Uncensored API

Claude code nsfw: the uncensored api alternative

Swap base URLs to use our uncensored LLM for claude code NSFW workflows, supporting 100,000-token context windows with standard OpenAI SDKs.

OpenAI-compatible endpoints
Crypto payments only
No card needed

Get your key View documentation

Test with one call

curl https://api.claudecodensfw.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the steps to restart the system service"}]
  }'

from openai import OpenAI

client = OpenAI(base_url="https://api.claudecodensfw.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.claudecodensfw.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

Core capabilities

Standard Integration

Use existing OpenAI SDKs by changing only the base URL and API key.

Long Context

Process up to 100,000 tokens per request for complex creative or coding tasks.

Streaming Support

Receive real-time responses via Server-Sent Events with full token usage tracking.

JSON Mode

Enforce structured output formats for reliable programmatic integration into your applications.

Tool Calling

Define custom functions and tools to extend the model's capabilities dynamically.

Privacy First

Prompts are not used for training; no phone number required for signup.

Setup guide

Get Your Key
Sign up with Google or email to receive an instant API key.
Add Credits
Top up with USDT or USDC to start sending requests immediately.
Swap Base URL
Update your client code to point to our dedicated uncensored endpoint.

Use cases

Explicit Prose

Generate adult-themed narrative content without unexpected refusals or content filters.

Coding Agents

Run Claude Code or similar agents with fewer restrictions on output.

Data Extraction

Parse large documents using JSON mode for structured data retrieval.

Creative Writing

Write unrestricted stories, scripts, or roleplay scenarios with full freedom.

claude code NSFW: why developers are switching

Developers switch because our uncensored LLM delivers unrestricted creative output without breaking standard OpenAI-compatible client code.

Explicit Prose Generation

Write novels with adult themes without content refusals. Swap the base URL and continue using your existing SDK.

High-Context Coding

Process 100,000 tokens for complex codebases. Run function calling tools while maintaining full context window integrity.

Unfiltered Research

Query controversial topics freely. No sudden blocks during deep analysis. Get straight answers for sensitive data projects.

What developers actually ask about this topic

Developers want explicit creative freedom without context loss. Our uncensored LLM handles adult themes natively. It supports 100k context windows and streaming responses via SSE. Function calling and JSON modes work out of the box. No extra wrappers needed. Just swap your base URL and key. Errors are free. Latency remains low. Start with $0.50 trial credit.

Worked cost examples with token arithmetic

Your uncensored LLM billing relies on precise token counts, not vague estimates. Input costs $0.15 per million tokens while output runs $0.50 per million. A 100k token context window with 2k output tokens generates exactly $1.25. You only pay for actual usage. Errors remain free. This transparent model ensures predictable spending for high-volume developers.

Common mistakes people make in this niche

Developers often assume any proxy supports standard tools, but our uncensored LLM limits you to function calling, JSON mode, and streaming via SSE. Sending requests that exceed the 8 MB body or 8 concurrent connections causes immediate drops. Another error is ignoring the 100,000-token context window, which splits prompt and completion. Always set max_tokens to 16,000 to avoid truncated responses. Verify your client handles the final streaming chunk for usage data correctly.

You get your key in seconds and start generating immediately.

Sign up. Click "Continue with Google" or use your email. The dashboard shows your API key instantly. No phone number required.
Add credit. Use crypto (USDT or USDC). Minimum is $20. You receive bonus credit based on your amount.
Swap base URL. Point your SDK to https://api.claudecodensfw.com/v1. Set the model ID to uncensored.
Send a request. POST to /v1/chat/completions. Receive unrestricted text output.

How this differs from a typical alternative

Unlike proxy aggregators that route traffic, we host a single, dedicated uncensored model optimized for high-context, unrestricted generation.

Feature	Typical Proxy	Our API
Routing	Aggregates multiple vendors	Single dedicated uncensored model
Endpoints	Varies by vendor	Standard OpenAI-compatible
Latency	Higher due to hops	Direct server response
Cost	Markup on base price	Transparent token billing
Model	Proprietary or mixed	Open-weight, tuned model

Common questions

What is claude code NSFW and how does it differ from standard models?

It is an uncensored LLM API that removes content refusals for lawful adult use. You can swap base URLs to bypass restrictions instantly. The model id is uncensored, supporting up to 100,000 tokens context.

Does this API support streaming responses for real-time generation?

Yes, streaming via SSE is fully supported. Token usage details appear in the final chunk of the stream. This allows developers to integrate real-time outputs efficiently without managing complex connection states manually.

What are the pricing rates for input and output tokens?

Input tokens cost $0.15 per 1M, and output tokens cost $0.50 per 1M. Errors and refusals incur zero charges. You only pay for actual token usage, ensuring transparent billing for every request.

How do I top up my account balance using cryptocurrency?

We accept USDT on TRC20 or USDC on Base for all payments. Minimum top-ups start at $20, with bonus credits increasing at higher tiers. Credit never expires, providing flexible funding for your projects.

Is there a free trial available for new developers?

Yes, every new account receives $0.50 of trial credit valid for seven days. This allows you to verify integration and performance before committing to paid usage.

What are the request limits for a single API key?

Keys allow 300 requests per minute and eight concurrent requests. Each request body must stay under 8 MB. These limits ensure stable performance for high-volume applications while preventing any single key from overwhelming the server.

Get your key in seconds

Get your key