# GPT Image 2.6 vs GPT Image 2.5: What Changes? > As of November 1, GPT Image 2.6 has no model ID. What OpenAI's spec says about 2.6 and markup, and our edit tests of 2.5 Sunburst vs Flare. - Canonical HTML: https://omniakey.com/blog/gpt-image-2-6-vs-gpt-image-2-5 - Markdown: https://omniakey.com/blog/gpt-image-2-6-vs-gpt-image-2-5.md - Published: 2026-11-01 (updated 2026-11-01) - Author: Kiki, COO at OmniaKey - Language: en - Category: Comparison - Reading time: 11 min - All posts: https://omniakey.com/blog/llms.txt --- GPT Image 2.6 is not out. As of November 1, 2026, OpenAI lists no gpt-image-2.6 model ID, price or changelog entry. The only official mention is in its API spec, which described a new edit field, markup, three times as "Supports GPT Image 2.5 and 2.6." On October 31, OpenAI cut 2.6 from two of the three; one still names it. What you can use today is GPT Image 2.5, in two versions: [Sunburst](https://omniakey.com/gpt-image-2-5-sunburst) and [Flare](https://omniakey.com/gpt-image-2-5-flare). **Short answer** - 2.6 is not released: no model ID, price or date. - The only change OpenAI ties to 2.6 is markup, a new edit field that the spec also lists for 2.5. OpenAI's image guide doesn't mention it yet. - In our 10 edits, Sunburst and Flare tied on recoloring and chalk text, and only Sunburst followed notes drawn on the photo, in 1 of 2 runs. - Use Sunburst for edits and Flare for everyday images at the same token price, and write edit instructions in the prompt, not only on the image. ## Is GPT Image 2.6 out? No. We checked OpenAI's official pages on November 1, 2026. - The [model list](https://developers.openai.com/api/docs/models) shows two image models, Sunburst and Flare, both 2.5, and the [full catalog](https://developers.openai.com/api/docs/models/all) links eight image pages, none of them 2.6. - The 2.6 model page address returns "Page not found". - The last image-model entry in the [changelog](https://developers.openai.com/api/docs/changelog) is the 2.5 launch on September 8, 2026, and nothing about images was added on October 28. - The [pricing page](https://developers.openai.com/api/docs/pricing#image-generation) has no 2.6 row. - The [API spec](https://raw.githubusercontent.com/openai/openai-openapi/main/openapi.yaml) lists 10 image model IDs, from `gpt-image-1.5` to `chatgpt-image-latest`, and none is `gpt-image-2.6`. ## Where does "GPT Image 2.6" come from? From one sentence in OpenAI's API spec, added on October 28 and partly removed on October 31. |Date (UTC)|What happened| |-|-| |Oct 28, 20:56|Spec commit adds markup; three descriptions say 2.5 and 2.6| |Oct 29, 17:01|Python SDK commit adds the field and the same text| |Oct 31, 00:26|openai-python v3.42.0 ships it| |Oct 31, 17:43|Spec commit cuts 2.6 from two of the three descriptions| The [October 28 commit](https://github.com/openai/openai-openapi/commit/aa880040fa7b23c8a7e3618b5ca757ecec71de95) added three descriptions of markup, each ending "Supports GPT Image 2.5 and 2.6. Cannot be combined with mask." The [October 31 commit](https://github.com/openai/openai-openapi/commit/c2aecc2fbe1ddff3e7500a0eaa5c2bc4c19c5318) changed two to "Supports GPT Image 2.5." and left the third. So the two request descriptions say 2.5 only, while the reusable markup schema in the same file still names 2.6. OpenAI has not said why. The Python SDK still carries the older wording: its [commit](https://github.com/openai/openai-python/commit/72c656df672989eed60c85bfafeb57f578fcc2ef) landed on October 29, v3.42.0 shipped on October 31 at 00:26 UTC, and the spec changed about 17 hours later. On October 29, 2026, WinCentral wrote, citing no source, that 2.6 will fix text, hands and object placement and that a launch looks imminent; OpenAI has not confirmed it, and its spec says nothing about image quality. ## What changes in 2.6, according to OpenAI? Only one thing: a new edit field called markup, which the spec lists for 2.5 as well. - A transparent PNG laid over the first image to guide the edit. - It must match that image's dimensions after orientation and contain transparent pixels. - It cannot be combined with mask. - It sits on `POST /v1/images/edits` only, as a multipart file or a JSON reference: file ID, HTTPS URL or base64 data URL. - The spec states no size cap, while a mask must be under 4 MB. The field appears zero times in OpenAI's [image generation guide](https://developers.openai.com/api/docs/guides/image-generation), changelog, the two 2.5 model pages and the pricing page, all checked November 1, 2026. OpenAI gives no example of a markup image and doesn't say how the model reads one, and the release date, price, speed, sizes and quality levels of 2.6 are all unpublished. ||GPT Image 2.5|GPT Image 2.6| |-|-|-| |Model IDs|Two: Sunburst, Flare|None yet| |Released|September 8, 2026|Not announced| |Model page|Yes|Not found| |Token prices|Published|Not published| |Quality levels|Low to max|Not published| |markup|Listed in the spec|One leftover line| 2.5's own launch is easier to pin down: the [September 8, 2026 changelog entry](https://developers.openai.com/api/docs/changelog) added the `xhigh` and `max` quality levels and kept GPT Image 2's token rates. For sizes and quality levels side by side, see [our GPT Image 2.5 vs GPT Image 2 comparison](https://omniakey.com/blog/gpt-image-2-5-vs-gpt-image-2). ## How do GPT Image 2.5 Sunburst and Flare edit today? Written instructions were followed in 6 of 6 edits, and notes drawn on the photo in 1 of 4. ### How we tested - Models: `gpt-image-2.5-flare` and `gpt-image-2.5-sunburst`, on their `2026-09-08` default snapshot, tested November 1, 2026. - Settings: the edit operation, `1536x1024`, `quality` medium, one image per request, the source as an inline Base64 JPEG at most 1024 px on the long side, since OmniaKey caps an edit request at 1 MiB. - The source photo came from [Nano Banana 2.1](https://omniakey.com/gemini-nano-banana-2-1), so neither model edits its own picture. For test 2 we drew red notes on a copy: a circle around the cookie jar with REMOVE, and ADD A RED APPLE with an arrow to the empty counter. - Runs: one per model in test 1 and two in tests 2 and 3, so 10 finished edits. One Flare request timed out at 186.7 s and was resent. - Time runs from sending the request to the status check that saw the image, polled every 4 seconds, so each figure can be up to about 4 s high. - We put every result next to the source at 2× zoom and checked pixel differences where no prompt touches. - OmniaKey sells API access to these models, so we ran the tests through it. Every price is OpenAI's own rate, not ours. OmniaKey has no markup field yet, so markup itself is untested. - Sources: OpenAI's Sunburst and Flare [model pages](https://developers.openai.com/api/docs/models/gpt-image-2.5-sunburst), the [changelog](https://developers.openai.com/api/docs/changelog), the [image guide](https://developers.openai.com/api/docs/guides/image-generation) and the [pricing page](https://developers.openai.com/api/docs/pricing), all checked November 1, 2026. Ten edits is a small sample: read each result as one example. ![A café counter with a white ceramic mug, a glass jar half full of chocolate-chip cookies and a fern in a terracotta pot, with a chalkboard reading FRESH BREAD on the wall behind](https://omniakey.com/_img/blog/gpt-image-2-6-vs-gpt-image-2-5/source.882b71a3.1600.webp) _The photo we edited, made with Nano Banana 2.1._ ### Test 1: Recolor one object (3:2) This test checks one clear color change and whether the rest of the frame survives. Prompt: > Change only the white mug on the left into a bright yellow ceramic mug. Keep everything else in the photo exactly the same: the cookie jar, the fern, the chalkboard and its text, the counter, the wall and the light. ![Two edits of the café counter photo side by side: a lemon-yellow mug from Flare on the left, a golden-yellow mug from Sunburst on the right](https://omniakey.com/_img/blog/gpt-image-2-6-vs-gpt-image-2-5/t1-compare.f7770fde.2400.webp) _Same prompt, Flare left and Sunburst right: both turned the mug yellow and kept the scene, Flare's yellow brighter, Sunburst's more golden._ ![Zoomed crops of the mug and the cookie jar: source photo and Flare on the top row, source photo and Sunburst on the bottom row](https://omniakey.com/_img/blog/gpt-image-2-6-vs-gpt-image-2-5/t1-detail.e0a876da.2072.webp) _Zoomed in: both mugs came back glossy and both sets of chocolate chips moved._ - **GPT Image 2.5 Flare** (20.7 s): a bright lemon-yellow mug, same shape, handle and position, but glossy where the original was matte. The jar, fern, chalk text, counter and wall stayed in place, while the chocolate chips on the cookies moved. - **GPT Image 2.5 Sunburst** (20.2 s): a deeper golden-yellow mug, also glossy, with a slightly thicker handle. The rest stayed in place, and the chips moved here too. **Verdict:** Tie. Flare's yellow is closer to the bright yellow we asked for and Sunburst's is more golden, and both redrew small details, so zoom in after an edit. ### Test 2: Follow notes drawn on the photo (3:2) This test checks whether the models read notes drawn on the image and clean up the marks. Prompt: > This photo has red hand-drawn notes on it. Do what the notes ask, then erase every red mark and every red word so the result looks like an untouched photo. Keep everything else in the photo exactly the same. ![The same café photo with red hand-drawn notes: a circle around the cookie jar with REMOVE above it, and ADD A RED APPLE with an arrow pointing to the empty end of the counter](https://omniakey.com/_img/blog/gpt-image-2-6-vs-gpt-image-2-5/source-marked.5d840e11.1600.webp) _The notes we drew on the photo: REMOVE around the jar, ADD A RED APPLE with an arrow to the empty counter._ ![Four edits of the café photo in a 2x2 grid: Flare run 1 top left, Sunburst run 1 top right, Flare run 2 bottom left, Sunburst run 2 bottom right](https://omniakey.com/_img/blog/gpt-image-2-6-vs-gpt-image-2-5/t2-compare.74641d8e.2072.webp) _All four edits erased the red marks; only Sunburst run 1 removed the jar and added the apple._ ![Zoomed crops: source photo and Sunburst run 1 at the cookie jar on the top row, the marked source photo and Sunburst run 1 at the arrow on the bottom row](https://omniakey.com/_img/blog/gpt-image-2-6-vs-gpt-image-2-5/t2-detail.33c5fcb4.2072.webp) _Sunburst run 1: the jar's spot is filled cleanly, the apple sits where the arrow pointed, and the fern was redrawn._ - **GPT Image 2.5 Flare** (22.2 s and 22.0 s): both runs erased the red circle, words and arrow completely, then stopped. The jar stayed and no apple appeared. - **GPT Image 2.5 Sunburst** (26.9 s and 22.2 s): run 1 removed the jar, filled the gap with clean wall and counter, and put a red apple with a stem and a natural shadow where the arrow pointed. It also redrew the fern denser and brought out the wall's plaster texture: on the wall, which no prompt touched, its average pixel difference from the source is 8.2 on a 0–255 scale, against 3.6–3.8 in the other three test-2 edits. Run 2 only erased the marks, like Flare. **Verdict:** Sunburst, narrowly: it did the whole job in 1 of 2 runs and Flare in 0 of 2, though both erased every red mark. Write the change in the prompt too. ### Test 3: Change chalk text (3:2) This test checks two lines of chalk handwriting: same words, same place, same size. Prompt: > Change the chalkboard text from FRESH BREAD to HOT SOUP, written in the same white chalk handwriting, at the same size and position, on two lines. Keep everything else in the photo exactly the same. ![Two edits of the chalkboard side by side: HOT SOUP in white chalk from Flare on the left, the same two lines from Sunburst on the right](https://omniakey.com/_img/blog/gpt-image-2-6-vs-gpt-image-2-5/t3-compare-r1.194f722f.2400.webp) _Both wrote HOT SOUP on two lines, same size and position._ ![Four zoomed crops of the chalkboard: Flare run 1 and Sunburst run 1 on the top row, Flare run 2 and Sunburst run 2 below](https://omniakey.com/_img/blog/gpt-image-2-6-vs-gpt-image-2-5/t3-detail.2937c92d.2072.webp) _All four are right; Flare run 2 left a faint erasure mark right of the P._ - **GPT Image 2.5 Flare** (22.3 s and 22.9 s): both runs wrote HOT and SOUP on two lines in white chalk at the original size and position, spelled right, with nothing extra. The letters are a little neater than the original handwriting, and run 2 left a faint erasure mark right of the P, where BREAD's D had been. - **GPT Image 2.5 Sunburst** (32.0 s and 22.2 s): the same two lines, spelled right, at the same size and position, with letters a little neater too and no erasure marks. **Verdict:** Tie, 4 of 4: both swap two lines of chalk text cleanly. ## Results, price and speed ||Sunburst|Flare| |-|-|-| |Recolor the mug (1 run)|Done|Done| |Drawn notes (2 runs)|1 of 2|0 of 2| |Chalk text (2 runs)|2 of 2|2 of 2| |Median time|22.2 s|22.2 s| |Token price|Same|Same| Test 1 was a tie on shades of yellow, Sunburst took test 2 by one run, and test 3 was a tie at 4 of 4. OpenAI's [pricing page](https://developers.openai.com/api/docs/pricing#image-generation), checked November 1, 2026, gives both the same rates. |Per 1M tokens|Sunburst|Flare| |-|-|-| |Image input|$8|$8| |Image output|$30|$30| |Cached image input|$2|$2| |Text input|$5|$5| |Cached text input|$1.25|$1.25| Batch halves the image rates, to $4, $15 and $1 per 1M tokens. The rates equal GPT Image 2's, while GPT Image 1.5's image output costs $32 per 1M tokens. The cached input rate applies only inside the Responses image tool, and direct `/v1/images/edits` calls pay the full $8 per 1M image input tokens. OpenAI publishes no per-image price for 2.5, and its model pages say the GPT Image 2 calculator doesn't estimate 2.5. Speed matched: both medians were 22.2 s, Flare between 20.7 s and 22.9 s and Sunburst between 20.2 s and 32.0 s. OpenAI calls Flare its fastest image model, but in our edits the two were level. One report shows a big gain over GPT Image 2: on Hacker News on September 8, 2026, jjcm wrote that about 50k GPT Image 2 images had averaged "around 104s", while with 2.5 "images are coming in at around 35-40s." ## Which should you use while you wait for 2.6? Use Sunburst for edits and Flare for everyday images, at the same token price. - **GPT Image 2.5 Sunburst** (Pick for edits): OpenAI's model for precise edits. Tied on recolor and chalk text, and the only one to follow notes drawn on the photo (1 of 2 runs). - **GPT Image 2.5 Flare** (Pick for everyday images): OpenAI's fastest image model, at the same token price. Tied on recolor and chalk text, but ignored the drawn notes in both runs. GPT Image 2.6 has no model ID yet, so there is nothing to switch to, and the one change OpenAI's spec names, markup, is a field on the same `/v1/images/edits` endpoint. |If you need|Do this| |-|-| |One clear change, such as a color or a word|Either model: all 6 such edits worked| |Remove or add an object|Sunburst, the only one to do it (1 of 2 runs); spell the change out in the prompt| |Edits from notes drawn on the image|Write the notes in the prompt too: alone they worked 1 of 4| |Fast everyday images|Flare| |markup once OpenAI explains it|Build edits on `/v1/images/edits`, where the field lives| For a same-prompt test against Google's model, see [how GPT Image 2.5 compares with Nano Banana 2.1](https://omniakey.com/blog/gpt-image-2-5-vs-nano-banana-2-1). ## How to call GPT Image 2.5 on OmniaKey Both 2.5 models are on OmniaKey for generating and editing. - `quality` takes `low`, `medium`, `high` or `auto`, while OpenAI's `xhigh` and `max` are left out. - An edit takes an inline Base64 image, and the whole request is capped at 1 MiB. - Several reference images go in `images`. - There is no mask or markup field yet. ```bash BASE64=$(base64 -i photo.jpg | tr -d '\n') curl --fail-with-body https://api.omniakey.com/v1/media/tasks \ -H "Authorization: Bearer your-omniakey-api-key" \ -H "Content-Type: application/json" \ -H "Idempotency-Key: mug-recolor-001" \ -d '{ "model": "gpt-image-2.5-sunburst", "type": "image", "operation": "edit", "input": { "prompt": "Change only the white mug into a bright yellow ceramic mug. Keep everything else the same.", "image": {"data": "'"$BASE64"'", "mime_type": "image/jpeg"} }, "parameters": {"size": "1536x1024", "quality": "medium"} }' ``` 1. The reply is `202` with a task ID. 2. Poll `GET /v1/media/tasks/{id}` until the status is `succeeded`. 3. Download the image from the signed URL in the task's `assets`. Swap the model to `gpt-image-2.5-flare` for Flare. Current rates are on the [Sunburst](https://omniakey.com/gpt-image-2-5-sunburst) and [Flare](https://omniakey.com/gpt-image-2-5-flare) model pages, every parameter is in the [image API docs](https://docs.omniakey.com/en/media/image), and you can try both in the [AI Image Generator](https://omniakey.com/ai-image-generator). ## Frequently asked questions ### Is GPT Image 2.6 released? No. The model list (checked November 1, 2026) shows two image models, Sunburst and Flare, from September 8, 2026. A 2.6 page returns "Page not found", and neither the changelog nor the pricing page lists a 2.6 entry. ### What is markup in the OpenAI image edit API? An optional field on `POST /v1/images/edits`: a transparent PNG laid over the first image to guide the edit. It must match that image's dimensions after orientation and contain transparent pixels, it cannot be combined with mask, and it can be sent as a multipart file or a JSON reference. ### Does markup work with GPT Image 2.5? On paper, yes: all three descriptions of the field in OpenAI's spec name 2.5, two of them 2.5 only, and openai-python has shipped the field since v3.42.0 on October 31, 2026. OpenAI's guide, changelog, model pages and pricing page don't mention it yet, and there is no official example. ### Is GPT Image 2.5 Sunburst better than Flare for editing? For one clear change they are level: both recolored the mug and got the two-line chalk text right every run. Sunburst followed our drawn notes in 1 of 2 runs, removing the jar and adding the apple, while Flare did not, and OpenAI positions Sunburst for editing precision. ### How much does GPT Image 2.5 cost? Both bill the same rates on OpenAI's pricing page (checked November 1, 2026): $8 per 1M image input tokens, $30 for image output, $2 for cached image input, $5 for text input and $1.25 for cached text input. Batch halves the image rates, and OpenAI publishes no per-image price. ## Sources checked - [Spec commit of October 28, 2026, adding markup and naming 2.6](https://github.com/openai/openai-openapi/commit/aa880040fa7b23c8a7e3618b5ca757ecec71de95) - [Spec commit of October 31, 2026, cutting 2.6 from two lines](https://github.com/openai/openai-openapi/commit/c2aecc2fbe1ddff3e7500a0eaa5c2bc4c19c5318) - [Spec file on main, with the leftover 2.6 line](https://raw.githubusercontent.com/openai/openai-openapi/main/openapi.yaml) - [openai-python commit of October 29, 2026, adding markup](https://github.com/openai/openai-python/commit/72c656df672989eed60c85bfafeb57f578fcc2ef) - [OpenAI model list](https://developers.openai.com/api/docs/models) - [OpenAI full catalog](https://developers.openai.com/api/docs/models/all) - [GPT Image 2.5 Sunburst model page](https://developers.openai.com/api/docs/models/gpt-image-2.5-sunburst) - [GPT Image 2.5 Flare model page](https://developers.openai.com/api/docs/models/gpt-image-2.5-flare) - [Changelog](https://developers.openai.com/api/docs/changelog) - [Image generation guide](https://developers.openai.com/api/docs/guides/image-generation) - [Pricing, image section](https://developers.openai.com/api/docs/pricing#image-generation) - [Hacker News comment by jjcm, September 8, 2026](https://news.ycombinator.com/item?id=49615865) Updated November 1, 2026. We will add GPT Image 2.6 when OpenAI lists its model ID, and markup when OpenAI documents it.