Quickstart: Uncensored LLM API

Base URL and Authentication

Our API lives at a single base URL that replaces your existing endpoint. You do not need to change your client logic or install new libraries. Just update the base URL to https://api.claudemaxapiproxy.com/v1 and provide your API key from the dashboard. The key is shown immediately after signup. No phone number is required. You can sign in with Google or use a simple email and password combination. One active key per account keeps things simple. A new key replaces the old one instantly if you regenerate it. This keeps your integration clean and secure.

Send a Chat Completion Request

Send a standard POST request to /v1/chat/completions to get a response. The model ID is uncensored. This model is an open-weight variant tuned to answer without content refusals for lawful adult use. It is not GPT, Claude, or any other vendor's model. You get text in and text out. The context window holds 100,000 tokens for both prompt and completion together. The maximum output per request is 16,000 tokens. If you do not set max_tokens, the limit drops to 2,048 tokens. This ensures predictable usage for your scripts.

Copycurl https://api.claudemaxapiproxy.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Calculate the SHA-256 hash of the string test123"}]
  }'

SDK Examples (Python, Node.js)

Use your existing SDK code with minimal changes. The Python client connects easily by setting the base URL. The Node.js client follows the same pattern. Both support the standard parameters like temperature and top_p. Streaming is available via Server-Sent Events. Function calling works with tools and tool_choice. JSON mode is supported via response_format. The pricing is transparent at $0.15 per 1M input tokens and $0.50 per 1M output tokens. Errors and refusals are free. Prepaid credit never expires. This makes it the cheapest LLM API for high-volume uncensored needs.

Copyfrom openai import OpenAI

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

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.claudemaxapiproxy.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 Responses (SSE)

Enable streaming by setting the stream parameter to true. You receive chunks of text as they are generated. The final chunk contains the token usage statistics. This allows real-time display in your applications. The rate limit is 300 requests per minute per key. You can have up to 8 concurrent requests. The request body must stay under 8 MB. These limits prevent abuse while ensuring fair usage. Streaming works seamlessly with the uncensored LLM model. You can adjust the temperature and seed for reproducibility. This is ideal for chat interfaces.

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)

Function Calling and Tools

Use tools to extend the model's capabilities. Define your functions in the tools array. Set the tool_choice to auto or specify a function. The model will return structured JSON when appropriate. This works with the openai compatible API format. You can also force JSON output with response_format set to json_object. This is useful for data extraction tasks. The model supports standard parameters like presence_penalty and frequency_penalty. These help control repetition and relevance. The uncensored nature means fewer refusals during complex tool calls. This makes it a reliable uncensored AI models choice for developers.

Understanding Limits and Errors

Handle errors gracefully with standard HTTP status codes. A 401 error means your key is invalid. A 402 error indicates you have no credit. A 429 error signals you have hit the rate limit. You can top up with crypto only. USDT on TRC20 or USDC on Base are accepted. Any whole amount from $20 to $500 works. Bonus credit increases with larger deposits. The trial gives $0.50 valid for 7 days. Prompts are not used for training. This respects your privacy. The hard content limit applies: no sexual content involving minors. This is the only refusal that always happens.