Skip to Content
API CallImage Generationgpt-image-1.5

gpt-image-1.5 API

This document introduces the input and output parameters for calling the gpt-image-1.5 model API, providing you with a reference for understanding the meaning of the fields when using the interface.

Request Parameters

Request Body

Field NameTypeRequiredDefault ValueDescription
promptstringRequired-Prompt
modelstringRequired-The model name used for this request, which is gpt-image-1.5.
nintOptional1Number of images to generate, ranging from 1 to 4
sizestringOptional”1024x1024”Resolution. GPT-image-1.5 supports 1024x1024, 1024x1536, 1536x1024.
qualitystringOptional-Image quality, supporting low, medium, high; higher quality takes longer. Compared to version 1.0, generation speed is 4 times faster and costs are reduced by 20%.
output_formatstringOptional”png”Output image format, supporting png, jpeg, webp.
output_compressionintOptional100Image compression intensity, values ranging from 0 to 100; 0 means no compression, 100 means maximum compression.

Response Parameters

Field NameTypeDescription
createdintegerUnix timestamp (in seconds) for the creation time of this request.
dataarrayInformation about the output image, including the URL for image download or Base64. The gpt-image-1.5 model returns base64 data.
• When specifying the return format of the generated image as url, the corresponding parameter subfield is url;
• When specifying the return format of the generated image as b64_json, the corresponding parameter subfield is b64_json.
Note: Links will expire within 7 days after generation, please save the images promptly.
errorObjectError information object
error.codestringError code
error.messagestringError message
error.paramstringRequest id

Example

OPENAI Compatible Interface

POST https://api.umodelverse.ai/v1/images/generations

Synchronous Request

** curl **

curl --location 'https://api.umodelverse.ai/v1/images/generations' \
  --header "Authorization: Bearer $MODELVERSE_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "gpt-image-1.5",
    "prompt": "a beautiful flower",
    "size": "1024x1024",
    "quality": "high",
    "output_format": "png",
    "output_compression": 100
  }'

** python **

import os, base64
from openai import OpenAI
 
client = OpenAI(
    base_url="https://api.umodelverse.ai/v1",
    api_key=os.getenv("MODELVERSE_API_KEY", "YOUR_API_KEY")
)
 
res = client.images.generate(
    model="gpt-image-1.5",
    prompt="a beautiful flower",
    size="1024x1024",
    quality="high",
)
 
# gpt-image-1.5 returns base64 data
image_b64 = res.data[0].b64_json
raw = image_b64.split(",")[-1] if image_b64.startswith("data:") else image_b64
with open("image.png", "wb") as f:
    f.write(base64.b64decode(raw))
print("Saved to image.png")

Image Editing

POST https://api.umodelverse.ai/v1/images/edits

gpt-image-1.5 supports more precise partial editing capabilities, allowing modifications to specific areas while maintaining consistent composition, tone, and character appearance in other areas, thereby avoiding complete re-drawing.

Use multipart/form-data for parameters, including at least the image to be edited, image (optional mask), as well as model, prompt, and other fields; the rest of the parameters such as size, quality, output_format, output_compression are consistent with the generation interface.

** curl **

curl --location 'https://api.umodelverse.ai/v1/images/edits' \
  --header "Authorization: Bearer $MODELVERSE_API_KEY" \
  -F "image=@/path/to/your/image.png" \
  -F "mask=@/path/to/your/mask.png" \
  -F "model=gpt-image-1.5" \
  -F "prompt=Add a beach ball in the center" \
  -F "size=1024x1024" \
  -F "n=1" \
  -F "quality=high" \
  -F "output_format=png" \
  -F "output_compression=100"

** python **

import os, base64, requests
 
url = "https://api.umodelverse.ai/v1/images/edits"
headers = {"Authorization": f"Bearer {os.getenv('MODELVERSE_API_KEY', '$MODELVERSE_API_KEY')}"}
 
files = {
    "image": ("beach.png", open("beach.png", "rb"), "image/png"),
    # Optional: Provide a mask to limit the editing area
    # "mask": ("mask.png", open("mask.png", "rb"), "image/png"),
}
 
data = {
    "model": "gpt-image-1.5",
    "prompt": "Add a beach ball in the center",
    "size": "1024x1024",
    "n": "1",
    "quality": "high",
    "output_format": "png",
    "output_compression": "100",
}
 
r = requests.post(url, headers=headers, files=files, data=data)
r.raise_for_status()
resp = r.json()
 
image_b64 = resp["data"][0]["b64_json"]
raw = image_b64.split(",")[-1] if image_b64.startswith("data:") else image_b64
with open("edit.png", "wb") as f:
    f.write(base64.b64decode(raw))
print("Saved to edit.png")

Response

{
  "created": 1750667997,
  "data":
  [
    {
      "b64_json": "{image_base64_string}"
    }
  ],
  "usage":
  {
    "total_tokens": 4169,
    "input_tokens": 9,
    "output_tokens": 4160,
    "input_tokens_details":
    {
      "text_tokens": 9
    }
  }
}
{
  "error": {
    "message": "error_message",
    "type": "error_type",
    "param": "request_id",
    "code": "error_code"
  }
}
gpt-image-1OpenAI/Sora2-T2V