- 🖼️ Editing variant of OpenAI's GPT Image 1.5 line.
- ✏️ Mask-based inpainting and outpainting via natural-language edits.
- 🔤 Text rendering described in OpenAI's model documentation.
- 🎯 OpenAI cites better instruction following and prompt adherence.
- 🧩 Accepts one or more reference images as edit input.
- 🔧 Served through OpenAI's images edit endpoint with optional masks.
- 📅 Edit variant released January 2026; succeeded by GPT Image 2.
- 🏢 Built and hosted by OpenAI.
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 1.5 (edit) is the image-editing counterpart of OpenAI's GPT Image 1.5 generation model, GPT Image 1.5. Rather than producing images from text alone, this variant modifies existing images: you supply a source image, an optional mask, and a prompt describing the change, and the model applies inpainting or outpainting while preserving the unmasked regions. OpenAI's model documentation covers both text rendering and editing through this line.
On OpenAI's own model documentation, GPT Image 1.5 is described as offering better instruction following and adherence to prompts than the earlier GPT Image generation, and it supports both creating and editing images through natural-language instructions. The editing workflow accepts one or more reference images as input.
Within the same family, GPT Image 1.5's editing model was later succeeded by GPT Image 2, OpenAI's newer image system that likewise supports masked inpainting and outpainting with emphasis on prompt adherence and typography. For teams already standardized on GPT Image 1.5, this edit endpoint remains a practical option for prompt-guided image revision.
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 |
|---|---|---|---|---|---|
| ▲ Apex Ant 0x73b4…e736 | 91.03 | #1 | $0.10 | image,media | 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.