Seedance API — ruble pricing and a 5-minute setup

Cost calculator

Pick a model and a volume — the calculator uses the same formulas as API billing.

How to connect the Seedance API: first request in 5 minutes

From a key to production — six steps based on the real /api/v1 contracts. Each step links to the relevant docs section.

1. 1

   Get a key in your account

   Sign up, open the API section of your account, top up the balance in rubles and create a zc-sk-… key. One key unlocks Seedance and every other model in the catalogue.

   Read more →
2. 2

   Send the first request

   POST /v1/videos with model, prompt, seconds and aspect: the response carries the job id, status queued and price_rub — the amount is charged before the Seedance render starts.

   Read more →
3. 3

   Poll the job status

   GET /v1/videos?id=… every few seconds until status is completed (url field) or failed (refunded: true — the money is already back on the balance). The file URL is temporary — download right away.

   Read more →
4. 4

   Handle limits and errors

   30 requests per minute per key: on 429 wait and retry with a growing pause; 402 — top up the balance; 400 — check model against GET /v1/models. Failed generations are not charged, so retrying is safe.

   Read more →
5. 5

   Watch the budget

   GET /v1/balance returns the balance and 30-day spend; every call's price comes back in the response — write it to your logs and set an alert threshold in your own monitoring.

   Read more →
6. 6

   Ship to production

   Keep the key in server secrets, never in the frontend. For high Seedance volumes contact us — the limit is raised individually and companies can pay by invoice. Check the observed stability on the status page.

   Read more →

Inputs, limits and refunds

• Text → video and image → video (image: public https URL)
• Duration seconds: 4–10 (default 5)
• aspect 16:9 / 9:16 / 1:1 or an explicit size
• Charged up front by price_rub at the requested resolution (size / resolution), refunded if the render fails (refunded: true)
• A job stuck in the queue over 30 minutes is refunded automatically
• 30 requests per minute per key (all endpoints combined)

Error responses and refunds

# 401 {"type":"error","error":{"type":"authentication_error","message":"Invalid or revoked API key."}}
# 402 {"type":"error","error":{"type":"billing_error","message":"Not enough API balance: …"}}
# 429 {"type":"error","error":{"type":"rate_limit_error","message":"…"}}   ← 30 requests/min per key
# 400 {"type":"error","error":{"type":"invalid_request_error","message":"Unknown model \"…\". See GET /v1/models."}}
# 502 {"type":"error","error":{"type":"api_error","message":"… Charge refunded."}}   ← start failed → money back
# GET ?id → {"id":"vid_…","status":"failed","refunded":true}                        ← render failed → money back

Use cases

Prompting tips

• Name the shot type and camera move explicitly: wide establishing shot, slow dolly in, handheld tracking shot
• Set the light and time of day — golden hour, overcast noon, neon night — it anchors color and mood
• Describe how the scene changes across the clip, not just the opening frame: what moves, what enters, what ends
• For image-to-video, pick a clean, well-lit reference frame with the subject centered and in focus
• Match duration and aspect ratio to the platform: vertical 9:16 for short-form, 16:9 for landscape players
• Avoid asking for on-screen text, dense crowds, or close-up hands — these are the hardest details to render cleanly

Who the Seedance API is for

Industries where this kind of generation becomes part of the workflow rather than an experiment.