OpenAI

GPT Image 1

Name: OpenAI GPT Image 1
Author: OpenAI

Try It Compare

Model ID:gpt-image-1

2025-04-23

Try It Compare

GPT Image 1 is OpenAI's first natively multimodal image model, originally released in March 2025 as part of GPT-4o. Unlike the DALL-E series that relied on diffusion-based generation, it uses an autoregressive architecture that enables both text-to-image creation and image-to-image transformation within a single unified model. It marked a significant leap in text rendering accuracy, photorealism, and contextual prompt understanding, and went viral upon release for its ability to generate Studio Ghibli-style imagery.

OpenAI PlusOpenAI ProAPI|Vision|Proprietary Model

Knowledge Cutoff

Unknown

The date this AI finished learning. It may not know about things that happened after this date.

Input → Output Format

The types of content this AI can receive, and what it can produce in return.

Context Memory

N/A

The maximum amount of text the AI can read and process in a single request. A larger number means it can handle longer documents or conversations.

API Cost

$0.011 ~ $0.25/ img

The cost when using without a subscription plan. Pricing may vary by quality, resolution, or generation mode.

Calculate Cost

Source:Official Docs OpenRouter

AI Performance Evaluation

Arena Image Score

1115

±3

As of 2026-04-23

Overall Rank

No.27

265,541 Votes

Arena by Image Category

Art

1115±6No.25

Cartoon

1115±5No.25

Photorealistic

1115±4No.30

Portraits

1115±5No.31

Text Rendering

1115±5No.29

3D Modeling

1115±6No.27

Commercial Design

1115±4No.29

Source:Arena Intelligence

OpenAI