proxyclaudecode.com

Uncensored API

Proxy claude code Alternative: Uncensored API

Get an uncensored LLM API with a 100k context window, prepaid crypto billing, and full OpenAI compatibility for your code.

100,000 token context window
Prepaid credit, no subscriptions
Crypto payments only

Start now View documentation

Test via API call

curl https://api.proxyclaudecode.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Parse this CSV and return JSON"}]
  }'

from openai import OpenAI

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

per 1M input tokens: $0.15
Output tokens / 1M: $0.50
token context: 100,000
trial credit: $0.50
requests per minute: 300

Core features

OpenAI Compatible: Drop-in replacement for standard clients using our base URL.
Uncensored Model: Answer without refusals for lawful adult or coding topics.
Streaming Support: Receive tokens via SSE with usage in the final chunk.
Function Calling: Supports tools, tool_choice, and JSON mode responses.
Crypto Top-ups: Pay with USDT or USDC and get bonus credit.
No Lock-in: Prepaid credit never expires and requires no monthly fee.

Setup steps

Create Account
Sign up with Google or email to get your key instantly.
Add Crypto Credit
Top up with USDT or USDC to start using the API.
Run First Request
Send a POST request to our /v1/chat/completions endpoint.

Build with it

Coding Assistants

Run coding models without content filters blocking technical explanations.

NSFW Content Gen

Generate adult fiction without arbitrary refusals for lawful topics.

Research Tools

Query sensitive security research data without unnecessary model guardrails.

Unlimited Workflows

Build scripts that process large texts within the 100k limit.

Who uses it, in which real situations; and plainly who it is NOT for

Developers seeking an uncensored LLM API for coding or NSFW content generation use this service.

Testing models without content refusals.
Bypassing subscription locks with prepaid tokens.

This is NOT for users needing image, audio, or embedding endpoints.

It also excludes those requiring model routing between vendors.

Use it when you want direct access to one open-weight model via an OpenAI-compatible endpoint.

proxy claude code use cases for coding and content

Developers deploy this uncensored LLM API for coding tasks and content generation without standard refusals.

Direct Model Access

Unlike routing proxies, we serve one tuned model. This avoids latency from multiple hops while keeping costs predictable for high-volume coding workflows.

Predictable Billing

Prepaid credit covers real usage. Errors cost nothing, ensuring you only pay for successful completions.

Crypto Payments

Top up via USDT or USDC.

Sign up via Google or email to receive your key instantly.
Top up prepaid credit using USDT (TRC20) or USDC (Base) with no card needed.
Configure your OpenAI-compatible SDK client to point at our base URL.
Send requests to /v1/chat/completions and receive streaming responses.

A checklist for choosing a provider in this niche

Verify you pay only for real tokens, not subscriptions. Confirm the base URL accepts standard OpenAI SDK parameters. Ensure crypto top-ups use USDT (TRC20) or USDC (Base). Check that errors consume zero credits. Verify the model is fixed, not routed. Test streaming support via SSE. Confirm a prepaid balance never expires. Validate that no phone number is required for signup.

What developers actually ask about this topic

Developers frequently ask how to handle latency when routing calls through a proxy, since some proxies reroute to slower models like Qwen 3 or Gemini Preview. You also want to know if the service supports streaming responses. We confirm full SSE support with token usage details in the final chunk. Another common question involves cost predictability. Our prepaid model charges only for real tokens, so errors remain free. Finally, users ask about account setup. We offer Google sign-in with no phone number required.

How this differs from a typical alternative on 4-6 concrete signs

We provide a single uncensored model, not a complex routing layer that hides latency or adds unexpected costs. Our prepaid credits never expire, and errors are free. You pay $0.15 per million input tokens. Crypto top-ups include bonus credits. Unlike subscription locks, we offer direct API access without vendor lock-in.

Feature	Typical Proxy	Our API
Billing	Subscription or complex tiers	Prepaid, expires-free
Cost	Variable routing fees	$0.15 / 1M input tokens	Bonus credit	None	+10% at $100
Content	Mixed models	Single uncensored model

Common questions

What is the proxy claude code alternative?

It is an uncensored LLM API. It serves one open-weight model via the standard OpenAI-compatible chat-completions endpoint. You send text and receive text with no routing logic involved.

Does it support streaming responses?

Yes. The API supports streaming via Server-Sent Events (SSE). Token usage details appear in the final chunk of the stream, allowing real-time display in your client applications.

What is the context window size?

The model supports a 100,000 token context window. This includes both prompt and completion tokens combined. Max output is 16,000 tokens per request, or 2,048 if you do not specify a limit.

How do I pay for credits?

You pay using cryptocurrency only. We accept USDT on the TRC20 network or USDC on the Base network. Top-ups range from $20 to $500, with bonus credits for larger amounts.

Is there a free trial available?

Yes. New accounts receive $0.50 of trial credit. You get immediate access to test the uncensored API with your own code.

Are prompts used for training data?

No. Your prompt data is not used for training. We collect only an email for your account. The API is designed for developers who need privacy alongside direct model access.

Secure your API key

Start now