GPT Image 1.5

OpenAI GPT Image 1.5 image generation model. Generate and edit images with enhanced speed and precision.

GPT Image 1.5 is OpenAI’s latest image generation model built on the GPT-5 architecture, available through AnyFast API. It is 4x faster and 20% cheaper than GPT Image 1, with improved text rendering and editing precision.

Key capabilities

• Text-to-Image — Generate images from natural language descriptions
• Image editing — Edit existing images with precise instructions
• Enhanced text — Dense text, small lettering, infographics, and UI mockups
• World knowledge — Context-aware generation with built-in reasoning
• Transparent background — Generate images with transparent backgrounds
• Batch generation — Generate up to 4 images per request

Output specifications

Property	Value
Sizes	1024x1024, 1536x1024, 1024x1536, auto
Quality	low, medium, high
Formats	png, webp, jpeg
Background	transparent, opaque

Quick example

cURL

curl https://www.anyfast.ai/v1/images/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-1.5",
    "prompt": "A cute cat wearing a space suit floating in the galaxy",
    "size": "1024x1024",
    "quality": "high"
  }'

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://www.anyfast.ai/v1"
)

response = client.images.generate(
    model="gpt-image-1.5",
    prompt="A cute cat wearing a space suit floating in the galaxy",
    size="1024x1024",
    quality="high"
)

print(response.data[0].b64_json[:100])

Parameters

Parameter	Type	Required	Description
model	string	Yes	Must be gpt-image-1.5
prompt	string	Yes	Text description of the desired image
n	integer	No	Number of images to generate (1–4). Default: 1
size	string	No	1024x1024, 1536x1024, 1024x1536, auto. Default: auto
quality	string	No	low, medium, high. Default: medium
output_format	string	No	png, webp, jpeg. Default: png
background	string	No	transparent or opaque. Default: opaque
moderation	string	No	auto or low. Default: auto
output_compression	integer	No	Compression level for jpeg/webp (0–100).

API Reference

View the interactive API playground for GPT Image 1.5.