Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.laozhang.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
Start With the Token Group

For GPT Image 2, the token group decides which route your request uses. The same gpt-image-2 model name maps to different routes in the default group and the Sora2Official group.

Default Group: Reverse Routes

Per-call billing. gpt-image-2 is the reverse ChatGPT Web route, gpt-image-2-vip is the reverse Codex route, and both are $0.03/call.

Sora2Official: Official Transit

Usage-based billing with the same pricing as the official API. The model name is still gpt-image-2, and the request shape matches the official Images API.
Check the token group first, then the model name. Default-group gpt-image-2 and Sora2Official gpt-image-2 share the same model name but have different routing, billing, and parameter support.

Online Test

You can test the output first at yingtu.ai, then move the prompt into your API integration.

​
Route Matrix

Token groupModel nameRouteBillingsizequalityAvailable endpoints
Default groupgpt-image-2Reverse ChatGPT Web$0.03/callNot supportedNot supportedImages generation, Images edits
Default groupgpt-image-2-vipReverse Codex$0.03/call30 explicit 1K/2K/4K sizesNot supportedImages generation, Images edits
Sora2Officialgpt-image-2Official-transit APISame as official pricingSupportedSupportedImages generation, Images edits

​
Which Route Should You Use?

NeedUse
Quick access without size controlDefault-group gpt-image-2
Reverse route with explicit 1K/2K/4K image size controlDefault-group gpt-image-2-vip
Existing official OpenAI GPT Image 2 code with full parameter compatibilitySora2Official gpt-image-2
quality or more official parametersSora2Official gpt-image-2

​
Base Configuration

All routes use the same OpenAI-compatible gateway URL: 
export LAOZHANG_API_KEY="sk-your-token"
export BASE_URL="https://api.laozhang.ai/v1"
Do not set the base URL to a model-specific path. The actual route is determined by the token group and the model field.

​
Parameter Support

​
Default-group gpt-image-2

Default-group gpt-image-2 is the reverse ChatGPT Web route. Use it when you want the simplest integration and do not need size control.
  • size: not supported
  • quality: not supported
  • Price: $0.03/call

​
Default-group gpt-image-2-vip

Default-group gpt-image-2-vip is the reverse Codex route. Use it when you need an explicit output size on a reverse route.
  • size: supported for 1K, 2K, and 4K outputs, with 30 explicit pixel values
  • quality: not supported; do not include quality in the request body
  • Price: $0.03/call
For gpt-image-2-vip, pass an explicit pixel value in size; do not use auto. Common defaults are 2048x2048, 2048x1152, and 1152x2048; use the 4K tier for final large assets.
Ratio1K size2K size4K size
1:11280x12802048x20482880x2880
2:3848x12801360x20482336x3520
3:21280x8482048x13603520x2336
3:4960x12801536x20482480x3312
4:31280x9602048x15363312x2480
4:51024x12801632x20482560x3216
5:41280x10242048x16323216x2560
9:16720x12801152x20482160x3840
16:91280x7202048x11523840x2160
21:91280x5442048x8643840x1632
gpt-image-2-vip supports 4K size values, but it is still a reverse route, not the official GPT Image 2 API. Use gpt-image-2 under the Sora2Official group when you need quality, full official parameter compatibility, or a request body that exactly matches official OpenAI code.

​
Sora2Official-group gpt-image-2

Sora2Official gpt-image-2 is the official-transit API route. Billing is usage-based with the same pricing as the official OpenAI GPT Image 2 API. Setup:
  1. Create a new token in the console.
  2. Select the Sora2Official group for that token.
  3. Keep model="gpt-image-2" in the request body.
  4. Keep the official request body and replace only the base URL and API key.
This route supports official parameters, including size, quality, and other parameters supported by the official API. Common size values:
  • 1024x1024
  • 1536x1024
  • 1024x1536
  • 2048x2048
  • 2048x1152
  • 3840x2160
  • 2160x3840
  • auto
Available quality values:
  • low
  • medium
  • high
  • auto

​
Endpoint Support

This page documents only the Images API integration path: use /v1/images/generations for text-to-image and /v1/images/edits for image-to-image. In SDKs, these correspond to images.generate and images.edit.
NeedEndpointNotes
Text-to-image/v1/images/generationsReturns data[0].b64_json by default, or data[0].url
Image-to-image/v1/images/editsMultipart local image upload
The Sora2Official official-transit route must use official-style Images API endpoints:
NeedEndpointNotes
Text-to-image/v1/images/generationsMatches the official Images generation endpoint
Image-to-image/v1/images/editsMatches the official Images edit endpoint
For the default-group reverse route, gpt-image-2-vip, and the Sora2Official official-transit route, this guide keeps only Images generation and Images edits as the documented integration methods.

​
Text-to-Image Examples

​
Default-group gpt-image-2

Do not pass size or quality. 
curl "$BASE_URL/images/generations" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $LAOZHANG_API_KEY" \
  -d '{
    "model": "gpt-image-2",
    "prompt": "Create a clean product render of a white ceramic mug on a gray desk, soft natural light, minimal background"
  }'

​
Default-group gpt-image-2-vip

Pass size only. Do not pass quality. The example below requests a 4K landscape image. 
curl "$BASE_URL/images/generations" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $LAOZHANG_API_KEY" \
  -d '{
    "model": "gpt-image-2-vip",
    "prompt": "Create a clean product render of a white ceramic mug on a gray desk, soft natural light, minimal background",
    "size": "3840x2160"
  }'

​
Sora2Official-group gpt-image-2

Use the official-style Images generation endpoint. You can pass size and quality. 
curl "$BASE_URL/images/generations" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $LAOZHANG_API_KEY" \
  -d '{
    "model": "gpt-image-2",
    "prompt": "Create a clean product render of a white ceramic mug on a gray desk, soft natural light, minimal background",
    "size": "1536x1024",
    "quality": "high"
  }'

​
Image-to-Image Examples

​
Default-group Images Edits

curl "$BASE_URL/images/edits" \
  -H "Authorization: Bearer $LAOZHANG_API_KEY" \
  -F "model=gpt-image-2" \
  -F "prompt=Use the provided image as the source. Keep the subject, composition, and text. Only change the sticker to red and add a very thin gold rim to the mug." \
  -F "image=@source.png"

​
Default-group gpt-image-2-vip Images Edits

curl "$BASE_URL/images/edits" \
  -H "Authorization: Bearer $LAOZHANG_API_KEY" \
  -F "model=gpt-image-2-vip" \
  -F "prompt=Use the provided image as the source. Keep the subject, composition, and text. Only change the sticker to blue." \
  -F "image=@source.png" \
  -F "size=2048x2048"

​
Sora2Official-group Images Edits

Official-transit image editing must use /v1/images/edits, with official-style parameters. 
curl "$BASE_URL/images/edits" \
  -H "Authorization: Bearer $LAOZHANG_API_KEY" \
  -F "model=gpt-image-2" \
  -F "prompt=Use the provided image as the source. Keep the subject, composition, and text. Only change the sticker to green." \
  -F "image=@source.png" \
  -F "size=1024x1024" \
  -F "quality=high"

​
Parse Responses

​
Save Images API b64_json

import base64

value = response["data"][0]["b64_json"]
if value.startswith("data:"):
    value = value.split(",", 1)[1]

value += "=" * ((4 - len(value) % 4) % 4)

with open("output.png", "wb") as f:
    f.write(base64.b64decode(value))

​
Read an Images API URL

image_url = response["data"][0]["url"]

​
FAQ

The token group decides the route. Default-group gpt-image-2 is the reverse ChatGPT Web route. Sora2Official gpt-image-2 is the official-transit API route.
No. Use gpt-image-2-vip in the default group when you need size control.
No. gpt-image-2-vip supports size, but it does not support quality. Use gpt-image-2 in the Sora2Official group when you need quality.
Yes. gpt-image-2-vip supports 4K-tier size values, including 3840x2160, 2160x3840, 2880x2880, and 3840x1632. It still does not support quality.
This page keeps only the Images API integration path: use /v1/images/generations for generation and /v1/images/edits for edits.
Create a token under the Sora2Official group, keep the official request body, replace the base URL with https://api.laozhang.ai/v1, and replace the API key with your LaoZhang API token.
The value may include a data:image/png;base64, prefix, or it may need padding at the end. Remove the prefix first, then pad with = before decoding.