AGENT MODE / SEEDANCE 2.5 API

Give your coding agent the right context before it writes code.

This page is for Cursor, Claude Code, Codex, ChatGPT, and other agents integrating Seedance 2.5 API for a human. Copy the instruction block, let the agent read the machine files, then create a provider key only when the code is ready.

Open llms-full.txt Open OpenAPI

01 / CONTEXTCOPY THIS FIRST

AGENT_PROMPT.TXTHUMAN -> AGENT

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=agent&utm_content=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.

Why this works

The agent gets stable context URLs, a schema, a key boundary, and the exact provider handoff. It can prepare code without pretending it already has credentials.

Create API key

02 / MACHINE FILESWHAT AGENTS SHOULD READ

/llms.txtShort index for LLMs and search agents. /llms-full.txtFull context: facts, status, schema, pricing notes, handoff. /agent.mdMarkdown checklist for coding agents. /openapi.jsonRequest contract for API clients and codegen.

03 / FACTSSTATUS-AWARE INTEGRATION

Confirmed

Live on EvoLink · API key access available

The upstream official API and EvoLink integration are live for the August 7 publication. Use the three workflow-specific EvoLink model IDs and verify the current price shown in the EvoLink console before production traffic.

Confirmed

Text to video

seedance-2.5-text-to-video

Live EvoLink model ID for prompt-only text-to-video requests.

Confirmed

Image to video

seedance-2.5-image-to-video

Live EvoLink model ID for first-frame or first/last-frame image-to-video requests.

Confirmed

Reference to video

seedance-2.5-reference-to-video

Live EvoLink model ID for multimodal reference-to-video, editing, and extension workflows.

Confirmed

Launch limits

4–30 seconds · 480p and 720p

Use the documented 4–30 second and 480p/720p launch values, keep them configurable, and confirm account-specific caps with a short live test.

04 / AGENT CHECKLISTBEFORE LIVE CALLS

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.