AI-TokenHub

English

简体中文

English

简体中文

Appearance

Response

Streaming Response ​

Seedream-5.0-lite/4.5/4.0 supports streaming output mode. When you call the image generation API and set stream to true, the server will push events to the client in real-time through Server-Sent Events (SSE) during the response generation process. This section describes the types of events that the server will push.

image_generation.partial_succeeded ​

Returned when any image generation succeeds in streaming response mode.

Parameter Description ​

type string

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 when this request was created.

image_index integer

The sequence number of the image corresponding to this event in the image generation request. Starts from 0 and increments regardless of whether the image generation succeeds or fails, i.e., it automatically 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 the response_format field is configured as url in the request.

b64_json string

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

size string

The width and height pixel values of the image, in the format <width pixels>x<height pixels>, e.g., 2048x2048.

image_generation.partial_failed ​

Returned when any image generation fails in streaming response mode.

  • If the failure is due to review rejection: The next image generation task will continue, meaning it does not affect the generation process of other images in the same request.
  • If the failure is due to internal server error (500): The next image generation task will not continue.

Parameter Description ​

type string

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 when this request was created.

image_index integer

The sequence number of the image corresponding to this event in the image generation request. Starts from 0 and increments regardless of whether the image generation succeeds or fails, i.e., it automatically increments by 1 in both image_generation.partial_succeeded and image_generation.partial_failed events.

error object

The error cause corresponding to this event in the image generation request.

Properties

  • error.code string See Error Codes.
  • error.message string Error prompt information.

image_generation.completed ​

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

Parameter Description ​

type string

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 when this request was created.

tools array of object

The tools called by the model configured in this request.

Properties

  • tools.type string The type of tool configured to be called.
    • web_search: Web search tool.

usage object

Usage information for this request.

Properties

  • usage.generated_images integer The number of images successfully generated by the model, excluding failed images. Only successfully generated images are charged by the number of images.
  • usage.input_images integer (new, Seedream 5.0 pro only) The number of images input to the model.
  • usage.output_tokens integer The number of tokens consumed for image generation by the model. Calculation logic: sum(image width × image height)/256, then round to the nearest integer.
  • usage.total_tokens integer The total number of tokens consumed by this request. Currently, input tokens are not calculated, so it is the same as output_tokens.
  • usage.tool_usage object Usage information for tools used.
    • usage.tool_usage.web_search integer Number of web search tool calls. Only returned when web search is enabled.

error ​

The error information corresponding to the error that occurred in this request.

Parameter Description ​

error object

The error information returned for the error in this request.

Properties

  • error.code string See Error Codes.
  • error.message string Error prompt information.