API Documentation for Developers

Base URL and Authentication

Use https://api.proxyaiopen.com/v1 as your endpoint. Send your unique API key in the Authorization header. You get one key per account, created instantly via Google or email. Errors and refusals incur no charge, so you can test safely. We do not store prompts for training.

First Request

Send a standard chat completion to generate text. The model ID is uncensored. You can stream results or wait for the full response. Context window is 100,000 tokens total. Max output is 16,000 tokens unless you specify a lower limit. No embeddings or image generation are available.

Copycurl https://api.proxyaiopen.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Set model to uncensored adult variant"}]
  }'

Python SDK Integration

Initialize the client with the new base URL. Pass your API key directly. The library handles retries and formatting automatically. You can adjust temperature or seed for reproducibility. This works with any OpenAI-compatible Python client. Streaming is supported via the async iterator.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.proxyaiopen.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 SDK Integration

Configure the client object with the proxy URL. Set the key in the headers or client config. Node clients handle the JSON parsing natively. You can limit the max tokens to control costs. The response object contains the generated text. Errors throw exceptions you can catch.

Copyimport OpenAI from "openai";

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

Streaming and SSE

Set stream: true in your request. Receive tokens as they generate. The final chunk contains usage statistics. This reduces latency for long responses. You can stop the stream early if needed. Token counts help you track billing accurately.

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)

Limits, Errors, and Billing

Rate limit is 300 requests per minute. Concurrent requests cap at 8 per key. Request body must stay under 8 MB. A 401 error means invalid credentials. A 402 indicates insufficient credit. A 429 signals you hit the rate limit. Billing is transparent: $0.15 per 1M input tokens and $0.50 per 1M output tokens. Pay with crypto only.