Migrating from OpenAI

If you're already using the OpenAI API, switching to TrustedRails takes two changes: the base URL and the API key.

Python

from openai import OpenAI

client = OpenAI(
    api_key="tr-prx-your-api-key",                     # ← your TrustedRails key
    base_url="https://proxy.trustedrails.com/v1",       # ← TrustedRails endpoint
)

# Everything else stays exactly the same
response = client.chat.completions.create(
    model="Qwen/Qwen3-235B-A22B-Instruct-2507-FP8",
    messages=[{"role": "user", "content": "Hello!"}],
)

JavaScript / TypeScript

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "tr-prx-your-api-key",                    // ← your TrustedRails key
  baseURL: "https://proxy.trustedrails.com/v1",       // ← TrustedRails endpoint
});

// Everything else stays exactly the same
const response = await client.chat.completions.create({
  model: "Qwen/Qwen3-235B-A22B-Instruct-2507-FP8",
  messages: [{ role: "user", content: "Hello!" }],
});

Environment variables

Many projects read the API key and base URL from environment variables. A clean way to migrate:

.env

OPENAI_API_KEY=tr-prx-your-api-key
OPENAI_BASE_URL=https://proxy.trustedrails.com/v1

If your OpenAI client reads these variables automatically (the official Python and JS SDKs do), no code changes are needed at all.

Choosing a model

Replace your OpenAI model name with a TrustedRails-supported model. See Supported Models for the full list.

Common mappings:

| Instead of | Try | |---|---| | gpt-4o | Qwen/Qwen3-235B-A22B-Instruct-2507-FP8 | | gpt-3.5-turbo | Check Supported Models for smaller models |

What about streaming, function calling, etc.?

TrustedRails supports the same features as the OpenAI Chat Completions API, including streaming and tool calling. See API Compatibility for details on supported parameters.