gpt88.cc General Integration Guide

What is gpt88.cc

gpt88.cc is a unified large-model API gateway for developers. Instead of learning a completely new protocol, you usually keep the existing client style and only change the gateway endpoint and key.

From the user side, it solves three common problems:

• Use one entry point for many model vendors.
• Choose the route that fits your network environment.
• Reuse one consistent setup pattern across SDKs, IDEs, and agent tools.

Who this guide is for

• First-time gpt88.cc users who want a full mental model first.
• Teams already using OpenAI SDKs and looking for a low-friction migration path.
• Users of Claude Code or Anthropic SDKs who want the matching route pattern.
• Teams using mixed tools such as Cursor, Codex CLI, cURL, Python, and Node.js.

OpenAI and Claude compatibility mindset

The most important distinction is not the model brand. It is the protocol expected by the client.

Standard APIs
  Use the Base URL: https://api.gpt88.cc

Direct image / video APIs
  Use the Base URL: https://img.gpt88.cc

OpenAI / Claude / Anthropic protocol differences
  Keep the selected Base URL and use the endpoint path and request format required by the protocol.

What to prepare before starting

1. Create an API key in the gpt88.cc console
2. Pick one default model for the first successful test
3. Choose the right route
4. Identify whether your tool is OpenAI-style or Claude / Anthropic-style
5. Send one minimal request first

Step-by-step integration flow

1. Create or choose an API key.
2. Pick one default model.
3. Choose the route.
4. Match the route style to the client protocol.
5. Send one minimal request.
6. Only then expand to your real workflow.

Integrate by tool type

cURL

Use cURL for the first connectivity proof: network, key validity, and model name correctness.

curl https://api.gpt88.cc/v1/chat/completions \
  -H "Authorization: Bearer $GPT88_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-haiku-4-5-20251001",
    "messages": [
      {"role": "user", "content": "Introduce gpt88.cc in one sentence"}
    ]
  }'

Python SDK

For OpenAI-style Python services, usually the only required change is base_url.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.gpt88.cc",
    api_key="YOUR_GPT88_API_KEY",
)

resp = client.chat.completions.create(
    model="claude-haiku-4-5-20251001",
    messages=[{"role": "user", "content": "Introduce gpt88.cc in one sentence"}],
)
print(resp.choices[0].message.content)

Node.js SDK

For server-side JavaScript or TypeScript applications, the pattern is the same: switch baseURL and keep the OpenAI SDK shape.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.gpt88.cc",
  apiKey: process.env.GPT88_API_KEY,
});

const resp = await client.chat.completions.create({
  model: "claude-haiku-4-5-20251001",
  messages: [{ role: "user", content: "Introduce gpt88.cc in one sentence" }],
});
console.log(resp.choices[0].message.content);

Related docs to read next

• Quickstart for the shortest hands-on path.
• Auth & Billing for API keys and RMB balance semantics.
• Config Export for reusable multi-tool configs.
• Models for model selection.

One-line summary

Keep the client protocol shape, point it at the correct gpt88.cc route, validate with one minimal request, then expand to your real model workflow.