Seedance 2.0 Mini

10% OFFNEW

Model ID

Put this value in the request body's `model` field — not the display name above.

Upstream vendor's own model id

Equivalent to the call ID above — either one works.

Video generationClosed source

by bytedance · ByteDance Seedance 2.0 Mini, a light, high-value video generation tier (asynchronous task). Text-to-video, image-to-video and multimodal reference; 480p / 720p, 4-15 seconds, 24 fps.

Try it now

Quick start

EndpointPOST /v1/videos/generations

AuthenticationAuthorization: Bearer sk-gpushare-…Get API key

Call styleAsynchronous: submit for an ID, then poll until it settles

Base URLhttps://api.dflop.top/v1

① Submit the task · cURL

curl https://api.dflop.top/v1/videos/generations \
  -H "Authorization: Bearer sk-gpushare-xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedance-2.0-mini",
    "content": [
      {"type": "text", "text": "海边日落,无人机航拍视角 --ratio 16:9"}
    ],
    "duration": 5
  }'
# 返回 {"id": "...", "status": "queued"}
# 图生视频:content 里追加 {"type":"image_url","image_url":{"url":"https://..."}}
# ⚠️ duration 缺省按 12 秒预扣,结算按实际时长 —— 建议显式传

② Poll for the result · cURL

curl https://api.dflop.top/v1/videos/generations/$TASK_ID \
  -H "Authorization: Bearer sk-gpushare-xxxxxxxx"

# status: queued -> running -> succeeded / failed / expired / cancelled
# 建议 5-10 秒轮询一次。轮询免费。

This is an async task: submit for a task ID, then poll until it settles. Polling itself is free.

Pricing

Billed per token, exactly as the upstream bills it: video price = token price × tokens used.

Rates: per second480p12.475Credits720p26.827Credits
Settlement: On submit, the worst case is held (the largest frame at that resolution + reference video at its limit) → settled on actual usage when done → the difference is refunded

Token usage = (input video seconds + output video seconds) × output width × height × frame rate ÷ 1024, at a fixed 24 fps. Width and height come from the official pixel table for video generation tasks (by resolution × aspect ratio); the usage.completion_tokens the upstream returns is what counts.
Minimum usage: when the input includes video, input video counts as at least 4 seconds — a 2-second reference video costs the same as a 4-second one. The official limit for total reference video is 15 seconds.
Token price (credits per 1M tokens): without input video · 480p output 1242 · without input video · 720p output 1242 · with input video · 480p output 756 · with input video · 720p output 756.
Failed or expired tasks are refunded in full.
Polling task status is free and does not count toward usage.
All your API keys share one balance; when it runs out the API returns HTTP 402 `quota_exceeded`.

Capabilities & specs

Category: Video generation
Endpoint family: Video generation (Videos)
Released: 2026-06-16
License: Closed source

Try it

Models like this bill for real per image / per second / per call and are mostly async tasks, so there is no one-click test here. Use the sample code above, or generate in the matching workbench (which has a parameter panel and a cost estimate).

Open the workbench

Common errors

404 model_not_found

You passed the display name instead of the model ID.✗ Seedance 2.0 Mini→✓ doubao-seedance-2.0-mini

→ Copy the Model ID at the top of this page

402 quota_exceeded

Insufficient account balance. All your API keys share one balance.

→ Add funds in your account

401 / 403

The API key is invalid, or it has a model allowlist that doesn't include this ID.

→ Check the key's status and allowed models

400 invalid_request

`resolution` is required on Lite (`-lite`) SKUs and only accepts 720p / 1080p; anything else also returns 400.

→ Check your request body against the sample code above

Seedance 2.0 Mini FAQ

How do I call Seedance 2.0 Mini?

Set the model field of the request body to doubao-seedance-2.0-mini (the upstream's official name doubao-seedance-2-0-mini-260615 works too), send it to https://api.dflop.top/v1/videos/generations, and put your key (it starts with sk-gpushare-) in the Authorization: Bearer header. This is not a chat SKU; submit tasks to the dedicated endpoint above.

How much does the Seedance 2.0 Mini API cost?

Billing: per token (the same formula as the upstream's official one). Video price = token price × tokens used; tokens used = (input video length + output video length) × output width × height × frame rate ÷ 1024, with the frame rate fixed at 24, as reported in the upstream's usage.completion_tokens
Token price (without input video · 480p output): 1,380 credits (≈ ¥23 / ≈ $3.41) per 1M tokens
Token price (without input video · 720p output): 1,380 credits (≈ ¥23 / ≈ $3.41) per 1M tokens
Token price (with input video · 480p output): 840 credits (≈ ¥14 / ≈ $2.08) per 1M tokens
Token price (with input video · 720p output): 840 credits (≈ ¥14 / ≈ $2.08) per 1M tokens
For reference (16:9, no input video): 480p about 13.86 / 720p about 29.81 credits per second of output
Prices are in credits: 60 credits = ¥1. Each call first holds the most it could cost, then settles on actual usage and refunds the difference.

Quick start

EndpointPOST /v1/videos/generations

AuthenticationAuthorization: Bearer sk-gpushare-…Get API key

Call styleAsynchronous: submit for an ID, then poll until it settles

Base URLhttps://api.dflop.top/v1

① Submit the task · cURL

curl https://api.dflop.top/v1/videos/generations \
  -H "Authorization: Bearer sk-gpushare-xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedance-2.0-mini",
    "content": [
      {"type": "text", "text": "海边日落,无人机航拍视角 --ratio 16:9"}
    ],
    "duration": 5
  }'
# 返回 {"id": "...", "status": "queued"}
# 图生视频:content 里追加 {"type":"image_url","image_url":{"url":"https://..."}}
# ⚠️ duration 缺省按 12 秒预扣,结算按实际时长 —— 建议显式传

② Poll for the result · cURL

curl https://api.dflop.top/v1/videos/generations/$TASK_ID \
  -H "Authorization: Bearer sk-gpushare-xxxxxxxx"

# status: queued -> running -> succeeded / failed / expired / cancelled
# 建议 5-10 秒轮询一次。轮询免费。

This is an async task: submit for a task ID, then poll until it settles. Polling itself is free.

Pricing

Billed per token, exactly as the upstream bills it: video price = token price × tokens used.

Rates: per second480p12.475Credits720p26.827Credits
Settlement: On submit, the worst case is held (the largest frame at that resolution + reference video at its limit) → settled on actual usage when done → the difference is refunded

Token usage = (input video seconds + output video seconds) × output width × height × frame rate ÷ 1024, at a fixed 24 fps. Width and height come from the official pixel table for video generation tasks (by resolution × aspect ratio); the usage.completion_tokens the upstream returns is what counts.
Minimum usage: when the input includes video, input video counts as at least 4 seconds — a 2-second reference video costs the same as a 4-second one. The official limit for total reference video is 15 seconds.
Token price (credits per 1M tokens): without input video · 480p output 1242 · without input video · 720p output 1242 · with input video · 480p output 756 · with input video · 720p output 756.
Failed or expired tasks are refunded in full.
Polling task status is free and does not count toward usage.
All your API keys share one balance; when it runs out the API returns HTTP 402 `quota_exceeded`.

Common errors

404 model_not_found

You passed the display name instead of the model ID.✗ Seedance 2.0 Mini→✓ doubao-seedance-2.0-mini

→ Copy the Model ID at the top of this page

402 quota_exceeded

Insufficient account balance. All your API keys share one balance.

→ Add funds in your account

401 / 403

The API key is invalid, or it has a model allowlist that doesn't include this ID.

→ Check the key's status and allowed models

400 invalid_request

`resolution` is required on Lite (`-lite`) SKUs and only accepts 720p / 1080p; anything else also returns 400.

→ Check your request body against the sample code above

Seedance 2.0 Mini FAQ

How do I call Seedance 2.0 Mini?

How much does the Seedance 2.0 Mini API cost?

Billing: per token (the same formula as the upstream's official one). Video price = token price × tokens used; tokens used = (input video length + output video length) × output width × height × frame rate ÷ 1024, with the frame rate fixed at 24, as reported in the upstream's usage.completion_tokens
Token price (without input video · 480p output): 1,380 credits (≈ ¥23 / ≈ $3.41) per 1M tokens
Token price (without input video · 720p output): 1,380 credits (≈ ¥23 / ≈ $3.41) per 1M tokens
Token price (with input video · 480p output): 840 credits (≈ ¥14 / ≈ $2.08) per 1M tokens
Token price (with input video · 720p output): 840 credits (≈ ¥14 / ≈ $2.08) per 1M tokens
For reference (16:9, no input video): 480p about 13.86 / 720p about 29.81 credits per second of output
Prices are in credits: 60 credits = ¥1. Each call first holds the most it could cost, then settles on actual usage and refunds the difference.

Seedance 2.0 Mini

Quick start

Pricing

Capabilities & specs

Try it

Common errors

Seedance 2.0 Mini FAQ

Related

Seedance 2.0 Mini

Quick start

Pricing

Capabilities & specs

Try it

Common errors

Seedance 2.0 Mini FAQ

Related

Quick start

Pricing

Capabilities & specs

Try it

Common errors

More models from this vendor

Seedance 2.0 Mini FAQ

Related

Quick start

Pricing

Capabilities & specs

Try it

Common errors

More models from this vendor

Seedance 2.0 Mini FAQ

Related