GPT Image (formerly DALL-E)

AI ImageOpenAI - est. 2021

OpenAI's image generation models in ChatGPT, Codex and the API, successors to DALL-E 3

4.4 / 5Free plan availableVerified review
Try GPT Image (formerly DALL-E) Free →

Start free, upgrade anytime

Reviewed Nov 2026

Editorial take

DALL-E 3 was retired in 2026 and replaced by OpenAI's GPT Image models, now on the Images 2.6 release with Sunburst and Flare tiers. Image generation inside ChatGPT remains the lowest-friction path to AI images for existing ChatGPT users. For professional-grade aesthetics, Midjourney still leads.

What is GPT Image (formerly DALL-E)?

DALL-E 3 has been retired: OpenAI removed dall-e-2 and dall-e-3 from the API on May 12, 2026 and retired the DALL-E GPT in ChatGPT on August 30, 2026. Image generation in ChatGPT, Codex and the API now runs on OpenAI's GPT Image models. The current release, Images 2.6 (November 4, 2026), comes in two tiers: GPT-Image-2.6 Sunburst for detailed compositions and GPT-Image-2.6 Flare for fast iteration. Both accept text and image inputs, edit images, and add a complexity setting, markup-guided edits, SVG output and animated GIF output. API use is billed per token, and the older gpt-image-1-mini and gpt-image-1.5 models leave the API on December 1, 2026.

Best for

ChatGPT users who want image generation and editing without a separate tool

Key strength

Best ChatGPT and OpenAI ecosystem integration

Output Quality4.8Integration4.0Value3.5Ease of Use4.5Free Tier3.5

Score breakdown (out of 5)

What you would use it for

  • →Generating images directly inside ChatGPT conversations without switching tools
  • →Illustrating blog posts and social media content quickly from a text description
  • →Creating concept mockups without detailed prompt engineering
  • →Generating variations on an existing image concept
  • →Producing visual content for presentations and marketing materials fast

Pros & Cons

👍 Pros

  • ✓Follows prompts more accurately than most competing image generators
  • ✓Included with ChatGPT Plus subscription
  • ✓Generates realistic human faces
  • ✓Developer-friendly API

👎 Cons

  • ✗Prioritizes literal interpretation over artistic expression
  • ✗Strict content moderation
  • ✗Limited fine-tuning options
  • ✗Output tends toward corporate and stock photography aesthetics

Key Features

  • ✓ High prompt adherence
  • ✓ Image editing and inpainting from text and image inputs
  • ✓ Markup-guided edits
  • ✓ SVG and animated GIF output (Images 2.6)
  • ✓ Complexity setting to trade detail for speed
  • ✓ Two API tiers: Sunburst for detail, Flare for speed
  • ✓ Built into ChatGPT and Codex

Available on

Web (via ChatGPT)ChatGPT mobile and desktop appsCodexOpenAI API

Integrates with

ChatGPT (built-in)CodexOpenAI API (images endpoints)ZapierMake

GPT Image (formerly DALL-E) Pricing

✅ GPT Image (formerly DALL-E) has a free plan - no credit card required to start.

ChatGPT Free

$0
  • ✓Image generation in ChatGPT with daily limits
Start Free →
Most Popular

ChatGPT Go

$8/mo/monthly
  • ✓More image generation than Free
Get ChatGPT Go →

ChatGPT Plus

$20/mo/monthly
  • ✓Higher image generation limits
Get ChatGPT Plus →

API (GPT-Image-2.6)

Pay-per-use/usage
  • ✓Text input $5.00/1M tokens ($1.25 cached)
  • ✓Image input $8.00/1M tokens ($2.00 cached)
  • ✓Image output $30.00/1M tokens
  • ✓Same rates for Sunburst and Flare
  • ✓No Batch API support
Get API (GPT-Image-2.6) →

GPT Image (formerly DALL-E) vs Competitors

Best GPT Image (formerly DALL-E) alternatives →Best AI Image Generation tools →

From the blog

Developer resources

Related Tools

AI Image4.8

Midjourney consistently produces the most aesthetically refined AI images of any tool in this category. Its outputs have a distinctive visual quality that distinguishes them from DALL-E or Stable Diffusion. The web app is now the main interface and Discord remains available. The prompting style takes some practice, but the community gallery and fast iteration loop help new users learn it.

From $10/mo|Re-verified Oct 2026
AI Writing4.7

ChatGPT is the most capable all-in-one AI assistant available. Its combination of image generation, voice mode, code execution, web browsing, and a large custom GPT ecosystem makes it the default choice for users who want one tool that handles everything. The tradeoff is that it is rarely the deepest tool on any single task.

Free + paid plans|Re-verified Nov 2026
AI Image4.3

Leonardo AI is the best-value image generation platform for creators who need both generation quality and fine-grained control. Fine-tuning custom models on your own reference images, a generous free tier, and a strong community of shared models make it more flexible than Midjourney at a lower cost.

Free + paid plans|Re-verified Oct 2026
AI Image4.2

Ideogram is the strongest AI image generation tool for typography accuracy. Legible text rendered inside generated images addresses the biggest weakness of Midjourney and DALL-E. For marketing materials, posters, and anything requiring readable text within an image, Ideogram is the practical choice.

Free + paid plans|Re-verified Oct 2026

This page contains affiliate links. We may earn a commission at no extra cost to you. Learn more.