Blog · 2026-11-05
GPT Image 2.6 vs GPT Image 2.5: New Outputs at Nearly the Same Price
Model pages: GPT Image 2.6 Flare API · GPT Image 2.6 Sunburst API · GPT Image 2.5 Flare API · GPT Image 2.5 Sunburst API — pricing, specs and the playground
GPT Image 2.6 is the model to call when the job needs animated GIF, SVG, markup-image or mask edits, or an exact pixel size; GPT Image 2.5 is the one to call when you need its xhigh or max quality levels or the lowest 2K price. On apimodels.app both charge plain images a fixed price per image by resolution and quality, starting at $0.01, so the choice is mostly about features.
Price separates them only at a few sizes. At 1K both cost $0.01 / $0.02 / $0.03 at low / medium / high, and at 4K medium and high they match too. 2.6 costs $0.03 / $0.035 / $0.045 at 2K against $0.02 / $0.03 / $0.04 on 2.5, and $0.03 at 4K low against $0.02. 2.6 is a new set of abilities rather than a sharper 2.5, and 2.5 keeps quality levels that 2.6 lacks.
GPT Image 2.6 vs GPT Image 2.5 at a glance
Tiers — Each generation has two tiers, Flare as the default and Sunburst for the highest fidelity. In 2.6 they take the same parameters and bill from the same price list, so cost follows what you ask for, not the tier. In 2.5 they share every cell at 1K and 2K, but at 4K Sunburst runs $0.02 / $0.085 / $0.16 / $0.28 / $0.47 from low to max against $0.02 / $0.045 / $0.08 / $0.17 / $0.3 on Flare.
Pricing — GPT Image 2.6 charges plain PNG, JPEG and WebP images at a set size a fixed price per image: 1K $0.01 / $0.02 / $0.03, 2K $0.03 / $0.035 / $0.045, and 4K $0.03 / $0.045 / $0.08 on Flare or $0.03 / $0.085 / $0.16 on Sunburst (low / medium / high). Animated GIF, masks, markup images, transparent backgrounds and edits that keep the source size are billed per token at 10% below OpenAI's official rates — image output $27 per 1M tokens, image input $7.20 (cached $1.80), text input $4.50 (cached $1.125) and text output $9 — and SVG is a flat $0.0315 per image. GPT Image 2.5 charges a fixed price per image from fifteen resolution × quality cells, $0.01 to $0.3 on Flare and $0.01 to $0.47 on Sunburst, with reference images and transparent backgrounds included.
Resolution and sizes — 2.6 accepts aspect_ratio with 1K, 2K or 4K, an exact WIDTHxHEIGHT (multiples of 16, longest edge up to 3840, ratio up to 3:1, 0.66 to 8.29 megapixels), a preset name or auto. 2.5 renders native 1K, 2K and 4K in six aspect ratios (1:1, 3:4, 4:3, 9:16, 16:9, 21:9) and bills by the pixel count of the returned image: 1.7MP or less is 1K, 1.7-4.6MP is 2K, above 4.6MP is 4K.
Quality — 2.6 offers low, medium, high or auto, plus a separate reasoning_effort (low, medium or high) that trades latency for detail; both 2.6 tiers default to medium on apimodels.app. 2.5 offers low, medium, high, xhigh and max as a price axis, defaulting to medium on Flare and high on Sunburst.
Inputs — 2.6 takes up to 16 reference images plus either a markup image or a mask, not both. 2.5 takes reference images, but a request carrying a mask returns 400, so local edits are steered through the prompt.
Output types — 2.6 returns PNG, JPEG or WebP with transparent backgrounds available, plus animated GIF and SVG, up to 10 images per call. 2.5 returns raster images, including native transparent PNG; GIF and SVG are not part of it.
Speed — In our 5 November 2026 tests, 2.6 took about 20 seconds at 1K low, about 27 seconds at 1K high, 13 to 25 seconds at 2K and 4K, and 22 to 58 seconds for a 1K low edit with one reference. Single 2.5 test calls took 37s at 1K low, 17s at 2K medium and 95s at 4K high on Flare, and 36s at 1K high, 17s at 2K high and 28s at 4K high on Sunburst, the last on a previous channel.
Limits — On 2.6, SVG is text-to-image only, GIF frames share one sheet of at most 3840 px on the longest edge, and results are kept for 30 days. On 2.5, sketch input, the creation templates and comment-on-image editing are ChatGPT features, not part of the API.
Per-image prices side by side
With 2.5 you can price a job before running it: pick a size and a quality, read the cell, multiply. A 2K medium banner is $0.03 on either tier and a 4K high poster is $0.08 on Flare or $0.16 on Sunburst. The tier is set by the pixel count of the image you get back, not by the parameter you sent, so a 2K image at 2720x1536 is 4.18MP and bills as 2K.
With 2.6 the price is assembled from tokens. Quality, size, GIF, every reference image and the prompt all change the count, so there is no fixed price per image. On apimodels.app an upper bound is held when the request is accepted and the unused part is released when the image is ready. Completed PNG, JPEG and WebP requests return a usage object whose charged field is what was deducted; GIF, markup or mask edits, SVG and failed tasks return none.
Since 6 November 2026, plain images on 2.6 have fixed per-image prices, so the per-request measurements from our 5 November tests no longer set what you pay. Side by side, 2.6 and 2.5 cost the same at 1K and at 4K medium and high; 2.6 costs $0.01 more at 2K low and 4K low and $0.005 more at 2K medium and 2K high. Requests that 2.6 still bills per token, such as an animated GIF or an edit that keeps the source size, depend on the tokens used.
What 2.6 adds that 2.5 does not have
The case for 2.6 is a set of abilities that 2.5 does not offer:
- Animated GIF: output_format gif, with frame_count from 2 to 16 (default 9) and frame_duration_ms from 20 to 2000 (default 200).
- SVG: output_format svg returns a static vector from a text prompt at a flat $0.0315, suited to icons, logos and flat illustrations.
- Markup-image edits: circles, arrows or notes drawn on a transparent PNG show the model what to change in the first reference.
- Masks: white marks the area to change, black the area to keep; 2.5 rejects any mask.
- Batch and effort controls: up to 10 images per call, up to 16 references, and reasoning_effort (low, medium or high).
Each comes with a constraint. GIF frames share one sheet of at most 3840 px on the longest edge; pass aspect_ratio with 1K, 2K or 4K, or no size, and apimodels.app shrinks the frames to fit, while with an exact size you keep it small yourself (the whole sheet must stay within 3840 px on the longest edge and 8,294,400 pixels in total). SVG is one image per request, quality has no effect on it, and the file holds no scripts, external resources or embedded raster. A markup image cannot be combined with a mask.
In our tests of the previous generation, masks behaved as hints rather than hard boundaries, which is why 2.5 returns 400 for them. We have not measured how strictly 2.6 respects a mask, so for a strict local edit also name the region in the prompt, for example "change only the label on the bottle, keep everything else unchanged".
Where 2.5 still holds its ground
The xhigh and max quality levels exist only on 2.5: 1K max is $0.08, 2K max is $0.15, and 4K max is $0.3 on Flare and $0.47 on Sunburst. 2.6 stops at high and offers reasoning_effort as a separate dial, so a workflow built on max quality has no direct equivalent there.
Local edits work without a mask. Name the object to change and say the rest stays; in our tests, "change only the red circle to blue, leave everything else unchanged" changed only the circle. Native transparent PNG, with background set to transparent and output_format to png, is verified at 1K, 2K and 4K at no extra charge.
Watch the defaults when you switch: 2.5 Sunburst renders at high unless told otherwise, while 2.6 Sunburst defaults to medium on apimodels.app, so pass quality explicitly.
What a job costs
Both sets of figures are fixed per-image prices for plain images at a set size, so they hold whatever the prompt; 2.6 GIF, mask and markup-image requests are billed per token and are not in this list.
- 100 social images at 1K low, 16:9: $1 on 2.6, $1 on 2.5.
- The same 100 at 1K high: $3 on either.
- 100 single-reference edits at 1K low with a set size: $1 on 2.6, $1 on 2.5, reference included.
- 100 category banners at 2K medium, 16:9: $3.50 on 2.6, $3 on 2.5; at 2K low, $3 against $2.
- A set of 10 SVG icons: $0.315 on 2.6; 2.5 has no SVG output.
2.6 has no measured GIF cost yet, and GIF is billed per token, so run a test call before budgeting animations. On either generation a request can fail through a moderation refusal or an upstream error, and failed requests are not charged.
Which one to use
Pick GPT Image 2.6 if the deliverable is a GIF or an SVG, if you want to point at the change with a markup image or a mask, or if you need an exact pixel size; at 1K the price is the same as 2.5, so new work at that size loses nothing by starting on 2.6. Use Flare for everyday volume and Sunburst when someone will zoom in; they cost the same at 1K and 2K and differ only at 4K.
Pick GPT Image 2.5 if you need the price before the call, if your volume sits at 2K, if you rely on xhigh or max quality, or if you render 4K and want a documented per-image price. Flare is the natural home for 4K volume, since Sunburst's 4K row is higher.
Do not move a working 2.5 pipeline at 2K just because 2.6 is newer: 2K medium is $0.035 on 2.6 against $0.03 on 2.5, and you gain nothing unless you need one of the new outputs or controls. If the job is turning an existing logo or photograph into a vector, neither fits: 2.6 makes SVG from a text prompt only and suits flat artwork rather than photographic scenes, and 2.5 has no SVG output.
Calling both with one key
All four models share one endpoint and one apimodels.app key; only the model value and the request fields change.
# GPT Image 2.6 Flare: animated GIF, 9 frames at 200 ms
curl https://api.apimodels.app/v1/images/generations \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "gpt-image-2.6-flare", "prompt": "A paper boat on small waves", "output_format": "gif", "frame_count": 9, "frame_duration_ms": 200, "size": "960x960"}'
# GPT Image 2.6 Sunburst: 2K, high quality, reasoning effort high
curl https://api.apimodels.app/v1/images/generations \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "gpt-image-2.6-sunburst", "prompt": "Wool coat with brass buttons", "aspect_ratio": "16:9", "size": "2K", "quality": "high", "reasoning_effort": "high"}'
# GPT Image 2.5 Flare: transparent PNG at 1K low ($0.01)
curl https://api.apimodels.app/v1/images/generations \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "gpt-image-2.5-flare", "prompt": "A ceramic mug, product shot", "aspect_ratio": "1:1", "size": "1K", "quality": "low", "background": "transparent", "output_format": "png"}'
# GPT Image 2.5 Sunburst: 4K high ($0.16)
curl https://api.apimodels.app/v1/images/generations \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "gpt-image-2.5-sunburst", "prompt": "Trade-show poster, engraved brass", "aspect_ratio": "16:9", "size": "4K", "quality": "high"}'
# Each call returns a taskId; poll it with
# GET https://api.apimodels.app/v1/images/generations?task_id=YOUR_TASK_IDFAQ
Is GPT Image 2.6 more expensive than GPT Image 2.5?
A little, at some sizes. On apimodels.app both charge plain images a fixed price per image by resolution and quality. They cost the same at 1K ($0.01 / $0.02 / $0.03 at low / medium / high) and at 4K medium and high; 2.6 is higher at 2K ($0.03 / $0.035 / $0.045 against $0.02 / $0.03 / $0.04) and at 4K low ($0.03 against $0.02). GIF, mask and markup-image requests exist only on 2.6 and are billed per token.
Can GPT Image 2.5 make animated GIFs or SVG files?
No. Animated GIF (2 to 16 frames) and SVG vector output are new in GPT Image 2.6. On apimodels.app, set output_format to gif or svg on gpt-image-2.6-flare or gpt-image-2.6-sunburst; SVG is text-to-image only, one image per request, at a flat $0.0315.
Does GPT Image 2.5 support mask edits?
No. On apimodels.app a 2.5 request carrying a mask returns 400, because none of the upstream channels we tested treated a mask as a hard boundary. Keep 2.5 edits local through the prompt, or use 2.6, which accepts a mask or a markup image but not both; we have not yet measured how strictly 2.6 respects a mask.
Do GPT Image 2.6 Flare and Sunburst cost the same?
Yes. On apimodels.app both 2.6 tiers bill from one per-token price list: image output $27 per 1M tokens, image input $7.20, text input $4.50 and text output $9, 10% below OpenAI's official rates, with SVG at a flat $0.0315. The cost follows quality, size, format and references, not the tier. In 2.5 the tiers match at 1K and 2K, but Sunburst is priced higher at 4K.
How do I check what a GPT Image 2.6 request cost?
Completed PNG, JPEG and WebP requests on apimodels.app return a usage object in data.usage on the task query, and its usage.cost.charged field is what was actually deducted. Each request is rounded up to $0.0001, and an upper bound is held at submission with the unused part released when the image is ready. GIF, markup or mask edits, SVG and failed tasks return no usage.