How does it differ from GPT Image 2.5 Flare?

Sunburst is built for edit precision and takes longer per image; Flare is built for speed and is what OpenAI calls the default for most applications. They are two separate OpenAI model ids, and on RouteMux both bill per image and both support 2K / 4K and editing. Use Sunburst for images that will be inspected closely or retouched repeatedly, Flare for batch work and anything where someone is waiting.

How are 2K / 4K images billed?

Per image, by resolution tier: standard, 2K and 4K each have one fixed price, listed in the pricing section. Nothing is billed per token, so prompt length and image content do not change what you pay.

Pass size 3840x2160 or 2160x3840, or the literal "4K". 2K works the same way: 2048x2048, 2560x1440, 1440x2560 or "2K". The endpoints and response shape stay the same; n must be 1, mask is not supported, and one image takes about 40 seconds to 4 minutes, longer at peak times.

Does image editing support 4K?

Yes. Pass size to /v1/images/edits, with up to 10 reference images; the standard and 2K tiers can edit too. Of the two 2.5 models, Sunburst is the one built for edit precision.

GPT Image 2.5 Sunburst

Save 70%Official

openai/gpt-image-2.5-sunburst

OpenAI GPT Image 2.5 Sunburst — the precision tier of the 2.5 family for demanding editing and creative work, billed per image.

Get an API key View code sample

Live model playground

Try GPT Image 2.5 Sunburst here

Tune the request, see the current price ceiling, and inspect the real response without leaving this model page.

asyncimage

1Configure input

Prompt

106 / 20,000

Source images for editing

Maximum estimated cost—

2Live resultExample

Input modalities: TextImage
Output modalities: Image
Capabilities: Image generation · Image editing
Upstream release: 2026-09-08
RouteMux name: openai/gpt-image-2.5-sunburst

What is GPT Image 2.5 Sunburst

GPT Image 2.5 Sunburst is one of the two image models OpenAI released on September 8, 2026 (snapshot gpt-image-2.5-sunburst-2026-09-08). OpenAI recommends Sunburst where editing precision matters most; it adds precision for detailed creative work at the cost of longer generation times. It holds fine detail and drifts less when you edit the same image several times in a row, which matters for posters, product shots and brand assets: the third edit should not quietly redraw what you were happy with.

The other model, GPT Image 2.5 Flare, is the faster default. They are separate model ids, so you choose by name. Compared with GPT Image 2, the 2.5 models add the xhigh and max quality settings. Billing is per image, not per token: each resolution tier has one fixed price per image, and prompt length, scene complexity and quality do not change it.

At the standard tier each call returns one image of about 1.5 megapixels (for example 1254×1254), and size only selects the aspect ratio; omitting size, auto, or any value outside the 2K / 4K sets all give the standard tier. For higher resolution, set size to 2K: 2048x2048 (1:1), 2560x1440 (16:9), 1440x2560 (9:16), or simply 2K; or 4K: 3840x2160 (16:9), 2160x3840 (9:16), or simply 4K. Measured outputs: 2K returns 2736×1536 at 16:9 and 2048×2048 at 1:1; 4K returns 3840×2160 at 16:9. Text-to-image and image-to-image both work at 2K / 4K, with up to 10 reference images for edits. These tiers need n set to 1, do not support mask, and take about 40 seconds to 4 minutes per image, longer at peak times.

In every tier it speaks the OpenAI Images protocol: /v1/images/generations and /v1/images/edits take the same request shape as OpenAI, the call is synchronous, and the image comes back as base64 in data[0].b64_json.

Before you choose

How does it differ from GPT Image 2.5 Flare?: Sunburst is built for edit precision and takes longer per image; Flare is built for speed and is what OpenAI calls the default for most applications. They are two separate OpenAI model ids, and on RouteMux both bill per image and both support 2K / 4K and editing. Use Sunburst for images that will be inspected closely or retouched repeatedly, Flare for batch work and anything where someone is waiting.
How are 2K / 4K images billed?: Per image, by resolution tier: standard, 2K and 4K each have one fixed price, listed in the pricing section. Nothing is billed per token, so prompt length and image content do not change what you pay.
How do I get 4K?: Pass size 3840x2160 or 2160x3840, or the literal "4K". 2K works the same way: 2048x2048, 2560x1440, 1440x2560 or "2K". The endpoints and response shape stay the same; n must be 1, mask is not supported, and one image takes about 40 seconds to 4 minutes, longer at peak times.
Does image editing support 4K?: Yes. Pass size to /v1/images/edits, with up to 10 reference images; the standard and 2K tiers can edit too. Of the two 2.5 models, Sunburst is the one built for edit precision.

GPT Image 2.5 Sunburst pricing: Standard, 2K and 4K per image

Billed per image, not per token: Standard $0.0186 per image, 2K $0.08 per image, and 4K $0.12 per image. 2K and 4K support both text-to-image and image editing — just pass the matching size.

Prices verified 2026-10-18 · Charged only when an image is returned

StandardSave 70%

$0.0186/ image

Official ~~$0.062~~

About 1.5 MP, e.g. 1254×1254; size sets the aspect ratio only

✓ Text-to-image✓ Image editing✓ About 15–30 s

2KNew

$0.08/ image

Measured 2048×2048 · 2736×1536 · 1536×2736

✓ Text-to-image✓ Image editing · up to 10 reference images✓ About 40 s – 4 min

4KNew

$0.12/ image

Measured 3840×2160 · 2160×3840

✓ Text-to-image✓ Image editing · up to 10 reference images✓ About 40 s – 4 min

Estimate by image

Resolution

Images

Estimated cost

$8.00

Failed requests are free

How to get 2K / 4K

# set size to any 2K / 4K value from the table
curl https://api.routemux.com/v1/images/generations \
  -H "Authorization: Bearer $ROUTEMUX_API_KEY" \
  -d '{"model":"openai/gpt-image-2.5-sunburst",
       "prompt":"...", "size":"3840x2160"}'
# returns data[0].b64_json (PNG), same shape as Standard

Billing details

Price depends only on resolution — not on prompt length or quality
2K / 4K return one image per request (n must be 1); mask is not supported
A size not listed in the table returns 400 and is not charged
Standard-tier image editing also charges a small amount for input-image tokens
You pay only when an image is returned — failures, timeouts and blocked requests are free

GPT Image 2.5 Sunburst price per image (USD, verified 2026-10-18)
Tier	Measured output size	size value	Price per image	Vs. list price
Standard	About 1.5 MP, e.g. 1254×1254	auto, 1024x1024, 1536x1024, 1024x1536	$0.0186/ image	Official ~~$0.062~~Save 70%
2K	2048×2048 / 2736×1536 / 1536×2736	2048x2048, 2560x1440, 1440x2560	$0.08/ image	List price is per token; no published per-image price
4K	3840×2160 / 2160×3840	3840x2160, 2160x3840	$0.12/ image	List price is per token; no published per-image price

Key capabilities

The precision tier: OpenAI recommends it where editing precision matters most; it takes longer per image than Flare.
Steadier across edits: Repeated edits to the same image are less likely to disturb the parts you did not ask to change.
2K / 4K output: Pick the tier with size. Text-to-image and edits both reach 2K and 4K; 4K at 16:9 measured 3840×2160.
Priced per image, per tier: Standard, 2K and 4K each have one per-image price, independent of prompt length, scene complexity or quality.

Limited time10% extra Credits on your first top-up — up to 200 bonus Credits

Applies to your first top-up within 72 hours of signing up. Minimum $20, once per account.

Interface and protocols

OpenAI Images

Use any of these IDs to call this model via the API.

RouteMux nameopenai/gpt-image-2.5-sunburst

Replace the ROUTEMUX_KEY placeholder with your API key. Create one →

from openai import OpenAI

client = OpenAI(
    base_url="https://api.routemux.com/v1",
    api_key="<ROUTEMUX_KEY>",
)

response = client.images.generate(
    model="openai/gpt-image-2.5-sunburst",
    prompt="A red panda coding under the moonlight",
    n=1,
)
print(response.data[0].url)

base_url: https://api.routemux.com/v1

Performance (last 30 days)

1,211 requests · last 30 days

Total usage5.94M

P50 first-token latency41.33s

Avg throughputInsufficient data (1211 requests)

Success rate100.0%

Uptime · 24htested via openai_images

100.00%

Success rate · 60d · from real requests

GPT Image 2.5 Sunburst FAQ

›What is GPT Image 2.5 Sunburst?

OpenAI GPT Image 2.5 Sunburst — the precision tier of the 2.5 family for demanding editing and creative work, billed per image.

›How much does the GPT Image 2.5 Sunburst API cost?

Through RouteMux, GPT Image 2.5 Sunburst is priced at $0.0186, below the official list price.

›How do I call GPT Image 2.5 Sunburst via API?

GPT Image 2.5 Sunburst is OpenAI-compatible: point your base URL at RouteMux and set the model field to openai/gpt-image-2.5-sunburst — no code changes needed.

›Which input and output modalities does GPT Image 2.5 Sunburst support?

GPT Image 2.5 Sunburst accepts text, image as input and produces image as output.

›When was GPT Image 2.5 Sunburst released?

GPT Image 2.5 Sunburst was released on September 8, 2026.

Sources

Reviewed by the RouteMux team on 2026-10-24

View as Markdown