OpenAI image models
Flare and Sunburst, explained
OpenAI released GPT-Image-2.5 on 8 September 2026. The name covers two API models rather than one, and both are now in the ListenHub image tool.
Both models bill at the same rates, so the choice is about output rather than cost.
OpenAI’s models index describes it as “Fast, high-quality everyday image generation”, and the image generation guide says to choose Flare for exactly that. It is the default of the two.
The models index calls it “Our most capable model for image generation and editing”, and the guide says to choose Sunburst “for workflows where editing precision matters most”.
Both models publish a 2026-09-08 snapshot alongside the rolling alias. Pin the snapshot when output has to stay reproducible, and take the alias when you would rather inherit improvements.
2.5 is served from the same two image endpoints as GPT-Image-2, plus the Responses image tool. The additions below are what a working integration has to account for before it switches the model string.
Earlier GPT Image models stop at high. Both 2.5 models add xhigh and max on top, and both still default to auto. OpenAI states that earlier models do not support these two values, so shared code has to pick the setting per model rather than pass one through.
The background parameter takes opaque or transparent on both 2.5 models. Transparency needs a PNG or WebP output format, because a JPEG has no alpha channel for the setting to write into.
An edit request takes up to 16 input images and an optional mask, so a change can be scoped to part of the picture. Through the Responses image tool an edit can also chain off the previous response instead of restating the whole scene.
Per-token pricing is identical to GPT-Image-2. How many tokens an image consumes is a separate question: OpenAI states that the GPT-Image-2 calculator does not estimate GPT-Image-2.5 consumption, so the new quality tiers have no published cost per image.
Read off OpenAI’s model pages, API reference and pricing page. Rates are per million tokens. Neither model publishes a per-image price.
| Provider | OpenAI |
|---|---|
| Model IDs | gpt-image-2.5-flare · gpt-image-2.5-sunburst |
| Dated snapshots | Both publish a 2026-09-08 snapshot |
| Endpoints | Image generation and image edit, plus the Responses image tool |
| Quality | auto · low · medium · high · xhigh · max |
| Background | Opaque or transparent, with PNG or WebP output |
| Reference images | Up to 16 per edit request |
| Output size | Up to 3840px on the long edge |
| Aspect ratio | From 1:3 to 3:1 |
| Editing | Mask-based inpainting; edits can chain turns |
| Streaming | Up to 3 partial images before the final one |
| Text input | $5.00 per 1M tokens |
| Image input | $8.00 per 1M tokens |
| Image output | $30.00 per 1M tokens |
| Cost per image | Not published; the GPT-Image-2 calculator does not apply |
Both models are in the ListenHub image tool. Pick GPT-Image-2.5 Flare or GPT-Image-2.5 Sunburst from the model menu and generate at any supported resolution and aspect ratio.
Both models currently use the Stable channel. The tool shows an estimated credit cost for your settings before generation.
They bill identically, so it is not a price decision. Flare is OpenAI’s everyday choice and the one to start from; Sunburst is the one they position above it for generation and editing. Run the same prompt on both and keep the one you prefer.
GPT-Image-2 Stable remains available in the image tool.
Nano Banana Pro and Nano Banana 2 when the image has to contain readable text or look photographic. Seedream 5.0 Pro when you want to pin one spot on an image you already made and change just that.
It is OpenAI’s image generation and editing model, released on 8 September 2026. The API exposes it as two models rather than one: gpt-image-2.5-flare, which OpenAI’s models index describes as fast, high-quality everyday image generation, and gpt-image-2.5-sunburst, which it calls its most capable model for image generation and editing.
No. A request has to name either gpt-image-2.5-flare or gpt-image-2.5-sunburst, or one of their dated snapshots. A bare gpt-image-2.5 is not a valid model ID and will be rejected.
OpenAI’s image generation guide puts it as: choose Sunburst for workflows where editing precision matters most, and Flare for fast, high-quality everyday image generation. Both bill at the same rates, so the choice is about output rather than cost.
One thing is documented as exclusive: the xhigh and max quality settings, which OpenAI says earlier GPT Image models do not support. Transparent-background output, mask-based inpainting and edits of up to 16 input images are documented for the 2.5 models; the endpoints and the parameter list are otherwise the same as GPT-Image-2.
Per-token rates match GPT-Image-2 and are the same for both models: $5.00 per million text input tokens, $8.00 per million image input tokens and $30.00 per million image output tokens. There is no published price per image, and OpenAI notes that the GPT-Image-2 token calculator does not estimate GPT-Image-2.5 consumption, so cost at the new xhigh and max tiers has to be measured rather than looked up.
Up to 16 per edit request.
Yes. GPT-Image-2.5 Flare and GPT-Image-2.5 Sunburst Stable are available in the image tool’s model menu. The tool shows an estimated credit cost for your settings before generation.
Start with GPT-Image-2.5 Flare, and try Sunburst on the same prompt since they cost the same. Nano Banana Pro or Nano Banana 2 if the image contains text or has to look photographic. Seedream 5.0 Pro if you want to point at one spot in an image you already made and change just that.
Flare and Sunburst are both in the image tool, alongside GPT-Image-2, Nano Banana Pro, Nano Banana 2 and Seedream 5.0 Pro. The same prompt runs on any of them.
Open the image tool