OpenAI API exposes GPT Image 1 through model ID gpt-image-1. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.
Last refreshed 2026-05-10. Next refresh: weekly.
Quick Start
- 1
- 2
- 3
Code Examples
Install
pip install openaiAPI key
OPENAI_API_KEYModel ID
gpt-image-1Use the model slug directly, e.g. "gpt-4o" or "gpt-4.1-mini".
import os
from openai import OpenAI
client = OpenAI() # reads OPENAI_API_KEY from env
response = client.chat.completions.create(
model="gpt-image-1",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Pricing on OpenAI API
| Type | Rate |
|---|---|
| 1024x1024 image | Low $0.011 / Medium $0.042 / High $0.167 |
| Portrait / landscape image | Low $0.016 / Medium $0.063 / High $0.250 |
Capabilities
VisionMultimodal
About GPT Image 1
GPT Image 1 is OpenAI's first publicly released autoregressive image generation model. Made available via the API on April 23, 2025 (ChatGPT launched it March 25, 2025 where it generated over 700 million images in the first week). Supports low, medium, and high quality tiers with per-image pricing at $0.011/$0.042/$0.167 for 1024×1024. Superseded by GPT Image 1.5 in December 2025.
Model Specs
Released2025-04-23
ArchitectureAutoregressive Image