedance 2.5 is ByteDance's multimodal video model. Its official developer API is live; this independent site tracks official facts separately from provider availability.
Q.02How do I integrate the Seedance 2.5 API?
Choose the text-to-video, image-to-video, or reference-to-video workflow ID, create an API key, submit an asynchronous generation request, and poll the task endpoint until completion.
Q.03Is the Seedance 2.5 API available yet?
Yes. The official API and EvoLink integration are live as of August 7, 2026. As of August 7, 2026, EvoLink exposes three workflow-specific model IDs through its unified video API.
Q.04What durations and resolutions does the Seedance 2.5 API support?
Current documentation lists 4–30 seconds and 480p/720p. Confirm the exact enums for your account before production use; 4K is not a documented API tier.
Q.05How do AI coding agents use this guide?
Use /llms-full.txt and /openapi.json, ask the human for EVOLINK_API_KEY, select the workflow-specific model ID, and retain Seedance 2.0 as an explicit rollback.

READY TO RUN

Your request is ready. Continue with the recommended API provider.

Continue with EvoLink