API Documentation

Quickstart: Change base_url

Start by updating two variables. Point your client to https://api.proxyllm.cc/v1 and use your generated key. The endpoint mimics the OpenAI chat completions structure exactly. You do not need new libraries or complex adapters. Just swap the endpoint and the token, then run your existing logic.

Copycurl https://api.proxyllm.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List five common CSS layout techniques for modern web design."}]
  }'

Authentication and Keys

Generate a key via the dashboard and pass it in the Authorization header. Each account holds one active key; creating a new one revokes the old. Use Bearer your_api_key for standard requests. The system rejects invalid tokens immediately.

Chat Completions Endpoint

Send POST requests to /v1/chat/completions with a messages array. The model ID is uncensored. It handles text generation without standard refusals for lawful adult content. Set max_tokens to control output length; the default is 2,048 tokens.

Copyfrom openai import OpenAI

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

Streaming and SSE

Enable streaming by setting stream: true in your request payload. The API returns Server-Sent Events (SSE) for real-time token delivery. Token usage statistics appear in the final chunk of the stream. This reduces perceived latency for large responses.

Copyimport OpenAI from "openai";

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

Function Calling and JSON Mode

Define tools in the tools parameter for structured outputs. The model supports both function calling and strict JSON formatting via response_format. Use json_object to force valid JSON structures. Temperature and top_p parameters allow fine-tuning creativity.

Rate Limits and Errors

Expect 401 for invalid keys and 402 when credit runs out. The limit is 300 requests per minute per key. Concurrent requests cap at eight simultaneously. The context window spans 100,000 tokens total. Handle 429 errors by implementing exponential backoff in your client logic.

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)