Skip to content
Arbitex Docs

SDKs & examples

The Arbitex Gateway is a superset of the OpenAI API, so any client, SDK, or tool that targets OpenAI works against the gateway with only two changes: the base URL and the API key. There is no Arbitex-specific SDK to install.

Base URL + key

Section titled “Base URL + key”
Setting Value
Base URL https://api.arbitex.ai/v1
API key arb_live_… (see Authentication)
Model format provider/model-id (e.g. anthropic/claude-sonnet-4-20250514, openai/gpt-4o)

OpenAI Python SDK

Section titled “OpenAI Python SDK”
from openai import OpenAI


client = OpenAI(
    api_key="arb_live_your-api-key-here",
    base_url="https://api.arbitex.ai/v1",
)


# Streaming, with Arbitex DLP events surfaced alongside standard chunks
stream = client.chat.completions.create(
    model="openai/gpt-4o",
    messages=[{"role": "user", "content": "Summarize our Q3 results."}],
    stream=True,
)
for chunk in stream:
    delta = chunk.choices[0].delta.content or ""
    print(delta, end="")

OpenAI Node.js SDK

Section titled “OpenAI Node.js SDK”
import OpenAI from "openai";


const client = new OpenAI({
  apiKey: "arb_live_your-api-key-here",
  baseURL: "https://api.arbitex.ai/v1",
});


const resp = await client.chat.completions.create({
  model: "anthropic/claude-sonnet-4-20250514",
  messages: [{ role: "user", content: "Draft a polite decline email." }],
});
console.log(resp.choices[0].message.content);

Other tools

Section titled “Other tools”

Any tool with a configurable OpenAI base URL works — LangChain, LlamaIndex, the OpenAI CLI, IDE assistants, and similar. Point the base URL at https://api.arbitex.ai/v1 and supply your arb_live_ key.

Reading Arbitex extensions

Section titled “Reading Arbitex extensions”

The standard SDKs return the OpenAI response shape. To read the Arbitex additions:

  • Policy headers (X-Policy-Action, X-Matched-Rule) — read them from the raw HTTP response. Most SDKs expose response headers via a with_raw_response accessor or equivalent.
  • DLP streaming events (dlp_correction, output_blocked) — surface as events in the stream; handle them alongside standard content chunks.

See Chat completions for the full streaming + DLP-event reference.

Next steps

Section titled “Next steps”