AGENT 모드 / SEEDANCE 2.5 API
agent가 코드를 작성하기 전에 올바른 컨텍스트부터 전달하세요.
이 페이지는 사람을 대신해 Seedance 2.5 API를 연동하는 Cursor, Claude Code, Codex, ChatGPT 등 agent를 위한 것입니다. 지시 블록을 복사해 agent가 머신 파일을 읽게 하고, 코드가 준비된 뒤에 provider Key를 생성하세요.
01 / 컨텍스트먼저 이것을 복사
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=agent&utm_content=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.
왜 효과적인가
agent는 안정적인 컨텍스트 URL, schema, Key 경계, 명확한 provider 인계를 받습니다. 자격 증명이 이미 있는 척하지 않고 코드를 준비할 수 있습니다.
API 키 만들기02 / 머신 파일AGENT가 읽어야 할 것
03 / 사실상태를 반영한 연동
Expected
Provider-mediated access
Seedance 2.5 API availability should be verified with the provider before production use. Build behind a configurable model parameter.
Expected
Reference-to-video model ID
seedance-2.5-reference-to-video Confirmed in EvoLink API docs; model is pre-release ("not yet available"). References are optional, so a prompt-only call behaves as text-to-video.
Pending
Text-to-video / image-to-video IDs
Pending provider docs Not yet confirmed. Keep the model parameter configurable so the same code can switch when the IDs are published.
Expected
Launch 제한
4-30 seconds · 480p and 720p 전송 전에 길이, quality, 참조 수(최대 이미지 30 / 영상 10 / 오디오 10)를 검증하세요.
04 / AGENT 체크리스트실제 호출 전에
- Do not invent or hardcode an API key.
- Ask the human to create EVOLINK_API_KEY before live calls.
- Build behind a configurable model parameter.
- Surface cost as an estimate — public rates are not published yet.
- Validate duration, quality, and reference counts before sending.
- Use polling or callback_url for async completion.
- If the model is unavailable for the account, keep the request shape and switch models via the configurable parameter once access is enabled.