Implementation:Openai Openai python Response Input Image Param

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

Overview

Concrete TypedDict parameter type for supplying an image input to the model provided by the openai-python SDK.

Description

ResponseInputImageParam is a TypedDict used to construct image input items for the Responses API. Both detail (image resolution: "low", "high", or "auto") and type ("input_image") are required fields. The image can be referenced by file_id (an uploaded file) or by image_url (a fully qualified URL or base64-encoded data URL). Unlike ResponseInputImageContentParam, both detail and type are required in this variant. Learn more about image inputs.

Usage

Import this type when constructing standalone image input parameters for the Responses API where detail level must be explicitly specified.

Code Reference

Source Location

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

Signature

class ResponseInputImageParam(TypedDict, total=False):
    """An image input to the model."""

    detail: Required[Literal["low", "high", "auto"]]
    type: Required[Literal["input_image"]]
    file_id: Optional[str]
    image_url: Optional[str]

Import

from openai.types.responses import ResponseInputImageParam

I/O Contract

Fields

Name	Type	Required	Description
detail	Literal["low", "high", "auto"]	Yes	The detail level of the image. One of high, low, or auto. Defaults to auto.
type	Literal["input_image"]	Yes	The type of the input item. Always input_image.
file_id	Optional[str]	No	The ID of the file to be sent to the model.
image_url	Optional[str]	No	The URL of the image to be sent to the model. A fully qualified URL or base64-encoded data URL.

Usage Examples

import base64
import openai

client = openai.OpenAI()

# Using a URL
image_param = {
    "type": "input_image",
    "detail": "high",
    "image_url": "https://example.com/photo.jpg",
}

# Using base64-encoded data
with open("photo.png", "rb") as f:
    b64 = base64.b64encode(f.read()).decode("utf-8")

image_param_b64 = {
    "type": "input_image",
    "detail": "auto",
    "image_url": f"data:image/png;base64,{b64}",
}

response = client.responses.create(
    model="gpt-4o",
    input=[
        {
            "role": "user",
            "content": [
                image_param,
                {"type": "input_text", "text": "What is in this image?"},
            ],
        }
    ],
)
print(response.output_text)

Related Pages

• Environment:Openai_Openai_python_Python_3_9_Plus