GPT Image 2.5 API: Official Forwarding and VIP Per-Call Routes

gpt-image-2.5-flare and gpt-image-2.5-sunburst are available through official API forwarding, using the same Images API integration as official-forward gpt-image-2. Choose Flare for speed or Sunburst for precise image editing, or expose both options in your app. Both use token billing at the same token rates as official-forward gpt-image-2. Two VIP per-call models are also available: gpt-image-2.5-flare-vip and gpt-image-2.5-sunburst-vip, each at $0.03/call, using the same integration as gpt-image-2-vip. Updated September 9, 2026. LaoZhang API availability and group guidance follow the service launch notice. Representative VIP generation parameters were tested on the same date. Official model positioning, snapshots, and rates are sourced below.

Choose your route

Route	Model ID	Token group	Billing
Official forwarding	`gpt-image-2.5-flare`	`Sora2Official` or the enterprise official-forward group	Same token rates as official-forward GPT Image 2
Official forwarding	`gpt-image-2.5-sunburst`	`Sora2Official` or the enterprise official-forward group	Same token rates as official-forward GPT Image 2
VIP per-call	`gpt-image-2.5-flare-vip`	Default	$0.03/call, same integration as `gpt-image-2-vip`
VIP per-call	`gpt-image-2.5-sunburst-vip`	Default	$0.03/call, same integration as `gpt-image-2-vip`
Web version 2.5	`gpt-image-2-web`	Default	Currently $0.03/call; check the console

Choose the route and billing type before copying a request. Existing GPT Image 2 integrations can refer to the GPT Image 2 guide.

GPT Image 2.5 official-forward models and groups

Request model ID	Current snapshot	When to choose it
`gpt-image-2.5-flare`	`gpt-image-2.5-flare-2026-09-08`	Faster everyday, high-quality generation
`gpt-image-2.5-sunburst`	`gpt-image-2.5-sunburst-2026-09-08`	Generation and editing where edit precision matters most

Use an undated alias for a typical integration, or the full dated ID to pin a snapshot. The current alias mapping may change in the future.

Select usage-based billing in token management and confirm that the token allows your target model.
Both 2.5 models require an official-forward group. Choose Sora2Official for regular official forwarding or the enterprise official-forward group (called image2Enterprise in the launch notice) when stability is the priority. Default continues to use gpt-image-2-web, which now runs the latest GPT web version, 2.5.
Keep your existing official-forward Images API authentication, request structure, and result handling. Change model to an alias or snapshot above; do not put a group name in model.

The public pricing catalog on September 9, 2026 lists sora_official and GPT_Image_2_Enterprise for both official-forward models and their snapshots. The enterprise display name is GPTImage2 Sora2 Enterprise. Confirm the corresponding official-forward option in token management; Default tokens require the -vip IDs for VIP calls; they cannot use the unsuffixed official-forward IDs.

Minimal GPT Image 2.5 official-forward integration

These examples use the existing official-forward endpoints: /v1/images/generations for generation and /v1/images/edits for editing. The SDK methods are images.generate and images.edit.

export LAOZHANG_API_KEY="sk-your-usage-billed-token"
export BASE_URL="https://api2.laozhang.ai/v1"

Generate with Flare

curl --fail-with-body "$BASE_URL/images/generations" \
  -H "Authorization: Bearer $LAOZHANG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2.5-flare",
    "prompt": "A product photo of a white ceramic mug on a gray desk in soft natural light",
    "size": "1024x1024",
    "quality": "medium"
  }' -o generation.json

Edit with Sunburst

Prepare a local source.png, then run:

curl --fail-with-body "$BASE_URL/images/edits" \
  -H "Authorization: Bearer $LAOZHANG_API_KEY" \
  -F "model=gpt-image-2.5-sunburst" \
  -F "image=@source.png" \
  -F "prompt=Keep the mug shape, composition, and lighting. Change only the mug body to dark blue." \
  -F "size=1024x1024" \
  -F "quality=medium" \
  -o edit.json

Both models accept text and image inputs. These examples reflect their respective strengths; Flare can also edit, and Sunburst can also generate.

These integration examples follow the launch notice and official API documentation; the parameter tests in this update cover VIP generation below, not these official-forward routes. OpenAI lists low, medium, high, xhigh, max, and auto quality settings for both 2.5 models. Verify new quality tiers, size limits, and other optional fields with your target token. Official Responses image-tool documentation alone does not establish LaoZhang API Responses support for this route.

Save and verify the image

A successful Images API response should contain an image result. For data[0].b64_json, save the generation result with this script; read edit.json for an edit request:

import base64
import json
from pathlib import Path

response = json.loads(Path("generation.json").read_text())
value = response["data"][0]["b64_json"]
if value.startswith("data:"):
    value = value.split(",", 1)[1]
Path("output.png").write_bytes(base64.b64decode(value, validate=True))

Open output.png and check that it displays correctly at the requested dimensions. For edits, inspect both the requested change and the details that should remain intact. If the route returns data[0].url, download and open that image. Then check the model, group, usage, and actual charge in call logs. HTTP 200 or a model listing cannot replace image acceptance. For authentication or model-access errors, check the key, group, and model ID first. Correct invalid parameters using the returned error. If no image is present, retain the sanitized error and log time, check the Images API reference, and contact support without sharing a complete key.

GPT Image 2.5 official-forward billing

Both 2.5 models have the same token rates as official-forward gpt-image-2. Billing covers actual text input, image input, and image output usage. The fixed per-call price of older routes does not apply.

Official billing item	USD per 1 million tokens
Text input	$5
Cached text input	$1.25
Image input	$8
Cached image input	$2
Image output	$30

These are OpenAI’s official token rates. Confirm LaoZhang API settlement against the current model pricing and token group; contact support for enterprise quotes. Equal token rates do not mean equal cost per image. The model, size, quality, and reference images affect usage, so estimate costs from representative requests.

GPT Image 2.5 VIP per-call routes

gpt-image-2.5-flare-vip and gpt-image-2.5-sunburst-vip are now available at $0.03/call each, using the same integration and billing method as gpt-image-2-vip. Use a Default-group per-call token and confirm access to the target model.

Model ID	Billing	Integration
`gpt-image-2.5-flare-vip`	$0.03/call	Same as `gpt-image-2-vip`
`gpt-image-2.5-sunburst-vip`	$0.03/call	Same as `gpt-image-2-vip`

VIP generation parameters: size and quality

Both VIP models accept size and quality for image generation. Use low, medium, or high for quality. VIP currently rejects xhigh and max with HTTP 400. Omit either field when you do not need to choose its value.

Parameter	Value	Usage
`size`	`WIDTHxHEIGHT`, such as `2048x2048`	Set it explicitly when dimensions matter; choose a verified size below
`quality`	`low` / `medium` / `high`	All three have produced images with both VIP models; select a tier for your task or expose the three options to users

Generation checks on September 9, 2026: Every verified entry below was checked by decoding the returned PNG and measuring its actual dimensions, not just checking HTTP status. Testing used /v1/images/generations with curl, HTTP requests, and OpenAI Python SDK 2.24.0.

Requested `size`	`gpt-image-2.5-flare-vip`	`gpt-image-2.5-sunburst-vip`
`1024x1024`	Verified; exact dimensions	Verified; exact dimensions
`1536x1024`	Verified; exact dimensions	Not yet verified
`1024x1536`	Verified; exact dimensions	Not yet verified
`2048x2048`	Verified; exact dimensions	Verified; exact dimensions
`3840x2160`	Verified; exact dimensions	Not yet verified
`2160x3840`	Verified; exact dimensions	Verified; exact dimensions

“Not yet verified” means this run did not obtain a valid image at that size; it does not mean the size is unsupported. These are representative size checks, not tests of every size and quality combination.

For a shared starter request across both VIP models, use size="2048x2048" and quality="medium". Both returned an actual 2K square image with this combination. quality affects reported generation usage, while VIP billing remains per call; check actual rates and charges in the console.

Dimension handling: Use standard sizes and check both the response size and the actual image. In this run, Sunburst converted 1023x1024 to 1024x1024 and returned an image. Do not assume invalid dimensions always produce an error or use nonstandard sizes when exact pixels matter.

VIP generation example

For an existing gpt-image-2-vip integration, keep the base URL, authentication, endpoint, and result handling. Replace model with a full ID above. This example uses the verified 2K, medium combination:

export LAOZHANG_API_KEY="sk-your-per-call-token"

curl --fail-with-body "https://api2.laozhang.ai/v1/images/generations" \
  -H "Authorization: Bearer $LAOZHANG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2.5-flare-vip",
    "prompt": "A product photo of a white ceramic mug on a gray desk in soft natural light",
    "size": "2048x2048",
    "quality": "medium"
  }' -o generation.json

VIP editing example

Editing uses the same multipart request structure as gpt-image-2-vip; prepare a local source.png first. The parameter matrix above covers generation only. Editing dimensions, quality, and the final edited image have not completed separate output verification.

curl --fail-with-body "https://api2.laozhang.ai/v1/images/edits" \
  -H "Authorization: Bearer $LAOZHANG_API_KEY" \
  -F "model=gpt-image-2.5-sunburst-vip" \
  -F "image=@source.png" \
  -F "prompt=Keep the mug shape, composition, and lighting. Change only the mug body to dark blue." \
  -o edit.json

Both VIP models share this integration method. Choose either model or offer users a selector. Apply the image-saving and acceptance steps above, and confirm actual prices and charges in the console and call logs.

These are LaoZhang API per-call routes; keep the -vip suffix. Flare / Sunburst without -vip are official-forward models with token billing. Use the verified generation sizes and quality tiers above for VIP requests. Official-forward snapshot IDs and the xhigh / max tiers do not apply to the current VIP integration.

Default group: gpt-image-2-web now runs web version 2.5

The Default web route continues to use gpt-image-2-web. The service launch notice confirms that it now runs the latest GPT web version, 2.5. Existing integrations can keep this model ID; the web update does not require switching to Flare or Sunburst. gpt-image-2-web is a LaoZhang API web-route model name. It is a different integration route from Flare / Sunburst; web version 2.5 should not be equated with a specific official-forward snapshot. The current public catalog lists $0.03/call, without a switch to official-forward token billing. Confirm actual charges and parameter limits for this route in the console.

Getting Started

Core API

Text APIs

Video Generation APIs

Image Generation APIs

AI Understanding

GPT Image 2.5 API: Official Forwarding and VIP Per-Call Routes

Choose your route

GPT Image 2.5 official-forward models and groups

Minimal GPT Image 2.5 official-forward integration

Generate with Flare

Edit with Sunburst

Save and verify the image

GPT Image 2.5 official-forward billing

GPT Image 2.5 VIP per-call routes

VIP generation parameters: size and quality

VIP generation example

VIP editing example

Default group: gpt-image-2-web now runs web version 2.5

Sources and status checks

​Choose your route

​GPT Image 2.5 official-forward models and groups

​Minimal GPT Image 2.5 official-forward integration

​Generate with Flare

​Edit with Sunburst

​Save and verify the image

​GPT Image 2.5 official-forward billing

​GPT Image 2.5 VIP per-call routes

​VIP generation parameters: size and quality

​VIP generation example

​VIP editing example

​Default group: gpt-image-2-web now runs web version 2.5

​Related documentation

​Sources and status checks

Choose your route

GPT Image 2.5 official-forward models and groups

Minimal GPT Image 2.5 official-forward integration

Generate with Flare

Edit with Sunburst

Save and verify the image

GPT Image 2.5 official-forward billing

GPT Image 2.5 VIP per-call routes

VIP generation parameters: size and quality

VIP generation example

VIP editing example

Default group: gpt-image-2-web now runs web version 2.5

Related documentation

Sources and status checks