Images 2.6 (GPT-Image-2.6 Sunburst and Flare)

OpenAI's Images 2.6 generates images 50% faster; API models Sunburst (quality) and Flare (layout) add SVG export and a complexity parameter.

OpenAI · Generative media (image, video, audio, music, voice/avatar generation) · model

Published in Feed

Overview

OpenAI introduced Images 2.6 on November 4, 2026, in ChatGPT and Codex across all subscription tiers, with two API models, GPT-Image-2.6 Sunburst and GPT-Image-2.6 Flare. OpenAI says generation is 50% faster than before, with Flare producing low-quality images in as little as six seconds. Sunburst targets higher quality and edit-to-edit consistency at medium or high quality, while Flare targets layout quality for posters and product imagery. The API adds image markup, SVG export and a complexity parameter that controls how much planning the model does.

This is a sourced directory entry. Features and capabilities are reported in the linked sources; this entry does not document independent Aymorphic testing.

Key features

  • Two API models: GPT-Image-2.6 Sunburst and GPT-Image-2.6 Flare
  • Generation 50% faster; Flare low-quality images in about six seconds
  • Animated GIF loops from characters, mascots or product shots
  • API additions: image markup, SVG export, complexity parameter
  • Available in ChatGPT and Codex on desktop, mobile and web across tiers

Use cases

  • Poster and product-image layouts with Flare
  • Multi-step image editing with consistent characters using Sunburst
  • Vector (SVG) assets and short GIF loops for marketing

Pricing

Per-image API prices are on OpenAI's developer pricing page (not stated in the announcement); included in ChatGPT subscription tiers.

Pricing reflects the source record and may change. Confirm current terms with the provider.

Dates and sources

Released
4 Nov 2026
Record updated
6 Nov 2026
Record last checked
6 Nov 2026

Explore the Feed

Other entries filed under generative media (image, video, audio, music, voice/avatar generation); inclusion does not imply equivalent features.

Browse the Feed