- 🆕 OpenAI's text-to-image and editing model, released April 2026.
- 👁️ Generates and edits images from text and image inputs.
- 🔧 Supports high input fidelity for image-based editing.
- 📏 Offers flexible output image sizes.
- 🏢 Available through the OpenAI API.
- 🎯 Newest entry in OpenAI's GPT Image family.
- 💬 Pairs with a dedicated edit endpoint variant.
OpenAI is an American artificial intelligence research organization headquartered in San Francisco, structured as both a for-profit public benefit corporation and a nonprofit foundation. The lab developed the GPT family of large language models, the DALL-E image generation…
Explore 27 more models by OpenAI →GPT Image 2 is OpenAI's image generation and editing model, available through the OpenAI API. It produces images from text prompts and accepts image inputs for editing, supporting flexible output sizes and high-fidelity image inputs. A companion editing-focused variant, GPT Image 2 Edit, handles inpainting-style tasks through the API's image edit endpoint.
It is the newest member of OpenAI's GPT Image family, following its same-family predecessor GPT Image 1.5. Both models share the same core text-to-image and image-editing workflow exposed through the OpenAI API, with GPT Image 2 documented as supporting high input fidelity for editing tasks.
GPT Image 2 sits within a broad April 2026 OpenAI lineup that also includes text models such as GPT-5.5 and GPT-5.5 Pro. No independent benchmark figures from top evaluators were available at the time of writing, so the description here reflects OpenAI's own API documentation.
This About section is AI-generated from public sources via VeniceStats + Venice inference, with no human editing. It may contain inaccuracies.
| Seller | Reputation↓ | Routing | $ / img | Categories | API |
|---|---|---|---|---|---|
| Venice.ai Proxy 0x1f22…18c9 | 100.00 | #2 | $0.13 | image,creative | openai-images |
| ▲ Apex Ant 0x73b4…e736 | 91.01 | #1 | $0.09 | image,media | openai-images |
| D5V1N2 0xd5e7…7be0 | 33.17 | gated | $0.3125 | image,creative,router,fallback | openai-images |
"Best price" and the seller table are live AntSeed catalog data (advertised $/1M tokens — or $ per generated image for unit-billed image models — not settled amounts). Reputation = on-chain trust (0-100). "Routing" = the SDK's default buyer routing (what the VPR desktop app ships with): a trust ≥ 60 gate on the effective reputation, then cheapest-first among routable sellers; live failover state (per-peer cooldowns) is buyer-side runtime and not included. Model knowledge (TLDR, provider, About) via the VeniceStats enrichment layer. Advertised catalog, not the model used in any specific purchase. "Usage on AntSeed" counts only settlements whose buyers share the per-model split on-chain (metadata v2/v3, opt-in), so every usage figure is a lower bound.