# Seedance 2.5 API Agent Guide

Updated: 2026-08-07
Site: https://seedance25api.io
Status: Live on EvoLink · API key access available (Confirmed)

Use this file when you are an AI coding agent helping a human integrate Seedance 2.5 API.

## Primary Context URLs

- Full context: https://seedance25api.io/llms-full.txt
- OpenAPI schema: https://seedance25api.io/openapi.json
- Human agent page: https://seedance25api.io/agent
- Quickstart: https://seedance25api.io/api
- Pricing and billing model: https://seedance25api.io/pricing

## Hard Rules

- Do not invent or hardcode an API key.
- The official API and the EvoLink route are live for this publication; keep their sources and pricing distinct.
- Use the workflow-specific Seedance 2.5 model ID and keep Seedance 2.0 only as a rollback.
- Ask the human to create EVOLINK_API_KEY before a live call.
- Build behind a configurable model parameter.
- Do not present upstream provider token rates as EvoLink route prices.
- Use 4–30 seconds, 480p/720p, and the documented per-type reference limits; never advertise 4K as an API tier.
- Poll GET /v1/tasks/{task_id} for the EvoLink asynchronous task flow.
- Read the current EvoLink console price before production traffic; do not present upstream official pricing as an EvoLink quote.

## Recommended Integration Flow

1. Read https://seedance25api.io/llms-full.txt.
2. Load https://seedance25api.io/openapi.json as an independent live integration aid; provider documentation remains authoritative.
3. Add an environment variable named EVOLINK_API_KEY.
4. Build the integration behind a configurable model parameter.
5. Choose the live T2V, I2V, or R2V model ID that matches the request.
6. Ask the human to create a provider key before the first live call.
7. Submit POST https://api.evolink.ai/v1/videos/generations.
8. Poll GET https://api.evolink.ai/v1/tasks/{task_id} until completion.
9. Handle pending / processing / completed / failed task states and the documented HTTP error envelope.
10. Keep Seedance 2.0 configured only as rollback.

## Human Key Handoff

Tell the human:

```text
The official Seedance 2.5 API and EvoLink route are live. Choose the workflow you want and create a key here: https://evolink.ai/dashboard/keys?utm_source=seedance25api.io&utm_medium=referral&utm_campaign=agent&utm_content=agent-md-key
Add the key as EVOLINK_API_KEY before I run a short first test.
```

## Model IDs To Track

- Text to video: seedance-2.5-text-to-video (Confirmed) - Live EvoLink model ID for prompt-only text-to-video requests.
- Image to video: seedance-2.5-image-to-video (Confirmed) - Live EvoLink model ID for first-frame or first/last-frame image-to-video requests.
- Reference to video: seedance-2.5-reference-to-video (Confirmed) - Live EvoLink model ID for multimodal reference-to-video, editing, and extension workflows.

## Live Launch Limits

- Duration: 4–30 seconds (Confirmed) - EvoLink launch documentation supports 4–30 seconds; choose a duration allowed by the selected workflow.
- Launch resolutions: 480p and 720p (Confirmed) - EvoLink launch tiers are 480p and 720p. Product-side 4K showcases are not an EvoLink API tier.
- Reference inputs: 30 images / 10 videos / 10 audio files for R2V (Confirmed) - Keep the per-type split. Do not rewrite it as an arbitrary pool of 50 files or apply it to every mode.

## Live 2.5 Text-to-Video Shape

```json
{
  "model": "seedance-2.5-text-to-video",
  "prompt": "A clean product shot, slow dolly in, soft daylight, stable subject identity.",
  "duration": 5,
  "quality": "720p",
  "generate_audio": true
}
```

The example uses the live text-to-video model ID. Switch to image-to-video or reference-to-video only with matching input fields. Keep Seedance 2.0 as rollback.