OpenAI
GPT Image 2.5
gpt-image-2.5-sunburst
OpenAI's two-tier image generation and editing models: Flare focuses on speed, Sunburst pursues precision, covering both text-to-image and multi-turn image refinement
Try gpt-image-2.5-sunburst
Input
Showcases
View all showcasesOutput
imagePricing
gpt-image-2.5-sunburst per image
| Specifications | Unit Price |
|---|---|
| low | $0.0172 |
| medium | $0.0672 |
| high | $0.1829 |
| xhigh | $0.3572 |
| max | $0.7143 |
| auto | $0.3572 |
Positioning Overview
gpt-image-2.5-sunburst is the precision-oriented variant in OpenAI's gpt-image-2.5 image family. It supports both text-to-image generation and image editing and can be called through the unified HiAPI.ai interface. It improves on lighting and material rendering, reference subject consistency, and adherence to complex visual instructions, and it supports output at sizes up to 3840px as well as transparent backgrounds. It is suited to creative design work that demands high detail fidelity, brand asset production, and image workflows that require repeated refinement.
Key Highlights
- Precision-focused detail reproduction — trades longer single-generation times for finer detail and material rendering, making it suitable for tasks with high final-image quality requirements.
- Subject consistency across multi-round editing — when repeatedly modifying based on a reference image, the reference subject and layout are easier to keep consistent, reducing rework on each round.
- High resolution and transparent background — size options go up to 3840px, and transparent background output is available, reducing post-processing matting and compositing costs.
Capability Description
Text-to-image and image editing on the same variant: the same variant can generate images directly from prompts or accept reference images for editing, compositing, or preserving style and subject, with no need to switch models.
Multi-image reference input: up to 16 reference images can be passed in at once for multi-asset compositing or for preserving subject and style across images, suitable for scenarios that need to combine multiple visual elements.
Selectable aspect ratio and pixel dimensions: supports ratios such as 1:1 and 16:9 as well as pixel dimensions at the 2048 and 3840 levels, or the model can decide automatically, making it easy to align with landing pages and asset slots.
Quality and output format control: quality can be set from low to max across multiple levels, affecting detail, speed, and billing tier; output supports png, jpeg, and webp, with automatic or transparent background options.
Complex layouts and long prompts: prompts support up to 20000 characters, allowing longer visual instructions and layout descriptions, suitable for more structurally complex images and infographic needs.
Applicable Scenarios
- Brand and marketing design teams: fine creative drafts — input design requirements and reference images to produce high-resolution brand visual assets for official websites, presentation decks, and advertising materials.
- Design workflows: repeated refinement based on existing images — pass in original images and change instructions, iterating round by round while keeping subject and layout consistent, and produce deliverable final drafts for design review.
- E-commerce and product pages: multi-element composite imagery — use multiple product images and scene references as input to composite hero images and produce product display images ready to list.
- Asset production: transparent-background elements — generate graphic elements with transparent backgrounds from prompts, producing assets that can be overlaid directly onto pages or posters.
Limitations and Selection Advice
sunburst targets precision, so a single request takes longer and is not suitable for low-latency or high-concurrency batch image generation; high-resolution output further increases computation and waiting time. Scenes containing large amounts of small text or complex legends remain high-difficulty scenarios and should be manually reviewed. If you need a balance of speed and quality or large-batch image generation, consider the flare variant in the same family. Use of all generated content is subject to OpenAI's usage policy constraints; the model is closed-source and does not support local deployment or self-tuning.
Create a generation task
https://api.hiapi.ai/v1/tasks Headers
AuthorizationstringRequiredAccount API key. Required on every request. Example: Bearer YOUR_HIAPI_API_KEY. Get your API key
Content-TypestringOptionalThe request body is always parsed as JSON; when sent, only application/json (optionally with charset) is accepted — any other value returns 415. Example: application/json.
Idempotency-KeystringOptionalIdempotency key, up to 255 bytes. Retries with the same key from the same account create the task only once; replays return the original taskId.
On network timeouts or client retries, the same key creates the task only once — no double charges (scope: the API key's account). Use a business-unique identifier as the key (e.g. "order-42"); replays return the original taskId, and keys expire 24 hours after the first request. See the Unified Async API overview for the full scenario matrix.
Body
modelstringRequiredCurrent fixed value: gpt-image-2.5-sunburst
routestringOptionalCurrent fixed value: pro
inputobjectRequired
Business parameters for gpt-image-2.5-sunburst and route pro — see the parameter table below.
promptstringRequiredminLength 1maxLength 20000Prompt used to describe the image to be generated, or to specify the modifications to be made to the reference image; string type, maximum 20000 characters.
qualitystringOptionalDefault: "medium"Quality level, which determines output detail, generation speed, and price; string type, default medium.
lowmediumhighxhighmaxautobackgroundstringOptionalDefault: "auto"Background mode, used to select automatic, transparent, or opaque background; string type, default auto.
autotransparentopaqueimage_urlsarrayOptionalminItems 1maxItems 16Array of reference images, where each element is an image address; when provided, they are used for editing, compositing, or preserving the subject and style; if not provided, the operation is pure text-to-image.
Array [ string ]
aspect_ratiostringOptionalDefault: "1:1"Output canvas or pixel dimensions; string type, default 1:1; when set to auto, the model decides based on the request.
1:13:22:34:33:416:99:16autoShow all (10)
1024x10241536x10241024x15361536x11521152x15362048x20482048x11521152x20483840x21602160x3840output_formatstringOptionalDefault: "webp"Output image format; string type, default webp.
pngjpegwebpcallbackobjectOptional
Terminal-state notification config. When omitted, no callback is delivered — poll the task yourself. See the callback note below.
Provide callback.url when creating a task and HiAPI POSTs to your service once the task reaches a terminal state — no polling needed. The callback payload mirrors the task detail structure; signature verification, delivery retries and idempotency are documented on the Unified Async API overview page.
urlstringRequiredRequired when callback is present. A POST is sent to this URL once the task reaches a terminal state; must be a valid http(s) URL.
whenstringOptionalDefault: "final"Only final is supported today — notified on both success and fail.
finalstoragestringOptionalDefault: "temp"Artifact storage tier: temp (default, retained about 7 days) or persistent (long-term, billed by size). Insufficient balance or exceeding the storage cap silently downgrades to temp; the effective tier is shown in the task detail response.
temppersistentRequest examples
# Submit an async task; returns a taskId immediately (no waiting for generation)
curl -X POST "https://api.hiapi.ai/v1/tasks" \
-H "Authorization: Bearer $HIAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-image-2.5-sunburst@pro",
"input": {
"prompt": "…",
"quality": "medium",
"background": "auto",
"aspect_ratio": "1:1",
"output_format": "webp"
}
}' const res = await fetch("https://api.hiapi.ai/v1/tasks", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.HIAPI_API_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "gpt-image-2.5-sunburst@pro",
input: {
"prompt": "…",
"quality": "medium",
"background": "auto",
"aspect_ratio": "1:1",
"output_format": "webp"
}
}),
});
const task = await res.json();
// { code: 200, message: "success", data: { taskId } } import os, requests
res = requests.post(
"https://api.hiapi.ai/v1/tasks",
headers={"Authorization": f"Bearer {os.environ['HIAPI_API_KEY']}"},
json={
"model": "gpt-image-2.5-sunburst@pro",
"input": {
"prompt": "…",
"quality": "medium",
"background": "auto",
"aspect_ratio": "1:1",
"output_format": "webp"
}
},
)
print(res.json()) # { code, message, data: { taskId } } 200 OK
{
"code": 200,
"message": "success",
"data": {
"taskId": "tk-hiapi-01HZTQ8BX2N3GM3YFK4Z9D7VQR"
}
} 400 Bad Request
{
"code": 400,
"message": "invalid request",
"data": null,
"error_code": "INVALID_REQUEST"
} Get task detail
https://api.hiapi.ai/v1/tasks/:id Response fields
taskIdstringRequiredTask ID, always prefixed with tk-hiapi-.
modelstringRequiredResolved full model name. Tasks submitted with the route parameter return base@route (e.g. gpt-image-2/text-to-image@ext); otherwise identical to the name passed at creation.
routestringOptionalPresent only when the task was submitted with an explicit route parameter; echoes the submitted value.
statusstringRequiredTask status.
queued Queued, not started yet.
handling Being processed.
archiving Processing finished, artifacts being prepared.
success Terminal: completed, artifacts available (output returned).
fail Terminal: failed (error returned).
After submission, check status: success and fail are terminal, everything else is non-terminal. Poll every 1–3 seconds until terminal. On success, download artifacts from output[].url and transfer them before expireAt; pass storage: "persistent" at creation time when long-term retention is needed.
creatednumberRequiredTask creation time (Unix seconds).
completednumberRequiredUnix seconds when the task reached a terminal state; fixed to 0 while not terminal.
outputarrayOptional
Present only when status == success. Artifact list — always an array; a single task may return multiple types at once (e.g. video + first_frame).
Array [ object ]
Array items
urlstringRequiredArtifact URL, directly downloadable.
typestringRequiredCurrent possible values: video, image, audio, first_frame, last_frame, thumbnail; more may be added later.
expireAtnumberRequiredUnix seconds until which the artifact remains accessible; download or transfer before it expires.
errorobjectOptional
Present only when status == fail.
codestringRequiredBusiness error code.
messagestringRequiredError description.
Response examples
Success
{
"code": 200,
"message": "success",
"data": {
"taskId": "tk-hiapi-01HZTQ8BX2N3GM3YFK4Z9D7VQR",
"model": "happyhorse-1-0",
"status": "success",
"created": 1777282033,
"completed": 1777282099,
"output": [
{
"url": "https://cdn.hiapi.ai/tasks/.../video.mp4",
"type": "video",
"expireAt": 1777886899
}
]
}
} Processing (non-terminal)
{
"code": 200,
"message": "success",
"data": {
"taskId": "tk-hiapi-...",
"model": "happyhorse-1-0",
"status": "archiving",
"created": 1777282033,
"completed": 0
}
} Failed
{
"code": 200,
"message": "success",
"data": {
"taskId": "tk-hiapi-...",
"model": "happyhorse-1-0",
"status": "fail",
"created": 1777282033,
"completed": 1777282099,
"error": {
"code": "TASK_FAILED",
"message": "task failed"
}
}
} Articles
View all articles →Related Models
View all models →Same Type
-
Recraft V4.1 Recraft $0.010 /image -
Ideogram V4.5 Ideogram $0.011 /image -
Imagen 4 Google $0.030 /image -
Seedream 5.0 ByteDance $0.025 /image -
Grok Imagine Image 2.0 xAI $0.052 /image -
Wan 2.7 Image Alibaba $0.035 /image -
851 Labs Background Remover 851 Labs $0.002 /image -
Google Virtual Try-On Google $0.107 /image -
FLUX.1 Schnell Black Forest Labs $0.005 /image -
Nano Banana Pro Google $0.057 /image -
FLUX.2 Klein 9B Black Forest Labs $0.0086 /image -
Muse Image 1.0 Meta $0.015 per task











