# GPT Image 2.6 Flare GPT Image 2.6 Flare is OpenAI's smaller image model, built for speed and released with GPT Image 2.6 Sunburst on 4 November 2026. In Sloosh it takes a prompt and up to 16 reference images, renders at 1K, 2K or 4K, and offers five quality levels up to max. It also makes animated GIFs and SVG files. Web page: https://sloosh.ai/models/gpt-image-2.6-flare [Use GPT Image 2.6 Flare](https://sloosh.ai/studio/image?image-model=gpt-image-2.6-flare) ## Key facts in Sloosh | | | | --- | --- | | Made by | OpenAI | | Makes | image | | Inputs | text, up to 16 reference images | | Resolution | 1K, 2K or 4K (default 1K) | | Aspect ratios | Auto, 1:1, 3:2, 2:3, 16:9, 9:16, 4:5, 5:4 (default Auto) | | Quality | low, medium, high, xhigh, max (default medium) | | Prompt limit | 32,000 characters | | GIF output | yes, 288 x 288 to 768 x 768, up to 16 frames (12 at 768 x 768), 20 ms to 2 s a frame | | SVG output | yes, from a prompt with no reference images | | Background | Auto, Opaque or Transparent | ## Best for - Work where speed matters most. OpenAI calls Flare "the smaller model for workflows where speed matters most" ([OpenAI image prompting guide](https://developers.openai.com/api/docs/guides/image-prompting)). - Trying many ideas before a final render. OpenAI suggests testing Flare with the same prompts, references and quality once Sunburst meets your needs ([OpenAI](https://developers.openai.com/api/docs/guides/image-prompting)). - Composites built from several references (a product, a model, a background), since Sloosh accepts up to 16 per generation. - Short looping GIFs for social posts, stickers and reactions. Describe the subject, the motion and the loop in the prompt ([OpenAI image generation guide](https://developers.openai.com/api/docs/guides/image-generation)). - Logos and icons as SVG, which you can scale or recolor by editing the paths ([OpenAI image prompting guide](https://developers.openai.com/api/docs/guides/image-prompting)). ## How to use GPT Image 2.6 Flare in Sloosh 1. Open [Image Studio with Flare selected](https://sloosh.ai/studio/image?image-model=gpt-image-2.6-flare), or pick GPT Image 2.6 Flare in the model chip. 2. Add references if you have them (up to 16): from the drawer, by pasting, or with Use as reference on an earlier result. 3. Write the prompt. Name each reference by number and job, for example "Image 1: product photo". 4. Set aspect ratio, resolution (1K, 2K or 4K) and quality (low to max). 5. For an animated GIF or a vector SVG, pick it under Format. 6. Check the cost on the Generate button, then generate. ## GPT Image 2.6 Flare prompting tips - Moving from GPT Image 2.5 Flare? OpenAI suggests trying 2.6 Flare first with the same work ([OpenAI](https://developers.openai.com/api/docs/guides/image-prompting)). - Compare against Sunburst with the same prompt, references and quality, so you can see what the extra speed costs ([OpenAI](https://developers.openai.com/api/docs/guides/image-prompting)). - For a GIF, describe the subject, the motion and how the loop ends. Nine frames at 200 ms each make a 1.8 second loop ([OpenAI](https://developers.openai.com/api/docs/guides/image-generation)). ## GPT Image 2.6 Flare example prompts **Prompt 1** ```text Image 1: a product photo of a ceramic mug. Place this exact mug on a linen tablecloth by a window with soft morning light. A small plate of biscuits sits behind it, slightly out of focus. Vertical image for a product page. Keep the mug's shape, glaze and handle exactly as in image 1. ``` **Prompt 2** ```text Change only the label text in image 1 from "DAILY GLOW" to "NIGHT REPAIR", same typeface, size and colour. Keep the jar, the lid, the lighting and the background of image 1 unchanged. ``` **Prompt 3** ```text Image 1 is the jacket. Image 2 is the model. Put the jacket from image 1 on the model in image 2, zipped halfway. Change only her top. Keep her face, hair, pose, the background and the light exactly as in image 2. ``` ## How it compares in Sloosh | Model | Resolution | Quality levels | References | Prompt | | --- | --- | --- | --- | --- | | GPT Image 2.6 Flare | 1K, 2K, 4K | low to max (5) | 16 | 32,000 | | [GPT Image 2.6 Sunburst](https://sloosh.ai/models/gpt-image-2.6-sunburst) | 1K, 2K, 4K | low to max (5) | 16 | 32,000 | | [GPT Image 2.5 Flare](https://sloosh.ai/models/gpt-image-2.5-flare) | 1K, 2K, 4K | low to max (5) | 16 | 32,000 | | [GPT Image 2](https://sloosh.ai/models/gpt-image-2) | 1K, 2K, 4K | low, medium, high | 16 | 32,000 | OpenAI calls Flare "the smaller model for workflows where speed matters most" and Sunburst the one for more detail or precise edits ([OpenAI](https://developers.openai.com/api/docs/guides/image-prompting)). ## Where else it runs - OpenAI API, model GPT Image 2.6 Flare, with image generation and image edit endpoints (OpenAI model page, accessed 2026-11-05). ## Frequently asked questions ### What is GPT Image 2.6 Flare? OpenAI's smaller image model, built for speed and released on 4 November 2026 ([OpenAI](https://developers.openai.com/api/docs/changelog)). In Sloosh it makes 1K, 2K or 4K images from a prompt and up to 16 references. ### What is GPT Image 2.6? OpenAI's image release of November 2026, in two API models: Sunburst for detail and Flare for speed. ### Sunburst or Flare: which should I use? OpenAI calls Flare the smaller model for speed and Sunburst the one for more detail or precise edits. Use Flare for fast rounds and [Sunburst](https://sloosh.ai/models/gpt-image-2.6-sunburst) when detail or an edit won't hold. ### How is GPT Image 2.6 Flare different from GPT Image 2? It came out in November 2026, seven months after [GPT Image 2](https://sloosh.ai/models/gpt-image-2). In Sloosh both take 16 references and render up to 4K, and Flare adds xhigh and max quality. ### Can I use GPT Image 2.6 Flare without an API key? Yes. In Sloosh you pick it in Image Studio; the exact price shows on the Generate button before you run it. ### Is GPT Image 2.6 better than 2.5? OpenAI's guide says to try 2.6 Flare first for work you ran on [2.5 Flare](https://sloosh.ai/models/gpt-image-2.5-flare). In Sloosh both have the same settings, so you can compare them on one prompt. ### Can GPT Image 2.6 make GIFs? Yes. Pick GIF under Format in Sloosh, then set the frame size, frame count and frame duration. A GIF can run up to 16 frames. ### Can GPT Image 2.6 make SVG files? Yes. Pick SVG under Format in Sloosh. It writes a static vector file you can scale and recolor. SVG works from a prompt only, so it isn't offered once a reference image is attached. ## Related - Models: [GPT Image 2.6 Sunburst](https://sloosh.ai/models/gpt-image-2.6-sunburst), [GPT Image 2.5 Flare](https://sloosh.ai/models/gpt-image-2.5-flare), [GPT Image 2](https://sloosh.ai/models/gpt-image-2), [Nano Banana Pro](https://sloosh.ai/models/gemini-3-pro-image-preview) - Spaces: [Label designer](https://sloosh.ai/spaces/label-designer), [Packaging mockup pack](https://sloosh.ai/spaces/packaging-mockup-pack) ## Sources - [OpenAI: GPT Image 2.6 Flare model page](https://developers.openai.com/api/docs/models/gpt-image-2.6-flare) - [OpenAI: API changelog](https://developers.openai.com/api/docs/changelog) - [OpenAI: Image prompting guide](https://developers.openai.com/api/docs/guides/image-prompting) - [OpenAI: Image generation guide](https://developers.openai.com/api/docs/guides/image-generation) - [OpenAI: Introducing Images 2.6](https://openai.com/index/introducing-images-2-6/)