OpenAI

GPT Image 2.5

gpt-image-2.5-sunburst/image-to-image

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

Route

default pro

gpt-image-2.5-flare/image-to-image gpt-image-2.5-flare/text-to-image gpt-image-2.5-sunburst/image-to-image gpt-image-2.5-sunburst/text-to-image

Try gpt-image-2.5-sunburst/image-to-image

Input

Showcases

View all showcases

Output

image

Fill in the parameters and run — results show up here.

Pricing

gpt-image-2.5-sunburst/image-to-image per image

Specifications	Unit Price
1K	$0.050
2K	$0.080
4K	$0.120

Positioning Overview

The gpt-image-2.5-sunburst image editing pipeline is designed for developers who need high-fidelity modifications and extensions to existing images. It accepts one to sixteen reference images along with an editing instruction, outputs images at 1K, 2K, or 4K resolution tiers, and supports specifying aspect ratios and transparent backgrounds, making it suitable for design refinement workflows that require subject consistency across multiple iterations. Sunburst trades longer processing time for detail restoration precision.

Key Highlights

Precision-oriented editing pipeline — The Sunburst variant trades a longer per-request processing time for more refined detail restoration, making it suitable for editing tasks that are sensitive to final output quality.
Up to sixteen reference images in a single input — A single request can submit one to sixteen source or reference images, making it easy to feed subject, style, and layout information to the model together.
Four resolution tiers and selectable aspect ratios — Output supports 1K, 2K, and 4K resolution tiers plus thirteen aspect ratios, directly matching final deliverable specs and reducing secondary cropping.
Transparent backgrounds available at 1K — Transparent background mode is limited to 1K resolution; generated transparent assets can go directly into downstream compositing workflows.

Capabilities

Multi-reference conditional editing: Submit one to sixteen JPEG, PNG, or WebP images via image_urls, together with an editing instruction of up to 20,000 characters, to rewrite, replace, and outpainter existing assets.

Resolution and aspect ratio control: resolution selects the 1K, 2K, or 4K output tier; aspect_ratio supports thirteen ratios from 1:1 to 21:9, with the default auto letting the model decide.

Transparent background generation: background can be set to transparent, opaque, or auto; transparent mode is only available at 1K resolution, making it easy to produce cutout-free assets directly.

Refined detail restoration: The Sunburst variant prioritizes detail fidelity, staying closer to reference images in texture, lighting, and layout structure, making it suitable for editing rounds with higher final-output requirements.

Use Cases

Design teams batch-revising existing brand assets — Submit brand visual drafts as reference images, replace copy and color schemes according to a unified instruction, and produce complete asset sets for campaign delivery.
E-commerce operations refining product and scene images — Use real product photos as input to generate finished images with swapped backgrounds or scenes, ready for product detail pages and ad creatives.
Creatives iterating on the same image over multiple rounds — Continuously feed the current result back as input with supplementary instructions, converging step by step to the final draft and producing directly deliverable design finals.
Asset production requiring transparent-background graphics — Generate 1K transparent-background images from reference images plus editing instructions, to be used as layer assets in downstream compositing and layout.

Limitations and Selection Advice

Sunburst prioritizes precision, and a single request takes longer, so it is not suitable for low-latency or high-concurrency image generation scenarios; 2K and 4K output further increase compute and wait costs; transparent backgrounds are limited to 1K. Layouts with dense small text or complex legends remain error-prone, so manual review after output is recommended. If you need local deployment, self-tuning, or offline inference, this closed-source model cannot meet those needs, and an alternative solution is required. When you need fast batch image generation, consider the Flare pipeline in the same family.

Create a generation task

POST https://api.hiapi.ai/v1/tasks

Headers

AuthorizationstringRequired

Account API key. Required on every request. Example: Bearer YOUR_HIAPI_API_KEY. Get your API key

Content-TypestringOptional

The 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-KeystringOptional

Idempotency key, up to 255 bytes. Retries with the same key from the same account create the task only once; replays return the original taskId.

Idempotency key

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

modelstringRequired

Current fixed value: gpt-image-2.5-sunburst/image-to-image

routestringOptional

Current fixed value: default

inputobjectRequired

Business parameters for gpt-image-2.5-sunburst/image-to-image and route default — see the parameter table below.

promptstringRequiredminLength 1maxLength 20000

Generation or editing instruction describing what to generate or modify based on the source image, provided as a string, up to 20,000 characters long.

backgroundstringOptional

Background mode, provided as a string; supported only at 1K resolution, omit this parameter for 2K/4K.

Options:transparentopaqueauto

image_urlsarrayRequiredminItems 1maxItems 16

Array of source or reference images, each in JPEG, PNG, or WebP format, with 1 to 16 images.

Array [ string ]

resolutionstringOptionalDefault: "1K"

Output resolution tier, provided as a string, defaults to 1K; when background is auto/opaque/transparent, only 1K is supported.

Options:1K2K4K

aspect_ratiostringOptionalDefault: "auto"

Output aspect ratio, provided as a string, defaults to auto; omitting it is likewise treated as auto.

Options:auto1:13:22:34:33:416:99:16

Show all (5)

21:927:1616:279:88:9

callbackobjectOptional

Terminal-state notification config. When omitted, no callback is delivered — poll the task yourself. See the callback note below.

Callbacks (Webhook)

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.

urlstringRequired

Required 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.

Options:final

storagestringOptionalDefault: "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.

Options:temppersistent

Request 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/image-to-image",
  "input": {
    "prompt": "…",
    "image_urls": "…",
    "resolution": "1K",
    "aspect_ratio": "auto"
  }
}'

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/image-to-image",
    input: {
      "prompt": "…",
      "image_urls": "…",
      "resolution": "1K",
      "aspect_ratio": "auto"
    }
  }),
});
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/image-to-image",
        "input": {
          "prompt": "…",
          "image_urls": "…",
          "resolution": "1K",
          "aspect_ratio": "auto"
        }
    },
)
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

GET https://api.hiapi.ai/v1/tasks/:id

Response fields

taskIdstringRequired

Task ID, always prefixed with tk-hiapi-.

modelstringRequired

Resolved 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.

routestringOptional

Present only when the task was submitted with an explicit route parameter; echoes the submitted value.

statusstringRequired

Task status.

Status values

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.

creatednumberRequired

Task creation time (Unix seconds).

completednumberRequired

Unix 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

urlstringRequired

Artifact URL, directly downloadable.

typestringRequired

Current possible values: video, image, audio, first_frame, last_frame, thumbnail; more may be added later.

expireAtnumberRequired

Unix seconds until which the artifact remains accessible; download or transfer before it expires.

errorobjectOptional

Present only when status == fail.

codestringRequired

Business error code.

messagestringRequired

Error 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"
    }
  }
}