OpenAI Image Cloud Image input

GPT Image-2

OpenAI's natively multimodal model with exceptional text rendering and photorealistic quality across diverse styles

$0.25

per image in the cloud

Overview

GPT Image-2 is OpenAI's second-generation GPT image model, the successor to GPT Image-1 and GPT Image-1.5. It follows long, detailed prompts closely, renders text reliably and handles photorealistic and illustrated styles alike. On Gen-Image it also accepts a source image for image-to-image editing.

Key Features

Reliable Text Rendering: Clean, legible text for posters, labels, packaging and UI mockups
Strong Prompt Adherence: Follows complex compositions and multi-part instructions faithfully
Multi-Style Versatility: Photorealism, illustration, anime, vector art and 3D renders from one model
Image-to-Image Editing: Restyle or modify one of your images while keeping its subject
Quality Levels: Choose low, medium or high quality depending on the draft or final render

Best For

Marketing visuals and branded content with text
Product shots and lifestyle imagery
Infographics, diagrams and educational visuals
UI/UX mockups and design exploration
Editing an existing image with a plain-language instruction

Prompt Tips

Describe the scene in natural language: subject, setting, lighting and style
Put any text that must appear in the image between quotation marks and say where it goes
With a source image, keep the prompt short and describe only what should change
Use low quality to iterate on a composition, then switch to a higher quality for the final image

Use it

Three ways to run GPT Image-2

Make an image with GPT Image-2 ("gpt-image-2"): a lighthouse on a cliff at dusk, cinematic light

curl https://imference.com/generate \
  -H "Authorization: Bearer $IMFERENCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-image-2",
       "format_code": "square",
       "prompt": "a lighthouse on a cliff at dusk, cinematic light"}'

Claude needs the MCP server. API details in the reference.

Specs