OpenAIOpenAI·🖼️ Image Generation·New

GPT Image 2.5 Sunburst

anonymized
Try on Venice.ai ↗
Quick reference
GPT Image 2.5 Sunburst — TLDR
  • 🆕 OpenAI image generation and editing model, released September 2026.
  • 🎯 Positioned for workflows where editing precision matters most.
  • 👁️ Accepts both text and image inputs; generates and edits images.
  • 🔧 Quality settings: low, medium, high, xhigh, max, and auto.
  • 📏 Arbitrary output resolutions via width-by-height strings, e.g. 1536x864.
  • 🌐 Available in the Image API or as the Responses API image tool.
  • 🔒 Supports opaque and transparent backgrounds without preview caveats.
  • 🏢 Documented alongside the sibling GPT Image 2.5 Flare model.
💰 Pricing
$0.270 – $0.840
per image
📅 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 Sunburst is OpenAI's higher-precision entry in the GPT Image 2.5 generation, released in September 2026 alongside GPT Image 2.5 Flare. It generates and edits images from text and image inputs, and OpenAI's documentation recommends it specifically for workflows where editing precision matters most, while suggesting Flare as the default starting point for most applications. The editing-focused variant is catalogued separately as GPT Image 2.5 Sunburst Edit for inpainting, mirroring GPT Image 2.5 Flare Edit.

Compared with its predecessor GPT Image 2, the documented differences are largely in controls: the 2.5 models extend the quality ladder by adding xhigh and max settings on top of low, medium, high and auto, and transparent-background support is generally available rather than in preview as it is for GPT Image 2. Both generations support arbitrary output resolutions expressed as width-by-height strings.

Integration-wise, Sunburst can be selected directly as the model in the Image API, or specified in the image generation tool of the Responses API underneath a mainline text model such as GPT-6 Astra, enabling conversational, iteratively editable image sessions with an action parameter that forces generation or editing.

Earlier steps in this lineage available in the catalog include GPT Image 1.5 and its editing counterpart, which remain selectable model identifiers in OpenAI's image API reference. OpenAI notes that Sunburst's token rates match GPT Image 2, though the GPT Image 2 token calculator does not estimate 2.5 consumption.

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