Seedance 2.0 Lite

NEW

Model ID

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

Video generationClosed source

by bytedance · ByteDance Seedance 2.0 lite tier — strong value per clip (async task). Supports text-to-video, image-to-video and multimodal references; 720p/1080p, 4-15s, 24fps.

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-lite",
    "content": [
      {"type": "text", "text": "海边日落,无人机航拍视角 --ratio 16:9"}
    ],
    "resolution": "720p",
    "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
# ⚠️ 这张卡 resolution 必填(仅 720p / 1080p),整卡按交付分辨率计价,缺省返回 400

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 second720p59.616Credits1080p148.716Credits
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 3060 · Input has no video · 720p delivery 2760 · Input includes video · 1080p delivery 1860 · Input includes video · 720p delivery 1680.
This card is priced by delivery resolution. resolution is required (720p / 1080p only), and omitting it returns 400.
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: 2026-08-12
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 Lite→✓ doubao-seedance-2.0-lite

→ 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 Lite 的常见问题

怎么调用 Seedance 2.0 Lite？

请求体的 model 字段填 doubao-seedance-2.0-lite，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 Lite 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 3,060 积分（≈ ¥51 / ≈ $7.57）
token 单价（Input has no video · 720p delivery）：每 100 万 token 2,760 积分（≈ ¥46 / ≈ $6.82）
token 单价（Input includes video · 1080p delivery）：每 100 万 token 1,860 积分（≈ ¥31 / ≈ $4.6）
token 单价（Input includes video · 720p delivery）：每 100 万 token 1,680 积分（≈ ¥28 / ≈ $4.15）
折算参考（16:9、输入不含视频）：720p 约 59.62 / 1080p 约 148.72 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-lite",
    "content": [
      {"type": "text", "text": "海边日落,无人机航拍视角 --ratio 16:9"}
    ],
    "resolution": "720p",
    "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
# ⚠️ 这张卡 resolution 必填(仅 720p / 1080p),整卡按交付分辨率计价,缺省返回 400

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 second720p59.616Credits1080p148.716Credits
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 3060 · Input has no video · 720p delivery 2760 · Input includes video · 1080p delivery 1860 · Input includes video · 720p delivery 1680.
This card is priced by delivery resolution. resolution is required (720p / 1080p only), and omitting it returns 400.
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 Lite→✓ doubao-seedance-2.0-lite

→ 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 Lite 的常见问题

怎么调用 Seedance 2.0 Lite？

Seedance 2.0 Lite 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 3,060 积分（≈ ¥51 / ≈ $7.57）
token 单价（Input has no video · 720p delivery）：每 100 万 token 2,760 积分（≈ ¥46 / ≈ $6.82）
token 单价（Input includes video · 1080p delivery）：每 100 万 token 1,860 积分（≈ ¥31 / ≈ $4.6）
token 单价（Input includes video · 720p delivery）：每 100 万 token 1,680 积分（≈ ¥28 / ≈ $4.15）
折算参考（16:9、输入不含视频）：720p 约 59.62 / 1080p 约 148.72 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 Lite 的常见问题

Quick start

Pricing

Capabilities & specs

Try it

Common errors

More models from this vendor

关于 Seedance 2.0 Lite 的常见问题