Integrating Generic OpenAI-Compatible Tools

The one rule

Change base_url to https://api.xmai.sg/v1. That's it. Every tool in the OpenAI ecosystem — CLIs, IDE plugins, SDKs, agent frameworks — reads this value from a config file or constructor argument. Once you redirect it at xmAI, streaming, tool use, system prompts, and every other Chat Completions feature continue to work unchanged.

This page is the umbrella reference for tools that don't yet have a dedicated integration page. If your tool isn't listed, use the matrix below as a template — 95% of OpenAI-compatible tools follow the same pattern.

Prerequisites

• Registered at XmAI Console with credits available (free tier included)
• Created an API Key on the API Keys page (format sk-xxx...)

Tool matrix

The endpoint you'll use everywhere:

https://api.xmai.sg/v1

Tool	Where to set it	Config key	Example value
OpenAI Python SDK	OpenAI(...) constructor	base_url	https://api.xmai.sg/v1
OpenAI Node.js SDK	new OpenAI({...}) constructor	baseURL	https://api.xmai.sg/v1
Cursor	Settings → Models → Override OpenAI Base URL	UI text field	https://api.xmai.sg/v1
Cline (VS Code)	API Provider → OpenAI Compatible	API Base URL	https://api.xmai.sg/v1
Continue.dev	~/.continue/config.yaml → models[].apiBase	apiBase	https://api.xmai.sg/v1
Zed AI	settings.json → assistant.providers → openai.api_url	api_url	https://api.xmai.sg/v1
Vercel AI SDK (@ai-sdk/openai)	createOpenAI({...})	baseURL	https://api.xmai.sg/v1
LangChain (Python)	ChatOpenAI(...)	openai_api_base	https://api.xmai.sg/v1
LlamaIndex (Python)	OpenAI(...) constructor	api_base	https://api.xmai.sg/v1
LiteLLM	litellm.api_base or env OPENAI_API_BASE	api_base	https://api.xmai.sg/v1
Aider	CLI flag or env	--openai-api-base / OPENAI_API_BASE	https://api.xmai.sg/v1
Open WebUI / Chatbot UI	Settings → OpenAI API Base URL	UI text field	https://api.xmai.sg/v1

Pair whichever key field it uses (api_key, apiKey, OPENAI_API_KEY, etc.) with your xmAI key (sk-...). No code changes beyond that.

Worked examples

OpenAI Python SDK

from openai import OpenAI

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

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

OpenAI Node.js SDK

import OpenAI from 'openai'

const client = new OpenAI({
  apiKey: 'sk-your-xmai-key',
  baseURL: 'https://api.xmai.sg/v1',
})

const response = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'Hello!' }],
})
console.log(response.choices[0].message.content)

Vercel AI SDK (@ai-sdk/openai)

import { createOpenAI } from '@ai-sdk/openai'
import { generateText } from 'ai'

const xmai = createOpenAI({
  apiKey: process.env.XMAI_API_KEY,
  baseURL: 'https://api.xmai.sg/v1',
})

const { text } = await generateText({
  model: xmai('gpt-4o'),
  prompt: 'Hello!',
})
console.log(text)

LangChain (Python)

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="gpt-4o",
    openai_api_key="sk-your-xmai-key",
    openai_api_base="https://api.xmai.sg/v1",
)
print(llm.invoke("Hello!").content)

Continue.dev (~/.continue/config.yaml)

models:
  - name: xmAI GPT-4o
    provider: openai
    model: gpt-4o
    apiKey: sk-your-xmai-key
    apiBase: https://api.xmai.sg/v1
  - name: xmAI Claude Sonnet 4.6
    provider: openai
    model: claude-sonnet-4-6
    apiKey: sk-your-xmai-key
    apiBase: https://api.xmai.sg/v1

Cursor

1. Open Settings (⌘/Ctrl ,) → Models pane
2. Enable Override OpenAI Base URL and set it to https://api.xmai.sg/v1
3. In the OpenAI API Key field, paste your xmAI key (sk-...)
4. Click Verify — a green tick means you're connected

Custom model IDs in Cursor

Cursor's model dropdown shows OpenAI-native model names. Add xmAI-specific IDs (like claude-sonnet-4-6 or gemini-2.5-pro) via Add Custom Model → type the ID and save.

Verifying the connection

After sending a test request from any of the tools above:

1. Log into the Console → Request Logs to confirm the request landed
2. Or watch the Today's Usage card on the Dashboard for credit consumption

A new row in the log = you're connected.

Common pitfalls

Trailing /v1

Always include /v1 in base_url — xmAI's Chat Completions endpoint is https://api.xmai.sg/v1/chat/completions. Anthropic SDK users in Claude Code omit /v1 because the SDK auto-appends it; OpenAI SDKs do not auto-append, so you must write the full /v1.

Model ID mismatches

Tools that hardcode a model-picker dropdown may request IDs xmAI doesn't ship (e.g. gpt-4). The request reaches xmAI and comes back as 404 model not found. Fix: change the model to an ID listed in /v1/models (or the Models page).

Proxy / firewall

Corporate http_proxy settings sometimes intercept the xmAI domain. Exclude it:

export NO_PROXY="api.xmai.sg"

Custom CA chains:

export NODE_EXTRA_CA_CERTS=/path/to/your-ca-chain.pem

401 auth failures

• Check key status / expiry on the API Keys page
• Confirm the tool actually sends Authorization: Bearer <key> (some tools mis-label the field — if in doubt, enable verbose logging and inspect the header)

402 insufficient balance

xmAI deducts per-token in real time. When your balance runs out, requests return 402 or insufficient_balance. Top up on the wallet page, or enable auto-topup.

Don't see your tool?

If you got a tool working with xmAI via the "change the base URL" pattern, we'd love a PR with a dedicated guide — open one at github.com/xmai-ai/xmai-docs or ping the team in-app. The matrix above stays authoritative; every new page is a link from here.

Related

• Quick Start — SDK-level example with Python / Node / Go / curl
• Chat Completions API — the underlying API
• Models — available models and pricing
• Error Codes — error handling guide
• Claude Code — Anthropic-native setup
• OpenCode — open-source agentic client
• Codex CLI — OpenAI's official terminal agent
• Gemini CLI — why Gemini CLI itself is a poor fit + workaround