Uncensored LLM API

Claude-max-api-proxy: Uncensored API Alternative

Get an openai compatible API for uncensored LLM usage with our claude-max-api-proxy, supporting 100,000 token context windows for your existing code.

$0.15 per 1M input tokens
100,000 token context window
No content refusals for adults

Open account View documentation

Test with one request

curl 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"}]
  }'

from 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)

import 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);

$0.15per 1M input tokens

$0.50Output tokens / 1M

100,000token context

$0.50trial credit

300requests per minute

What's included

OpenAI SDK Compatible

Use existing client code with our base_url and API key.

100k Context Window

Process large documents with prompt and completion totaling 100,000 tokens.

Crypto-Only Pricing

Pay with USDT or USDC; prepaid credit never expires for you.

Streaming via SSE

Receive real-time token streams with usage data in the final chunk.

Function Calling Support

Enable tools and tool_choice for structured AI interactions and logic.

JSON Mode

Force structured output using response_format json_object for reliable parsing.

Setup steps

Generate Your Key
Sign in with Google or email to get an API key instantly.
Update Base URL
Point your SDK to HTTPS://api.claudemaxapiproxy.com/v1 and set your key.
Send Requests
Call POST /v1/chat/completions with model id "uncensored" for results.

What builders create

NSFW Content Generation

Create adult fiction without model refusals for lawful creative writing projects.

Code Completion

Assist developers with coding tasks using a proxy that ignores style constraints.

Research Analysis

Analyze controversial topics without the model hedging or refusing sensitive queries.

CLI Integration

Connect your local CLI tools to an uncensored LLM via standard SDKs.

Why claude-max-api-proxy is the uncensored alternative

The claude-max-api-proxy provides an uncensored LLM experience by serving a dedicated model that answers without unnecessary refusals for lawful adult content.

NSFW Chatbot Integration
Use the uncensored model for chatbot applications that need to handle adult themes without hitting standard content filters.
OpenAI Compatible API
Connect existing code by pointing your OpenAI SDK to our base URL and setting the model id to "uncensored".
Privacy-Friendly Usage
Prompts are not used for training. Your data stays private while you enjoy unlimited creative freedom.

How the proxy works: 3 steps to uncensored code

Connect your existing code in three simple steps to access our uncensored LLM without SDK changes.

Get your key: Sign up with Google or email on our Get API Key page to receive your unique token instantly.
Configure: Update your client’s base_url to https://api.claudemaxapiproxy.com/v1 and set the model ID to uncensored.
Send requests: POST to /v1/chat/completions using standard parameters like temperature and top_p.

Your requests now flow through our proxy, delivering uncensored responses via our OpenAI-compatible API.

Developers ask: Is it truly uncensored and reliable?

Yes, the model refuses fewer topics than standard Anthropic or OpenAI endpoints, but it still blocks minor sexual content involving minors. It does not offer embeddings, images, or fine-tuning—only text completions. You get streaming via SSE, JSON mode, and tool support. Errors cost nothing. Request limits are 300 per minute. Check your usage dashboard for real-time token counts.

Common mistakes: Proxy limits and token usage errors

Proxy limits and token usage errors cause most integration failures. Our API caps requests at 300 per minute and 8 concurrent connections per key. A single request body cannot exceed 8 MB. If you omit max_tokens, output defaults to 2,048 tokens, not the 16,000 maximum. Streaming via SSE includes usage data only in the final chunk. Always validate your token counts before sending.

Checklist: Choosing an uncensored proxy provider

Verify your API keys match the model id exactly. Ensure the base URL points to a dedicated endpoint, not a shared gateway. Confirm crypto top-ups include bonus credit tiers. Check that prepaid credits never expire. Validate streaming via SSE for real-time token usage. Ensure the provider refuses only minor content, not lawful adult text. Avoid providers requiring monthly subscriptions for uncensored access. Confirm 100,000 token context windows support your code needs.

Who Uses This Uncensored Proxy

NSFW creators and AI developers use this service for reliable content generation without refusals. The uncensored LLM handles adult themes smoothly, while the openai compatible API ensures your existing code runs immediately. This proxy serves teams needing privacy and direct control over model responses. It is NOT for users requiring image generation, fine-tuning, or multi-model routing. It also excludes those needing enterprise SLAs or on-premise deployments. Use it strictly for text-based LLM interactions.

Common questions

What is claude-max-api-proxy and how does it work?

It is an OpenAI-compatible proxy for uncensored usage. You send requests to our base URL and receive text. The system uses one model tuned for fewer refusals. Input text becomes output text via standard endpoints.

Does the API support streaming responses?

Yes, it supports streaming via Server-Sent Events. You receive tokens as they generate. The final chunk includes usage statistics. This allows real-time display of output without waiting for the entire response to finish.

Is the prepaid credit valid forever?

Yes, your credit never expires. You can top up whenever you want. Errors and refusals consume no tokens. Your balance remains available until you decide to use it for future requests.

Can I use the official OpenAI SDK?

Yes, you can use the standard SDK. Change the base URL and API key. Send the model identifier "uncensored". All parameters like temperature and stop work exactly as documented for compatible clients.

What payment methods do you accept for top-ups?

We accept only crypto for top-ups. Use USDT on TRC20 or USDC on Base. Minimum amount is $20. Credits are added immediately after payment confirmation.

Is the model truly uncensored?

Yes, it answers without content refusals. It handles adult topics freely. We only block sexual content involving minors. Lawful adult usage is fully supported without extra checks or hidden filters.

Get your key in one step

Open account