GPT Image 2.5 Sunburst is available through EvoLink's unified API for image generation and precise editing. Use reference images and masks to create product visuals, replace backgrounds, or refine selected details. API model ID: gpt-image-2.5-sunburst.
Test GPT Image 2.5 Sunburst output quality, estimate the token cost of one request, and generate a sample before you formally integrate.
Create image task
Fixed to gpt-image-2.5-sunburstImage generation and editing. Final charges follow actual token usage.
Reference images add input tokens to the request.
Pixel budget for the chosen ratio: 1K about 1.05 MP, 2K about 4.19 MP, 4K is 8.29 MP.
Rendering effort across five tiers, low to max. It drives the output token count, so it is the single biggest cost lever.
Transparent output includes an alpha channel. This preview feature may produce inconsistent results.
Generate 1–10 images per request. The estimate scales with the image count.
Results are kept for 24 hours — download anything you want to keep.
Start from the cost of a single sample, pick a testing budget, then price your own case in the calculator. The raw token rates are at the bottom.
First Test Cost
GPT Image 2.5 Sunburst - 1K - 1:1 - Low - 1 imageOne Low-quality image, no reference images
About 1888 tests with $10 in credits.
For this estimate, use 1K, 1:1, Low quality and 1 image with the prompt “Cat”. Longer prompts and reference images add input cost; final charges follow actual usage.
GPT Image 2.5 Sunburst testing budget guide
Pick an amount based on how many tests you expect.Good for a first validation.
Good for prompt iteration.
Good before production integration.
Final charges are based on actual token usage.
Rates are per 1K tokens. The calculator estimates a full request; final charges follow actual usage.
gpt-image-2.5-sunburstNo fixed per-image price: cost depends on the prompt, size, quality, reference images and image count.
| Item | Rule | Rate | Billing |
|---|---|---|---|
| Image output tokens | Output token usage depends on image size and quality. | $0.027/1K tokens-10% 1.836 cr/1K tokens$0.030 official price | Output tokens |
| Image input tokens | Reference images and masks add image input tokens. | $0.0072/1K tokens-10% 0.4896 cr/1K tokens$0.0080 official price | Input tokens |
| Image cached input tokens | Charged when upstream usage reports cached image tokens. | $0.0018/1K tokens-10% 0.1224 cr/1K tokens$0.0020 official price | Input tokens |
| Text input tokens | Text tokens used by the prompt. | $0.0045/1K tokens-10% 0.306 cr/1K tokens$0.0050 official price | Input tokens |
| Text cached input tokens | Charged when upstream usage reports cached text tokens. | $0.0012/1K tokens-10% 0.0765 cr/1K tokens$0.0013 official price | Input tokens |
Final charges are based on actual token usage.
Use Sunburst through EvoLink to revise product photos, adjust campaign visuals, and refine selected drafts. Combine reference images, written instructions, and masks for edits where control over details matters.
GPT Image 2.5 Sunburst is the precision-focused variant in OpenAI’s GPT Image 2.5 family. Call gpt-image-2.5-sunburst through EvoLink’s unified API for reference-based generation, local corrections, and successive image revisions. Flare is the faster default for everyday work; Sunburst is positioned for workflows that prioritize editing control.
Best fit: Precise reference edits, multi-turn revisions, campaign and product imagery · Cost basis: Prompt, size, quality, and reference-image input · Output boundary: Custom sizes up to a 3840 px edge; large outputs are experimental
gpt-image-2.5-sunburstToken-billed official route with five quality tiers (low to max), 1K/2K/4K resolution, explicit pixel sizes, n up to 10, and an inpainting mask.
Use the EvoLink API for product integration and batch jobs, or call it from Codex, Claude, or Gemini for fast creative and development workflows. Both paths share the same EvoLink API key, balance, model routes, and task history.
Best for: product backends, batch jobs, automated workflows
Call EvoLink’s unified image API from your server and control the model ID, parameters, task queue, callbacks, and result storage.
Best for: creative and development tasks in Codex, Claude, and Gemini
Give the Agent your output goal, assets, and acceptance criteria. It can choose the route, assemble the request, track the task, and return the result without requiring you to hand-code every step.
This example shows the shortest runnable flow: create a task, save the returned task ID, then poll or wait for an HTTPS callback. Open the API tab for the complete parameter and response reference.
curl -X POST https://api.evolink.ai/v1/images/generations \
-H "Authorization: Bearer $EVOLINK_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-image-2.5-sunburst",
"prompt": "A colorful sunset over the ocean, painterly style",
"size": "1:1",
"resolution": "1K",
"quality": "medium",
"n": 1,
"callback_url": "https://your-domain.com/webhooks/image-task-completed"
}'
# Save the returned task ID, then query:
curl https://api.evolink.ai/v1/tasks/{task_id} \
-H "Authorization: Bearer $EVOLINK_API_KEY"Check every value against the parameter cards above: ranges, allowed options, asset counts, and file types must match the selected route.
Check the Authorization bearer token and confirm the available balance and task billing in the console.
Review likeness rights, brand assets, readable text, sensitive content, and input-asset compliance.
A GPT Image 2.5 Sunburst task that reaches a final failed state is not charged. Keep the task ID, inspect the final state, and identify whether the cause is validation, review, or execution before retrying.
callback_url must be a public HTTPS URL, not localhost or a private network address. Always keep the task ID as a polling fallback.
| Feature | GPT Image 2.5 Sunburst | Nano Banana | Seedream |
|---|---|---|---|
| Estimated cost (1K, 1:1, Medium) | ~$0.012 / image | Lower-cost options | Per-image tiers |
| Billing model | Token based | Per generated image | Per image by output tier |
| Output quality | Low / Medium / High / xHigh / Max x 1K / 2K / 4K | 1K / 2K / 4K by model | 1K / 1.5K / 2K |
| Reference input | Up to 16 images plus mask | Model dependent | Up to 10 images |
| Best for | Precise edits, reference fidelity, in-image text | High-quality image generation | Ads, product creative, image editing |
In ratio mode the resolution tier sets the pixel budget (1K is about 1.05 MP, 2K about 4.19 MP, 4K is 8.29 MP). In auto or custom-pixel mode resolution is ignored.
EvoLink accepts low, medium, high, xhigh, and max; the default is medium. Hold quality fixed for a paired model test, then change it only to address a specific failure. Use the lowest-cost tested configuration that passes your requirements.
Credits are charged against the token counts the upstream usage object reports, so a request is quoted before it runs and settled on the real numbers afterwards.
OpenAI positions Flare as the default and Sunburst for editing precision at longer generation times. Assign each production job a candidate now, then confirm with your workload evaluation.
xhigh and max consume more output tokens than high. Track first-pass rate, retries, latency, and total spend per usable output before promoting a tier.
The fields that shape output and cost on POST /v1/images/generations. Generation is asynchronous — poll the returned task ID or use a callback, and save results promptly since image links stay valid for 24 hours. Full schemas and code samples live in the API tab.
| Parameter | Type | What it does |
|---|---|---|
| model | string · required | 'gpt-image-2.5-sunburst' — the token-billed GPT Image 2.5 Sunburst route. Use 'gpt-image-2.5-flare' for the GPT Image 2.5 Flare variant on the same endpoint. |
| prompt | string · required | The text instruction. Prompt tokens are metered as text input on the token route. |
| size | string · default auto | 'auto', one of 15 aspect ratios such as 1:1 or 16:9, or explicit WxH pixels in multiples of 16. |
| resolution | string · 1K / 2K / 4K | Pixel budget for ratio mode; ignored when size is auto or explicit pixels. |
| quality | string · low / medium / high / xhigh / max | Default: medium. Choose an explicit tier for reproducible testing; higher quality does not guarantee an acceptable final image. |
| background | string · opaque / transparent | Alpha channel of the output. Defaults to opaque; transparent is in Preview and results may be unstable. |
| n | integer · 1–10 | Images per request; cost scales linearly with the count. |
| image_urls | array · up to 16 | Reference images for image-to-image and editing. Each one adds image input tokens. |
| mask_url | string · optional | Alpha-channel PNG whose pixel dimensions match the reference image; transparent areas are regenerated. |
| callback_url | string · optional | HTTPS webhook that receives the task result, as an alternative to polling. |
Text rendering is improved, but exact placement, clarity, and structured composition can still miss the prompt.
Custom sizes can reach a 3840 px edge, but outputs with more than 3,686,400 total pixels—the pixel count of 2560x1440—are currently experimental.
background: "transparent" is available, but still in Preview — results may be unstable.
OpenAI notes that complex prompts may take up to two minutes to process.
Use the existing pricing calculator and Playground to estimate your size, quality, prompt, and reference-image configuration. Actual charges depend on reported usage; an estimate is not a fixed quote.
Compare the reconciled batch bill with accepted final outputs, including retries and all editing steps. Track review and repair time separately to assess the delivery cost.
The existing pricing section shows EvoLink and OpenAI rates by token type. Check the current values for this variant, then use actual input and output usage to assess your workload.
Because the comparison is computed from live SKU prices rather than a marketing claim, you can verify it at the moment you integrate, and re-check it whenever your volume grows enough for the difference to matter.
gpt-image-2.5-sunburst and gpt-image-2.5-flare share the same endpoint, parameters and token rates. OpenAI positions Sunburst for workflows where editing precision matters most and Flare as the fast default for high-quality everyday generation, so switching between them is a model-ID change, not a vendor migration.
The same token rates do not mean the same bill: each variant spends output tokens differently per request, so compare the usage object from a real request before you standardise on one.
The same API key that calls gpt-image-2.5-sunburst also calls Seedance for video, Nano Banana 2 and Seedream for alternative image routes, and the LLM catalogue — one balance, one task history, one authentication path.
That matters for image work specifically because pipelines rarely end at a still: generate the key frame with GPT Image 2.5 Sunburst, animate it with Seedance, and fall back to another image model when a job fits it better — without maintaining separate provider accounts, keys, and billing records.
Every generation reports submitted, processing, completed, or failed, with error details in the response and the console. Failed tasks are not treated as successful billable generations, so a bad batch of jobs does not quietly become a bill.
For production systems this is the difference between "request sent" and "image delivered": poll the task, verify the final state, and reconcile spending against per-task records in the console when you need to explain a number.
Compare GPT Image generations under one EvoLink account and API key, then choose by output quality, latency, and cost.
GPT Image 2.5 Flare
The fast GPT Image 2.5 variant: OpenAI's default for high-quality everyday generation on the same endpoint and rates.
View API
GPT Image 2
The previous OpenAI image route with low/medium/high quality, 1K/2K/4K tiers and token billing; still documented and priced by OpenAI.
View API
GPT Image 1.5
Previous OpenAI image route with fixed 1024-class sizes, token billing, and settled production behaviour.
View APIGPT Image 2.5 Flare
The other GPT Image 2.5 model: OpenAI's default for everyday generation and rapid iteration, same endpoint and token rates.
View API
Nano Banana 2
Google image model for high-quality generation and flexible creative workflows.
View API
Nano Banana Pro
Premium Nano Banana route for higher-fidelity images and production-grade output.
View API
Seedream 5.0 Pro
BytePlus image route with 1K/1.5K/2K tiers, multi-reference editing, and layer decomposition.
View API
Grok Imagine Image 2.0
xAI image route where the number of input images picks the mode, with 1K/2K output and up to 10 images per request.
View APISix workloads, two task briefs, and a worksheet for measuring cost per accepted image.
The fast GPT Image 2.5 variant: OpenAI's default for high-quality everyday generation on the same endpoint and rates.
What OpenAI released on September 8, 2026 and what changed from GPT Image 2.
EvoLink's first-hand test of the anonymous mona-lisa-1 checkpoint and what the 2.5 release does and does not resolve.
GPT Image 2.5 Sunburst is one of the two API models OpenAI released with ChatGPT Images 2.5 on September 8, 2026, with model ID gpt-image-2.5-sunburst. We have not verified the variant used by individual ChatGPT or Codex requests. For reproducible API tests, select and record the exact model ID.
OpenAI positions Flare as the default for most applications, with higher quality than gpt-image-2 at lower latency, and Sunburst as the precision option for editing-heavy work such as campaign creative and product imagery, with longer generation times. Both share the same endpoints, quality tiers, and list prices. We have not verified the variant used by individual ChatGPT or Codex requests. For reproducible API tests, select and record the exact model ID.
It is billed by token. Image output tokens dominate the bill and scale with resolution and quality tier; image input tokens are added per reference image; text input tokens come from the prompt. The Playground estimates the selected combination before you submit, and the pricing calculator prices your own case.
The pricing section compares the current EvoLink rate with the OpenAI list price and shows any savings available at the time you check. Use the calculator for your exact size, quality, and reference-image combination instead of relying on a universal per-image claim.
With the Image API, choose gpt-image-2.5-sunburst directly for generation or editing. With the Responses API, choose a mainline model that supports the image_generation tool; the tool handles image-model selection for conversational or multi-step workflows. EvoLink provides its own unified route for direct model access.
Yes. Use the Playground to test output quality, estimate credits, and inspect the request JSON before wiring it into your product.
size picks the shape - auto, one of 15 aspect ratios, or explicit WxH pixels. resolution picks the pixel budget for ratio mode only, and is ignored when size is auto or explicit pixels.
Yes. Every image in image_urls adds image input tokens. A mask is reserved as one extra input image at quote time and settled against the real upstream usage.
Width and height must be multiples of 16, total pixels must fall between 655,360 and 8,294,400, no edge may exceed 3840 px, and the aspect ratio must stay between 1:3 and 3:1. Outputs with more than 3,686,400 total pixels—the pixel count of 2560x1440—are currently experimental.
Yes — n accepts 1 to 10 and the cost scales linearly.
mask_url takes a PNG with an alpha channel whose pixel dimensions match the reference image exactly. Transparent pixels mark the area to regenerate, opaque pixels are preserved. Sent without a reference image, the mask is dropped.
Check the task status and error details in the response or console. Failed tasks should not be treated as successful billable generations.
Complex prompts may take up to two minutes. Text placement, recurring-character consistency, and precise structured composition can still need iteration.
No. OpenAI's standard rates are identical for gpt-image-2 and both 2.5 models. Comparisons that show a 2x jump are measuring against gpt-image-2's batch rates, which have no 2.5 equivalent yet.
Both variants add xhigh and max above high. OpenAI also documents auto; EvoLink exposes five explicit tiers and defaults to medium. Include inputs, retries, and actual usage when measuring cost per accepted image.
No. As of September 8, 2026, gpt-image-2 remains listed and priced by OpenAI with no deprecation date, and it stays live on EvoLink.
Unconfirmed. OpenAI's launch materials do not mention the anonymous Arena labels. EvoLink's first-hand Arena record for mona-lisa-1 stays on its own page.