- 🆕 OpenAI's November 2026 high-detail image generation and editing model
- 🎯 Positioned for detailed visual work; Flare targets fast iteration
- 👁️ Accepts text and image inputs, returns generated or edited images
- 🔧 Supports a complexity setting and markup-guided edits
- 📏 Can output SVG vector graphics and animated GIFs
- 💬 Callable via Images API or the Responses API image tool
- 🔒 API organization verification may be required before use
- 🏢 Part of OpenAI's GPT Image line, alongside an edit-focused 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 33 more models by OpenAI →GPT Image 2.6 Sunburst is OpenAI's quality-oriented image model in the GPT Image 2.6 generation, released alongside GPT Image 2.6 Flare and the editing-focused GPT Image 2.6 Sunburst Edit and GPT Image 2.6 Flare Edit entries. According to OpenAI's API documentation, the model generates and edits images from text and image inputs and is intended for detailed compositions and image editing workflows, while Flare is described as the option for fast iteration.
Compared with its direct predecessor GPT Image 2.5 Sunburst and its paired editing variant GPT Image 2.5 Sunburst Edit, the 2.6 release adds several documented controls: a complexity setting, markup-guided edits (where annotations drawn on an image steer the change), SVG output, and animated GIF output. These are described in OpenAI's image generation guide as capabilities of the 2.6 line rather than retrofits to 2.5.
Within the broader family, the lineage runs from GPT Image 2 and GPT Image 1.5 through the 2.5 split into Sunburst and GPT Image 2.5 Flare, with 2.6 continuing that two-track structure of a detail-focused and a speed-focused model.
In practice, Sunburst can be called directly through the images endpoints or selected as the model for the image generation tool when using a mainline text model such as GPT-6 Astra via the Responses API; OpenAI notes that organization verification may be required before GPT Image models can be used. No independently verified benchmark scores for this model were available at the time of writing.
This About section is AI-generated from public sources via VeniceStats + Venice inference, with no human editing. It may contain inaccuracies.
| Seller | Health | Rep↓ | Sales | Images | Routing | $ / img | Save |
|---|---|---|---|---|---|---|---|
| Venice.ai Proxy 0x1f22…18c9 | healthy | 86.84 | — | — | #1 | $0.0055 | −94% |
| ▲ Apex Ant 0x73b4…e736 | — | 81.71 | — | — | #2 | $0.045 | −50% |
"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 = buyer trust score (0-100, the Antseed SDK's own formula). "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.