DEVELOPERS

Build with Arbitex Gateway.

One URL change is all it takes. Arbitex exposes an OpenAI-compatible API — point your existing SDK at the gateway, add your X-API-Key header, and every AI call is governed automatically.

Read the Docs Book a Demo

Quick Start

Your first API call in under a minute.

Arbitex is OpenAI-compatible. Change your base URL to https://api.arbitex.ai/v1 and add an X-API-Key header. DLP inspection, policy enforcement, and audit logging activate automatically.

curl https://api.arbitex.ai/v1/chat/completions \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "X-API-Key: $ARBITEX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

from openai import OpenAI

client = OpenAI(
    api_key="your-openai-key",
    base_url="https://api.arbitex.ai/v1",
    default_headers={"X-API-Key": "your-arbitex-key"},
)

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

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.OPENAI_API_KEY,
  baseURL: "https://api.arbitex.ai/v1",
  defaultHeaders: {
    "X-API-Key": process.env.ARBITEX_API_KEY,
  },
});

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

Full integration guide at docs.arbitex.ai →

SDKs & Libraries

Native SDK wrappers for your language.

All SDKs wrap the OpenAI-compatible REST API with typed clients, automatic retry, and built-in header injection. Or use any existing OpenAI SDK directly with a base URL override.