Streaming Response

SSE streaming response. The response type is text/event-stream.

image_generation.partial_succeeded

Currently only Seedream-5.0/4.5/4.0 support streaming response.

Returned when any image generation succeeds in streaming response mode.

type string

This should be image_generation.partial_succeeded.

model string

The model ID used for this request, in the format <model name>-<version>.

created integer

The Unix timestamp (seconds) of the creation time for this request.

image_index integer

The index of the image corresponding to this event in the current image generation request. Starting from 0, it increments by 1 regardless of whether the image generation succeeds or fails, i.e., it auto-increments by 1 in both image_generation.partial_succeeded and image_generation.partial_failed events.

url string

The download URL of the image corresponding to this event. Returned when response_format is set to url in the request.

b64_json string

The Base64 encoding of the image corresponding to this event. Returned when response_format is set to b64_json in the request.

size string

The pixel dimensions of the image, in the format <width>×<height>, e.g., 2048×2048.

Response Example

{
  "type": "image_generation.partial_succeeded",
  "model": "doubao-seedream-5-0-260128",
  "created": 1589478378,
  "image_index": 0,
  "url": "https://...",
  "size": "2048×2048"
}

image_generation.partial_failed

Currently only Seedream-5.0/4.5/4.0 support streaming response.

Returned when any image generation fails in streaming response mode.

• If the failure reason is content moderation rejection: It will continue to request the next image generation task, meaning it does not affect the generation flow of other images within the same request.
• If the failure reason is an internal service error (500): It will not continue to request the next image generation task.

type string

This should be image_generation.partial_failed.

model string

The model ID used for this request, in the format <model name>-<version>.

created integer

The Unix timestamp (seconds) of the creation time for this request.

image_index integer

The index of the image corresponding to this event in the current image generation request. Starting from 0, it increments by 1 regardless of whether the image generation succeeds or fails, i.e., it auto-increments by 1 in both image_generation.partial_succeeded and image_generation.partial_failed events.

error object

The error reason for this event in the current image generation request.

error. code string

Error code.

error. message string

Error message.

Response Example

{
  "type": "image_generation.partial_failed",
  "model": "doubao-seedream-5-0-260128",
  "created": 1589478378,
  "image_index": 2,
  "error": {
      "code":"OutputImageSensitiveContentDetected",
      "message":"The request failed because the output image may contain sensitive information."
  }
}

image_generation.completed

Currently only Seedream-5.0/4.5/4.0 support streaming response.

Returned after all images (whether successful or failed) in the request have been processed. This is the last response event of the streaming response.

type string

This should be image_generation.completed.

model string

The model ID used for this request, in the format <model name>-<version>.

created integer

The Unix timestamp (seconds) of the creation time for this request.

tools array of object

Configured model tools for this request.

tools. type string

The configured tool type.

• web_search: Web search tool.

usage object

Usage information for this request.

usage. generated_images integer

The number of successfully generated images. Images that failed to generate are not included. Billing is based on the number of successfully generated images.

usage. output_tokens integer

Number of tokens spent on the generated image. Calculation logic: sum(image_width * image_height) / 256, then rounded.

usage. total_tokens integer

Total number of tokens consumed for this request. Input tokens are not currently counted, so this matches the output_tokens value.

usage. tool_usage object

Usage information for tools used.

usage.tool_usage. web_search integer

The number of times the web search tool was called. Only returned when web search is enabled.

Response Example

{
  "type": "image_generation.completed",
  "model": "doubao-seedream-5-0-260128",
  "created": 1589478378,
  "tools": [
         {
             "type": "web_search",
         }
     ],
  "usage": {
      "generated_images": 2,
      "output_tokens": xx,
      "total_tokens": xx,
      "tool_usage":{
        "web_search":1
    }
  }
}

error

Error information for this request, if an error occurred.

error object

The error message returned for this request error.

error. code string

Error code.

error. message string

Error message.

Response Example

"error": {
  "code":"BadRequest",
  "message":"The request failed because it is missing one or multiple required parameters. Request ID: {id}"
}