Is this the official Proxy GPT service?

No, we are an independent provider. Our API is compatible with standard OpenAI client libraries but runs our own uncensored model. You should check the specific vendor documentation for details on their proprietary models and features.

How do I pay for the API?

We accept crypto only: USDT on TRC20 or USDC on Base. You can top up between $20 and $500. You get bonus credit for larger amounts: 5% from $50, 10% from $100, and 15% from $200. Credit never expires.

Can I use this for NSFW content?

Yes, the model is uncensored and does not refuse lawful adult content. The only hard limit is on sexual content involving minors. You can use it for fiction, roleplay, or research without standard refusals.

Proxy gpt: API Documentation

Authentication and base URL

Send your API key in the Authorization header to https://api.proxygpt.cc/v1. The service is openai compatible API, so you do not need to rewrite your existing integration logic. Just update the base URL and inject your credentials into the standard header format. You get one active key per account; generating a new key immediately invalidates the previous one. This keeps things simple without complex routing overhead. You can obtain your key instantly via Google or email login without phone verification.

First request

Make a standard chat completion call to test the connection. The model ID is uncensored and it handles text generation without content refusals for lawful adult topics. You get a direct response with your chosen parameters. This works for developers who want raw model access without the noise of enterprise features. The request body is minimal and straightforward.

curl https://api.proxygpt.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "fetch https api with python requests library"}]
  }'

This returns a text response immediately. The system does not use your prompts for training. You can start experimenting with different temperatures and top-p values to tune the tone. It is a reliable uncensored GPT alternative for your specific use case.

Python SDK

Use the official OpenAI Python library with a custom base URL. This approach ensures you are not locked into a specific vendor. You can switch between different proxy services easily if your needs change. The code structure remains identical to standard implementations. Just point the client to our base URL and provide your key. This method supports all standard parameters like temperature and stop.

from openai import OpenAI

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

The response object contains the generated text and token usage. You can iterate through the result to extract the content. This is the most common way developers integrate our uncensored LLM into their applications. It handles the HTTP details for you automatically.

Node SDK

Initialize the OpenAI client with the correct base URL in Node.js environments. This allows you to use familiar methods for chat completions. You can pass the same parameters as you would for any other OpenAI-compatible service. The code is concise and easy to read. You do not need to install extra dependencies beyond the standard SDK.

import OpenAI from "openai";

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

The response includes the full completion data. You can access the message content directly. This is efficient for server-side generation tasks. The proxy handles the underlying network requests so you can focus on your application logic. It is a cheap LLM API option for scaling your projects.

Streaming responses

Enable streaming by setting the stream parameter to true. This sends partial responses as they are generated. You can display text to users in real time without waiting for the full completion. The server sends server-sent events (SSE) for each token. The final chunk contains the total token usage for the request. This is useful for chat interfaces that need immediate feedback.

stream = 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)

Handle the stream events to accumulate the final text. The proxy GPT service ensures that the streaming is stable and consistent. You can cancel the stream early if the user changes their mind. This reduces unnecessary token usage and saves credits. It is a key feature for responsive user experiences.

Rate limits and errors

The API enforces strict rate limits to ensure reliability. You are limited to 300 requests per minute and 8 concurrent requests per key. If you exceed these limits, you will receive a 429 error. Authentication errors return 401 for invalid keys. Insufficient funds result in a 402 error. The context window is 100,000 tokens for prompt and completion combined. Max output is 16,000 tokens unless you specify a lower max_tokens. Keep your request bodies under 8 MB. These limits are clear and consistent. You do not need to worry about hidden throttling. The service is designed for developers who need predictable performance. Errors are free, so you only pay for successful completions.

Proxy gpt API documentation