Quickstart: Use our proxy in minutes

Configure your base URL

Point your client to our gateway to bypass standard filters. The base URL replaces the default vendor endpoint with https://api.proxyapiopenai.com/v1. This single change routes all requests through our uncensored infrastructure without requiring code modifications beyond the URL string. You can verify connectivity by checking the available models.

The endpoint supports standard OpenAI-compatible parameters. Ensure your library targets the correct path to avoid 404 errors.

Set your API key

Authentication relies on a single bearer token generated upon signup. Retrieve your key from the dashboard and assign it to the OPENAI_API_KEY environment variable. Our proxy validates this key against prepaid credit balances rather than subscription tiers. Use the key immediately; it is active the moment you generate it.

Keep your key secure. Unlike standard providers, we do not offer multiple keys per account, so treat this token as your sole access credential.

Make your first request

Send a standard chat completion request to test connectivity. The model identifier uncensored ensures you receive outputs without content refusals for lawful adult topics. The following example demonstrates a basic text generation call using the default curl syntax.

Copycurl https://api.proxyapiopenai.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Summarize the provided log output."}]
  }'

This request returns a plain text response. The system ignores complex routing logic, delivering direct access to the underlying model weights.

Python SDK integration

Use the official OpenAI Python library to interact with our proxy. Initialize the client with your custom base URL and API key. This approach maintains compatibility with existing codebases while shifting the backend to our uncensored model. The SDK handles serialization automatically.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.proxyapiopenai.com/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

Run this script to verify that your environment correctly forwards requests to our servers. The response structure matches standard OpenAI JSON formats.

Node SDK integration

Integrate the Node.js client by specifying the base URL in the configuration object. This setup works with any Express or standalone Node application requiring generative text. The proxy supports standard streaming and non-streaming modes.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.proxyapiopenai.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

Ensure your package version supports the baseURL parameter. Older versions may require manual header adjustments.

Handle streaming responses

Enable real-time token generation by setting stream to true. The proxy sends Server-Sent Events (SSE) for each generated token. This reduces perceived latency for end-users and allows immediate text rendering. The final chunk contains the full token usage statistics.

Copystream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Parse the SSE stream to extract content pieces. Handle potential network interruptions gracefully, as streaming connections are more susceptible to dropouts than standard JSON responses.