OpenAIOpenAI·🖌️ Inpainting·New

GPT Image 2.5 Flare

anonymized
Try on Venice.ai ↗
Quick reference
GPT Image 2.5 Flare — TLDR
  • 🎨 Editing variant of OpenAI's GPT Image 2.5 Flare, released September 2026.
  • 🔧 Mask-based inpainting and outpainting through the OpenAI Images edits endpoint.
  • 📝 Renders quoted prompt text literally when generating in-image copy.
  • ⚡ Flare tier is positioned for fast, high-quality everyday generation and editing.
  • 🎯 Sibling Sunburst is positioned for workflows where editing precision matters most.
  • 🆕 Successor to the GPT Image 2 and GPT Image 1.5 edit endpoints.
  • 🏢 Built and served by OpenAI; also selectable inside the Responses API image tool.
  • 🌐 Accepts one or more input images plus an optional mask.
💰 Pricing
$0.340
per edit
📅 On Venice since
Sep 8, 2026
1 day ago
Provider

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…

Read full profile →
36 models on Venice
21 text · 4 image · 4 video · 4 inpaint · 2 embedding · 1 asr
Since Jan 15, 2025

About this model

GPT Image 2.5 Flare (edit) is the image-editing configuration of OpenAI's GPT Image 2.5 Flare model, the companion to the text-to-image variant GPT Image 2.5 Flare. OpenAI's API documentation lists two GPT Image 2.5 models — Flare and Sunburst — and describes Flare as the choice for fast, high-quality everyday image generation, while Sunburst is recommended where editing precision matters most. Both can be called directly through the Image API or selected inside the image generation tool when using the Responses API.

Functionally, the edit path takes one or more source images, an optional mask, and a prompt: masked regions indicate the areas the model should regenerate, so the same endpoint covers inpainting and canvas extension. Text placed in quotes within the prompt is treated as literal copy to render, which is how in-image typography is specified.

Compared with its same-family predecessors GPT Image 2 and GPT Image 1.5, the 2.5 generation is a refresh of the same editing interface rather than a new API surface: applications built against the earlier edits endpoint largely carry over by swapping the model identifier. OpenAI has not published detailed benchmark tables comparing the generations.

For workflows where edit fidelity is the priority, the sibling GPT Image 2.5 Sunburst editing variant is the counterpart tier, alongside its generation-only form GPT Image 2.5 Sunburst.

This About section is AI-generated from public sources (Claude Opus 5), with no human editing. It may contain inaccuracies — verify critical details against the sources listed above.

Data sources: Venice API · HuggingFace · Wikipedia — enrichment updated 15h ago