Implementation:Openai Openai python Image Edit Completed Event

Knowledge Sources	Openai_Openai_python OpenAI API Reference
Domains	API_Types, Python
Last Updated	2026-02-15 00:00 GMT

Overview

Concrete tool for representing an image edit completion streaming event provided by the openai-python SDK.

Description

ImageEditCompletedEvent is a Pydantic BaseModel emitted when image editing has completed and the final image is available. It contains the b64_json base64-encoded final image data, along with metadata about the edit settings: background (transparent, opaque, or auto), output_format (png, webp, or jpeg), quality (low, medium, high, or auto), and size. The type field is always "image_edit.completed". A usage field provides token consumption details via nested Usage and UsageInputTokensDetails models.

Usage

Import ImageEditCompletedEvent when processing streaming events from the image edit API to detect when the final edited image is ready.

Code Reference

Source Location

• Repository: openai-python
• File: src/openai/types/image_edit_completed_event.py

Signature

class UsageInputTokensDetails(BaseModel):
    image_tokens: int
    text_tokens: int

class Usage(BaseModel):
    input_tokens: int
    input_tokens_details: UsageInputTokensDetails
    output_tokens: int
    total_tokens: int

class ImageEditCompletedEvent(BaseModel):
    b64_json: str
    background: Literal["transparent", "opaque", "auto"]
    created_at: int
    output_format: Literal["png", "webp", "jpeg"]
    quality: Literal["low", "medium", "high", "auto"]
    size: Literal["1024x1024", "1024x1536", "1536x1024", "auto"]
    type: Literal["image_edit.completed"]
    usage: Usage

Import

from openai.types import ImageEditCompletedEvent

I/O Contract

Fields (ImageEditCompletedEvent)

Name	Type	Required	Description
b64_json	str	Yes	Base64-encoded final edited image data, suitable for rendering as an image.
background	Literal["transparent", "opaque", "auto"]	Yes	The background setting for the edited image.
created_at	int	Yes	Unix timestamp when the event was created.
output_format	Literal["png", "webp", "jpeg"]	Yes	The output format for the edited image.
quality	Literal["low", "medium", "high", "auto"]	Yes	The quality setting for the edited image.
size	Literal["1024x1024", "1024x1536", "1536x1024", "auto"]	Yes	The size of the edited image.
type	Literal["image_edit.completed"]	Yes	The event type. Always "image_edit.completed".
usage	Usage	Yes	Token usage information for the image generation.

Fields (Usage)

Name	Type	Required	Description
input_tokens	int	Yes	Number of tokens (images and text) in the input prompt.
input_tokens_details	UsageInputTokensDetails	Yes	Detailed breakdown of input tokens.
output_tokens	int	Yes	Number of image tokens in the output image.
total_tokens	int	Yes	Total number of tokens used for the image generation.

Fields (UsageInputTokensDetails)

Name	Type	Required	Description
image_tokens	int	Yes	Number of image tokens in the input prompt.
text_tokens	int	Yes	Number of text tokens in the input prompt.

Usage Examples

from openai.types import ImageEditCompletedEvent
import base64

# When processing streaming events from image edit
def handle_event(event):
    if isinstance(event, ImageEditCompletedEvent):
        # Decode the final image
        image_data = base64.b64decode(event.b64_json)
        print(f"Image size: {event.size}")
        print(f"Quality: {event.quality}")
        print(f"Tokens used: {event.usage.total_tokens}")
        with open("edited.png", "wb") as f:
            f.write(image_data)

Related Pages

• Environment:Openai_Openai_python_Python_3_9_Plus