OpenAI Compatible API

LaiDian Token API Docs

Use one endpoint for chat, Responses, model listing, and image generation. The rate multiplier is 1x. Actual model availability depends on your API key, group, quota, and upstream status.

Base URL https://givemesometoken.xyz/v1

Authorization Authorization: Bearer sk-your-api-key

/v1

One Base URL

Use https://givemesometoken.xyz/v1 in OpenAI-compatible clients such as Chatbox, Cherry Studio, and LobeChat.

1x Multiplier

No inflated multiplier and no hidden markup. Usage and billing are visible in the console.

IMG

Image APIs

gpt-image-2 uses /v1/images/generations, not the regular chat endpoint.

Quick Start

Create an API key in the console, then send it as a Bearer token. This example uses gpt-5.4; you can also use gpt-5.5 if your key has access.

curl https://givemesometoken.xyz/v1/chat/completions \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "messages": [
      {"role": "system", "content": "You are a concise assistant."},
      {"role": "user", "content": "Describe LaiDian Token in one sentence."}
    ]
  }'

For most clients, set the Base URL only to https://givemesometoken.xyz/v1. The client will append /chat/completions, /responses, or the image endpoint automatically.

Endpoints

Purpose	Method and Path	Notes
Model list	`GET /v1/models`	Lists models available to the current API key. Availability depends on account, group, quota, and upstream status.
Chat completions	`POST /v1/chat/completions`	OpenAI Chat Completions compatible format. Recommended for Chatbox, Cherry Studio, and LobeChat.
Responses	`POST /v1/responses`	Use this when your SDK or client supports the Responses API.
Image generation	`POST /v1/images/generations`	Use with image models such as `gpt-image-2`.
Image edits	`POST /v1/images/edits`	Requires a client and model that support image editing.
Native Gemini	`/v1beta`	For Gemini SDK/CLI style requests. Do not use this for regular OpenAI-compatible clients.

Chat

Chat Completions is the most compatible entry point. It supports both normal and streaming responses.

curl -N https://givemesometoken.xyz/v1/chat/completions \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "stream": true,
    "messages": [
      {"role": "user", "content": "Write a three-line product intro."}
    ]
  }'

JavaScript

const response = await fetch("https://givemesometoken.xyz/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer sk-your-api-key",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    model: "gpt-5.4",
    messages: [{ role: "user", content: "Hello, LaiDian Token." }]
  })
});

const data = await response.json();
console.log(data.choices[0].message.content);

Python

from openai import OpenAI

client = OpenAI(
    api_key="sk-your-api-key",
    base_url="https://givemesometoken.xyz/v1",
)

resp = client.chat.completions.create(
    model="gpt-5.4",
    messages=[
        {"role": "user", "content": "Explain what an API relay is."}
    ],
)

print(resp.choices[0].message.content)

Responses API

If your SDK or client supports the Responses API, call /v1/responses directly.

curl https://givemesometoken.xyz/v1/responses \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "input": "Give me one API key security tip for developers."
  }'

Image Generation

Image models should not use the chat endpoint. Use /v1/images/generations; the example model is gpt-image-2.

curl https://givemesometoken.xyz/v1/images/generations \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2",
    "prompt": "A minimal product hero image for a transparent AI API relay, clean Apple-style, warm light.",
    "size": "1024x1024"
  }'

Image Edits

Image editing uses multipart form-data. Upload the source image as the image field.

curl https://givemesometoken.xyz/v1/images/edits \
  -H "Authorization: Bearer sk-your-api-key" \
  -F "model=gpt-image-2" \
  -F "prompt=Add a tiny green token in the center." \
  -F "image=@input.png"

Image endpoints only work for API keys assigned to groups with OpenAI image capability. If the key belongs to another platform group, the image endpoint may return unsupported or 404.

Client Setup

Client	Recommended Setup	Models
Chatbox	Select OpenAI API or OpenAI Compatible. Set Base URL to `https://givemesometoken.xyz/v1`.	`gpt-5.4`, `gpt-5.5`
Cherry Studio	Use an OpenAI-compatible provider and set the custom API endpoint to `https://givemesometoken.xyz/v1`.	Add models manually according to your console access.
LobeChat	Use the OpenAI Compatible provider and paste your LaiDian Token `sk-...` key.	Use the models returned by `/v1/models`.
Gemini SDK/CLI	For native Gemini protocol, use `https://givemesometoken.xyz/v1beta`.	Use the corresponding Gemini models.

Troubleshooting

Should the Base URL include `/chat`?

No. For clients like Chatbox, use https://givemesometoken.xyz/v1. The client appends the endpoint path automatically.

Why is a model unavailable?

Model availability depends on your API key, group, quota, and upstream status. Check GET /v1/models first.

Why does image generation fail?

Use /v1/images/generations with an image model such as gpt-image-2. Normal chat clients may not support image endpoints.

What does 401 mean?

Make sure the request includes Authorization: Bearer sk-your-api-key and that the key has not been deleted, disabled, or copied incorrectly.

What if I get balance or quota errors?

Open the console and check your balance, plan, group assignment, and usage records.