Quickstart: uncensored OpenAI compatible proxy

Base URL and Model ID

Use our proxy endpoint with the official OpenAI SDKs. Point your client to https://api.proxyopenai.com/v1 and set the model to uncensored. This works because we mimic the standard chat-completions schema. You do not need new libraries.

Authentication relies on a Bearer token. Pass your API key in the Authorization header. We support streaming via Server-Sent Events. Token usage appears in the final chunk.

• Endpoint: POST /v1/chat/completions
• Model: uncensored
• Auth: Bearer token

Python SDK Integration

Install the standard OpenAI package and configure the base URL. Pass your key to the client constructor. Make a request to the chat completions endpoint. The response contains the generated text in choices[0].message.content.

Set max_tokens to control output length. Our model allows as many tokens as fit in the window. Errors return standard HTTP status codes. Check the response object for details.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.proxyopenai.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)

Node.js SDK Integration

Import the OpenAI library and set the environment variables. Define the base URL explicitly. Create a chat completion request with your messages. Await the response to get the content.

This approach works with any OpenAI-compatible client. You can use the same code for other proxies. Adjust the temperature and top_p parameters as needed. The API returns JSON by default.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.proxyopenai.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);

Function Calling and JSON Mode

Enable structured outputs with JSON mode. Set response_format to {"type": "json_object"}. The model returns valid JSON that parses directly. This ensures consistent data structures.

Use function calling for tool integration. Define tools in the request body. The model selects the appropriate function. Pass arguments and execute the tool. Results feed back into the conversation. This supports complex workflows.

Streaming Responses

Enable streaming for real-time token delivery. Set stream to true in your request. The API returns a stream of chunks. Each chunk contains partial content.

Parse the Server-Sent Events stream. Concatenate the text content. Monitor for the final chunk. It includes token usage statistics. This reduces perceived latency significantly.

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)

Rate Limits and Tokens

Respect the rate limits to avoid errors. You get 300 requests per minute. Allow 8 concurrent requests per key. The request body must stay under 8 MB.

The context window is 100,000 tokens. This includes prompt and completion. Errors and refusals are free. Credit charges only for successful tokens. Monitor your usage via the dashboard.

cURL

Copycurl https://api.proxyopenai.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "list all files in the src directory"}]
  }'