Doubao Seedream

Doubao Seedream image generation supports text-to-image, single-image reference, multi-image reference, and sequential image generation. The platform uses the async task protocol: create a task to receive a taskId, then query the task or use a callback to retrieve results.

Model

Model Name	Output	Mode
`doubao-seedream-5.0-lite`	Image URLs	Text-to-image, image references, sequential generation, web search
`doubao-seedream-4.5`	Image URLs	Text-to-image, image references, sequential generation

Pricing

Priced by successfully generated images. Failed images are not charged.

Model	Credits
`doubao-seedream-5.0-lite`	15 credits/image
`doubao-seedream-4.5`	15 credits/image

Sequential generation pre-charges the maximum possible image count. After completion, unused image credits are refunded based on the number of successful images.

Create Task

curl -X POST https://api.aivideoapi.ai/v1/images/generations \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedream-5.0-lite",
    "callback_url": "https://your-server.com/webhook",
      "input": {
        "prompt": "An orange cat reading beside a window, watercolor illustration, soft morning light",
        "size": "2K",
        "watermark": false
      }
  }'

Request Body

Field	Type	Required	Description
`model`	string	Yes	`doubao-seedream-5.0-lite` or `doubao-seedream-4.5`
`input`	object	Yes	Generation parameters, see below
`callback_url`	string	No	Optional callback URL for completion/failure notifications

Input Parameters

Field	Type	Required	Description
`prompt`	string	Yes	Image generation prompt. Chinese and English are supported.
`image_urls`	string[]	No	Public HTTP(S) reference image URLs. Base64 input is not supported. 1-14 images when provided.
`size`	string	No	Output size, defaults to `2048x2048`. Use a resolution tier or pixel size; see Size & Resolution.
`sequential_image_generation`	string	No	Sequential generation mode, defaults to `disabled`. One of: `disabled`, `auto`.
`sequential_image_generation_options`	object	No	Sequential generation options. Only used when `sequential_image_generation=auto`.
`tools`	array	No	Only supported by `doubao-seedream-5.0-lite`. Use `[{ "type": "web_search" }]`.
`stream`	boolean	No	Whether to request upstream streaming, defaults to `false`. The platform still returns final images through the task result.
`output_format`	string	No	Only supported by `doubao-seedream-5.0-lite`. One of: `jpeg`, `png`. Defaults to `jpeg`.
`watermark`	boolean	No	Whether to add a watermark, defaults to `true`.
`optimize_prompt_options`	object	No	Prompt optimization options. Currently supports `{ "mode": "standard" }`.

doubao-seedream-4.5 does not support 3K, tools, or output_format.

Reference Image Limits

Limit	Requirement
Image formats	`jpeg`, `png`, `webp`, `bmp`, `tiff`, `gif`, `heic`, `heif`
File size	Up to 30 MB per image
Total pixels	Up to 6000×6000 per image
Width and height	Both must be greater than 14 px
Aspect ratio	`[1/16, 16]`
Multi-image reference	Up to 14 images

When sequential generation is enabled, reference image count plus generated image count must not exceed 15.

Size & Resolution

size can be a resolution tier or a pixel size such as 2048x2048. Pixel sizes must have total pixels between 2560x1440 and 4096x4096, with aspect ratio between [1/16, 16].

Model	Supported Tiers	Default
`doubao-seedream-5.0-lite`	`2K`, `3K`, `4K`	`2048x2048`
`doubao-seedream-4.5`	`2K`, `4K`	`2048x2048`

Common sizes:

Resolution	Aspect Ratio	Pixel Size
`2K`	`1:1`	`2048x2048`
`2K`	`4:3`	`2304x1728`
`2K`	`3:4`	`1728x2304`
`2K`	`16:9`	`2848x1600`
`2K`	`9:16`	`1600x2848`
`2K`	`3:2`	`2496x1664`
`2K`	`2:3`	`1664x2496`
`2K`	`21:9`	`3136x1344`
`3K`	`1:1`	`3072x3072`
`3K`	`4:3`	`3456x2592`
`3K`	`3:4`	`2592x3456`
`3K`	`16:9`	`4096x2304`
`3K`	`9:16`	`2304x4096`
`3K`	`3:2`	`3744x2496`
`3K`	`2:3`	`2496x3744`
`3K`	`21:9`	`4704x2016`
`4K`	`1:1`	`4096x4096`
`4K`	`4:3`	`4704x3520`
`4K`	`3:4`	`3520x4704`
`4K`	`16:9`	`5504x3040`
`4K`	`9:16`	`3040x5504`
`4K`	`3:2`	`4992x3328`
`4K`	`2:3`	`3328x4992`
`4K`	`21:9`	`6240x2656`

3K is only supported by doubao-seedream-5.0-lite.

Sequential Generation

sequential_image_generation controls whether to generate an image set:

Value	Description
`disabled`	Disable sequential generation and generate one image.
`auto`	Let the model decide whether to return an image set and how many images to generate.

sequential_image_generation_options supports:

Field	Type	Required	Description
`max_images`	integer	No	Maximum generated images, 1-15.

Example: Text-to-Image

curl -X POST https://api.aivideoapi.ai/v1/images/generations \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedream-5.0-lite",
    "callback_url": "https://your-server.com/webhook",
    "input": {
      "prompt": "A cinematic night city poster with neon reflections on a rainy street",
      "size": "2K",
      "watermark": false
    }
  }'

Example: Multi-Image Reference

curl -X POST https://api.aivideoapi.ai/v1/images/generations \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedream-4.5",
    "callback_url": "https://your-server.com/webhook",
    "input": {
      "prompt": "Use the subject and colors from the two references to create a clean premium product poster",
      "image_urls": [
        "https://example.com/reference-1.png",
        "https://example.com/reference-2.png"
      ],
      "size": "2048x2048"
    }
  }'

Example: Sequential Generation With Web Search

curl -X POST https://api.aivideoapi.ai/v1/images/generations \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedream-5.0-lite",
    "callback_url": "https://your-server.com/webhook",
    "input": {
      "prompt": "Generate a set of ecommerce detail-page images for summer camping gear, including a tent, lantern, folding chair, and outdoor table",
      "size": "3K",
      "sequential_image_generation": "auto",
      "sequential_image_generation_options": {
        "max_images": 6
      },
      "tools": [
        { "type": "web_search" }
      ],
      "output_format": "png"
    }
  }'

Response

{
  "code": 200,
  "msg": "success",
  "data": {
    "taskId": "397ce9f2-c04e-4244-ac33-3af19a7cc297"
  }
}

Query Task

curl https://api.aivideoapi.ai/v1/tasks/{taskId} \
  -H "Authorization: Bearer sk-your-api-key"

Status flow: pending -> processing -> completed or failed.

Completed

{
  "id": "397ce9f2-c04e-4244-ac33-3af19a7cc297",
  "status": "completed",
  "model": "doubao-seedream-5.0-lite",
  "created_at": 1775383908,
  "completed_at": 1775383925,
  "output": {
    "urls": [
      "https://file.aivideoapi.ai/images/2026/07/04/abc123.png"
    ],
    "metadata": {
      "model": "doubao-seedream-5.0-lite",
      "generated_images": 1,
      "requested_image_count": 1,
      "output_format": "png",
      "image_sizes": ["2048x2048"],
      "partial_errors": [],
      "usage": {
        "generated_images": 1,
        "output_tokens": 16384,
        "total_tokens": 16384
      }
    }
  }
}

Partial Sequential Failure

If at least one image succeeds, the task is marked completed. Successful images are returned normally and failed images are recorded in metadata.partial_errors. Billing is based only on successful images.

{
  "id": "397ce9f2-c04e-4244-ac33-3af19a7cc297",
  "status": "completed",
  "model": "doubao-seedream-5.0-lite",
  "output": {
    "urls": [
      "https://file.aivideoapi.ai/images/2026/07/04/abc123.png"
    ],
    "metadata": {
      "generated_images": 1,
      "requested_image_count": 2,
      "partial_errors": [
        {
          "index": 1,
          "code": "image_generation_failed",
          "message": "Some images failed to generate. Adjust parameters and retry."
        }
      ]
    }
  }
}

Failed

{
  "id": "57c8772c-f834-46f3-9b7d-81f92e104050",
  "status": "failed",
  "model": "doubao-seedream-5.0-lite",
  "created_at": 1775383908,
  "error": {
    "code": "upstream_error",
    "message": "Image generation failed"
  }
}

Failed tasks are automatically refunded.

Callback Notifications

Pass callback_url when creating the task. When the task completes or fails, we send a POST request whose payload matches the GET /v1/tasks/{taskId} response.

Error Codes

When a request fails, the API returns a JSON error response:

{
  "error": {
    "code": "insufficient_credits",
    "message": "Your credit balance is too low. Please top up.",
    "type": "billing_error"
  }
}

Error Reference

HTTP Status	Code	Type	Description
400	`invalid_request`	invalid_request_error	Missing or invalid parameters
401	`invalid_api_key`	authentication_error	API key is invalid, disabled, or deleted
402	`insufficient_credits`	billing_error	Credit balance too low, please top up
403	`ip_not_allowed`	permission_error	Request IP not in the key's allowlist
404	`model_not_found`	invalid_request_error	Model does not exist or is inactive
404	`task_not_found`	invalid_request_error	Task ID does not exist
429	`rate_limit_exceeded`	rate_limit_error	Too many requests, please slow down
429	`spend_limit_exceeded`	billing_error	Key spend limit reached (hourly/daily/total)
500	`internal_error`	api_error	Unexpected server error
503	`upstream_error`	upstream_error	Upstream AI provider returned an error

Common Scenarios

invalid_request (400)

Returned when required fields are missing or invalid.

{
  "error": {
    "code": "invalid_request",
    "message": "'model' is required.",
    "type": "invalid_request_error"
  }
}

insufficient_credits (402)

Your balance is too low. Check your balance with GET /v1/credits and top up in Dashboard > Billing.

invalid_api_key (401)

Possible causes:

The key does not start with sk-
The key has been disabled or deleted
The user account has been banned

upstream_error (503)

The upstream AI provider returned an error. This may happen when:

The input contains sensitive or prohibited content
The provider is temporarily unavailable
The request parameters are not supported by the provider

Credits are automatically refunded when a task fails due to upstream errors.