Short answer: The Seedance 2.5 API lets your server create videos and images with the same credits and prices as the web generator. Each account can run 1 active generation, send 10 generation requests per minute and spend 2,000 API credits per day.
What is the Seedance 2.5 API?
It is a REST API at the base URL /api/v1, described in the Seedance 2.5 API documentation with an OpenAPI 3.1 spec you can import into Postman, Insomnia or a client generator. You authenticate with a Bearer API key, and every generation is asynchronous: create the job, poll its status, then download the output. API generation uses an active paid subscription or purchased credits from your account balance.
For the web side of your cost planning, visit Seedance 2.5 and keep the same prompt and output requirements when comparing a web job with an API quote.
Which models can I call with the Seedance 2.5 API?
| Video model | API model ID |
|---|---|
| Seedance 2.5 | seedance-2.5 |
| Seedance 2.0 Pro | seedance-2.0-pro |
| Seedance 2.0 Fast | seedance-2.0-fast |
| Seedance 2.0 Mini | seedance-2.0-mini |
| Seedance 1.5 Pro | seedance-1.5-pro |
| Kling 3.0 | kling-3.0 |
| Veo 3.1 fast | veo-3.1-fast |
The image models are gpt-image-2, nano-banana-2 and nano-banana-pro. Call GET /models for the supported modes, resolutions, durations and aspect ratios of each model.
Still on Seedance 2.0? Our Seedance 2.0 API guide covers the Pro, Fast and Mini model IDs and how to upgrade to 2.5.
How much does the Seedance 2.5 API cost?
- The first five reference images are included; each additional image costs 7 credits.
- Other models and settings follow the same prices as the web generator, listed on the Seedance 2.5 pricing. Annual plans there work out to about $0.35–$0.50 per 100 credits.
- Quotes, status queries and downloads do not use generation credits.
- Credits are reserved before submission, and a verified failure is refunded once.
To see how this compares with third-party Seedance API resellers, read the Seedance 2.5 API providers comparison.
What are the Seedance 2.5 API rate limits?
These limits apply per account and are shared by all API keys on it.
| Limit | Value |
|---|---|
| Active API generations | 1 |
| Generation and upload requests | 10/minute, 1,000/day |
| Reads and quotes | 60/minute, 20,000/day |
| API generation credit budget | 2,000/day |
| Image uploads | 100 files and 500 MiB/day |
Daily windows reset in UTC.
Is there another Seedance 2.5 API with video and audio references?
The Seedance 2.5 API with multimodal references uses the same Bearer-key, create-and-poll pattern and the same credit balance as its web generator. It adds multimodal-to-video, with up to 30 images, 10 videos and 10 audio files per Seedance 2.5 request, and Seedance 2.5 output at 480p, 720p or 1080p from 4 to 30 seconds. Use it when your integration needs video or audio references.
How do I make my first Seedance 2.5 API call?
- Create a key. Go to Settings → API keys. The key is shown only once. Requests with an Origin header are rejected, so call the API from a server, not a browser.
- Get a quote. Send
POST /quoteswith your generation body. The response returnscost_creditsand doesn't generate or charge anything. - Create the job. Send
POST /videoswith anIdempotency-Keyheader and an optionalmax_cost_creditscap. A202response means accepted, not finished. - Poll. Call
GET /generations/{id}no more than once every 10 seconds, using the same key that created the job. - Download. When the status is
success, readoutputs[].url. The URLs expire within 15 minutes, and media is kept for 14 days.
Need a Python quote–create–poll walkthrough? Read our Seedance 2.5 video generation API Python guide.
Can I use the Seedance 2.5 API in n8n?
The n8n flow is: Trigger → Quote → Create → Save ID → Wait 20–30 s → Get status → loop while pending/processing → Download on success. Store the key as a Header Auth credential, not in node fields, and retry with the original idempotency key instead of creating a new job.
Integration checklist
- ☐ Key stored only on the server
- ☐ Every job quoted first, with
max_cost_creditsset - ☐ One idempotency key per intended generation, reused on retry
- ☐ Polling every 10 s or longer (20–30 s in n8n)
- ☐ Outputs copied to your own storage before the URLs expire
- ☐ Only one active generation per account
Seedance 2.5 API FAQ
How much does the Seedance 2.5 API cost per second?
Most users integrate on their own by following the /docs/api documentation; if you need more permissions or have special requirements, contact support.
What access does the Seedance 2.5 API require?
Check the selected model, your paid plan or purchased-credit balance, and the displayed cost before submitting a generation request.
Does a failed Seedance 2.5 API generation cost credits?
No, a verified failure is refunded once. An uncertain task is not refunded automatically just because time has passed, so retry with the same idempotency key.
What are the Seedance 2.5 API rate limits?
Per account: 1 active generation, 10 generation and upload requests per minute and 1,000 per day, 60 reads and quotes per minute and 20,000 per day, and a 2,000-credit daily generation budget.
How long are Seedance 2.5 API outputs kept?
14 days. Each output URL expires within 15 minutes, so request a fresh URL when needed and copy files to your own storage.
Try Seedance 2.5 Today
Ready to experience the next generation of AI video creation? Seedance 2.5 and see the difference for yourself.
