Seedance 2.0 Fast

NEW

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 Fast — the low-latency video tier (async task).

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://usapi.dflop.top/v1

① Submit the task · cURL

curl https://usapi.dflop.top/v1/videos/generations \
  -H "Authorization: Bearer sk-gpushare-xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedance-2.0-fast",
    "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://usapi.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 by token (word-for-word identical to the upstream official terms): video price = per-token price × tokens used.

Rates: per second480p16.723Credits720p35.964Credits1080p80.919Credits
Settlement: Submission holds the worst case up front (the largest-pixel aspect ratio at this resolution + reference video at the full limit) → settled at actual usage on completion → the difference is refunded

Token usage = (input video duration + output video duration) × output video width × height × frame rate ÷ 1024, with the frame rate fixed at 24; width and height come from the pixel table in the official "Create video generation task" docs (by resolution × aspect ratio), and the usage.completion_tokens returned by the upstream is authoritative.
Minimum usage: when the input includes video, input video duration is counted from 4 seconds, so a 2-second reference video costs the same as a 4-second one. The official cap on total reference video duration is 15 seconds.
Token pricing (points / million tokens): Input has no video · 1080p delivery 1665 · Input has no video · 480p delivery 1665 · Input has no video · 720p delivery 1665 · Input includes video · 1080p delivery 990 · Input includes video · 480p delivery 990 · Input includes video · 720p delivery 990.
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: 2026-01-28
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 Fast→✓ doubao-seedance-2.0-fast

→ 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

关于 Seedance 2.0 Fast 的常见问题

怎么调用 Seedance 2.0 Fast？

请求体的 model 字段填 doubao-seedance-2.0-fast（上游官方原名 doubao-seedance-2-0-fast-260128 同样可用），打到 https://usapi.dflop.top/v1/videos/generations，把 sk-gpushare- 开头的密钥放进 Authorization: Bearer 请求头。这是非对话类 SKU，用上面的专用端点提交任务。

Seedance 2.0 Fast 的 API 价格是多少？

计费口径：按 token 计费（与上游官方逐字相同）。视频价格 = token 单价 × token 用量；token 用量 =（输入视频时长 + 输出视频时长）× 输出视频的宽 × 高 × 帧率 ÷ 1024，帧率固定 24，以上游回传的 usage.completion_tokens 为准
token 单价（Input has no video · 1080p delivery）：每 100 万 token 1,665 积分（≈ ¥27.75 / ≈ $4.12）
token 单价（Input has no video · 480p delivery）：每 100 万 token 1,665 积分（≈ ¥27.75 / ≈ $4.12）
token 单价（Input has no video · 720p delivery）：每 100 万 token 1,665 积分（≈ ¥27.75 / ≈ $4.12）
token 单价（Input includes video · 1080p delivery）：每 100 万 token 990 积分（≈ ¥16.5 / ≈ $2.45）
token 单价（Input includes video · 480p delivery）：每 100 万 token 990 积分（≈ ¥16.5 / ≈ $2.45）
token 单价（Input includes video · 720p delivery）：每 100 万 token 990 积分（≈ ¥16.5 / ≈ $2.45）
折算参考（16:9、输入不含视频）：480p 约 16.72 / 720p 约 35.96 / 1080p 约 80.92 积分/秒成片
平台以积分计价，60 积分 = ¥1；每次调用先按上限预扣，返回后按实际用量结算，差额自动退回。

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://usapi.dflop.top/v1

① Submit the task · cURL

curl https://usapi.dflop.top/v1/videos/generations \
  -H "Authorization: Bearer sk-gpushare-xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedance-2.0-fast",
    "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://usapi.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 by token (word-for-word identical to the upstream official terms): video price = per-token price × tokens used.

Rates: per second480p16.723Credits720p35.964Credits1080p80.919Credits
Settlement: Submission holds the worst case up front (the largest-pixel aspect ratio at this resolution + reference video at the full limit) → settled at actual usage on completion → the difference is refunded

Token usage = (input video duration + output video duration) × output video width × height × frame rate ÷ 1024, with the frame rate fixed at 24; width and height come from the pixel table in the official "Create video generation task" docs (by resolution × aspect ratio), and the usage.completion_tokens returned by the upstream is authoritative.
Minimum usage: when the input includes video, input video duration is counted from 4 seconds, so a 2-second reference video costs the same as a 4-second one. The official cap on total reference video duration is 15 seconds.
Token pricing (points / million tokens): Input has no video · 1080p delivery 1665 · Input has no video · 480p delivery 1665 · Input has no video · 720p delivery 1665 · Input includes video · 1080p delivery 990 · Input includes video · 480p delivery 990 · Input includes video · 720p delivery 990.
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 Fast→✓ doubao-seedance-2.0-fast

→ 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

关于 Seedance 2.0 Fast 的常见问题

怎么调用 Seedance 2.0 Fast？

Seedance 2.0 Fast 的 API 价格是多少？

计费口径：按 token 计费（与上游官方逐字相同）。视频价格 = token 单价 × token 用量；token 用量 =（输入视频时长 + 输出视频时长）× 输出视频的宽 × 高 × 帧率 ÷ 1024，帧率固定 24，以上游回传的 usage.completion_tokens 为准
token 单价（Input has no video · 1080p delivery）：每 100 万 token 1,665 积分（≈ ¥27.75 / ≈ $4.12）
token 单价（Input has no video · 480p delivery）：每 100 万 token 1,665 积分（≈ ¥27.75 / ≈ $4.12）
token 单价（Input has no video · 720p delivery）：每 100 万 token 1,665 积分（≈ ¥27.75 / ≈ $4.12）
token 单价（Input includes video · 1080p delivery）：每 100 万 token 990 积分（≈ ¥16.5 / ≈ $2.45）
token 单价（Input includes video · 480p delivery）：每 100 万 token 990 积分（≈ ¥16.5 / ≈ $2.45）
token 单价（Input includes video · 720p delivery）：每 100 万 token 990 积分（≈ ¥16.5 / ≈ $2.45）
折算参考（16:9、输入不含视频）：480p 约 16.72 / 720p 约 35.96 / 1080p 约 80.92 积分/秒成片
平台以积分计价，60 积分 = ¥1；每次调用先按上限预扣，返回后按实际用量结算，差额自动退回。

Quick start

Pricing

Capabilities & specs

Try it

Common errors

More models from this vendor

关于 Seedance 2.0 Fast 的常见问题

Quick start

Pricing

Capabilities & specs

Try it

Common errors

More models from this vendor

关于 Seedance 2.0 Fast 的常见问题