Uncensored Proxy API

Claude code proxy Alternative API

Run Claude Code with any model via our OpenAI-compatible proxy. Get an uncensored LLM for $0.15 per 1M tokens with a 100k context window.

Open account View documentation

No monthly subscription fees
Crypto top-ups only
100k token context window

Test with one request

curl https://api.proxycodeclaude.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Show me the current system uptime stats"}]
  }'

from openai import OpenAI

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

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

Platform features

OpenAI-Compatible Endpoint

Use any OpenAI SDK to route requests to our proxy API seamlessly.

Uncensored Model Output

Receive responses without content refusals for lawful adult or coding use cases.

Transparent Per-Token Billing

Pay $0.15 per 1M input tokens with no hidden monthly subscription costs.

Streaming Support

Receive real-time tokens via SSE with usage data in the final chunk.

JSON Mode Support

Enforce structured output using response_format json_object for reliable programmatic parsing.

Instant Crypto Top-Up

Fund your account with USDT or USDC and receive bonus credit instantly.

Setup process

Get Your API Key
Sign up with Google or email to receive your key immediately.
Top Up with Crypto
Deposit USDT or USDC to activate your prepaid credit balance.
Configure Your Proxy
Update your base URL and API key in your client configuration.

Use cases

Uncensored Code Generation

Run Claude Code with alternative models without content filter interruptions.

High-Volume Data Processing

Process large documents using the 100,000 token context window efficiently.

Structured JSON Output

Generate reliable JSON responses for automated workflows using JSON mode.

Cost-Effective API Scaling

Avoid monthly fees by paying only for the tokens you actually use.

The Best claude code proxy for Uncensored Coding

This API bypasses subscription limits, letting you plug any model into Claude Code for a fraction of the cost.

Direct Model Routing

Use the uncensored model id to bypass content filters while keeping your existing client code intact.

Transparent Billing

Pay only for tokens used. Errors and refusals are free, with no hidden monthly fees.

Crypto Top-ups

Top up with USDT or USDC. Credit never expires, so you never lose your balance.

Checklist: How to Verify Your LLM Proxy Provider

Verify your provider by checking these six critical factors before switching.

Endpoint Compatibility: Ensure it supports POST /v1/chat/completions without unexpected routing.
Transparent Billing: Confirm per-token pricing matches actual usage, not inflated estimates.
Latency Reality: Test response times; proxy hops add noticeable delay.
Rate Limits: Check requests per minute to avoid sudden service interruptions.
Content Filters: Verify uncensored behavior for your specific use case.
Key Management: Prefer services allowing easy key rotation without downtime.

Common Developer Questions on Uncensored Proxy APIs

Yes, any OpenAI-compatible endpoint works with Claude Code if you update the base URL. This proxy uses the standard /v1/chat/completions route. You simply point your client to our base URL and set the model to uncensored. We support streaming, JSON mode, and function calling. Errors do not consume your prepaid credit. The system accepts only crypto top-ups via USDT or USDC. This approach bypasses subscription limits while keeping your existing code intact.

Real Cost Examples: Token Math for Your Budget

Our uncensored proxy API costs $0.15 per 1M input tokens and $0.50 per 1M output tokens.

For a 100K context request sending 2K tokens, you pay roughly $0.0005.

Even heavy usage stays cheap.

Prepaid credit never expires.

No hidden monthly fees.

Errors are free.

Usage	Cost
1M input	$0.15
1M output	$0.50

5 Signs You Need an Alternative Proxy API

Switch when your proxy locks you into a single expensive model. Ours accepts the "uncensored" ID via standard OpenAI endpoints. You control the backend without vendor fees. Verify our prepaid crypto billing and 100k context window. Stop paying monthly for limited access. Get transparent per-token rates instead.

Typical Proxy	Our Solution
Fixed Monthly Fee	Pay Only for Tokens
Single Vendor Lock-in	OpenAI Compatible SDK
Hidden Egress Costs	Transparent $0.15/$0.50 Rates

Common Mistakes When Switching LLM Proxies

Developers often overlook that uncensored models lack strict guardrails, requiring manual output validation. Others assume all proxies support streaming, yet our API requires SSE parsing for real-time token delivery. Ignoring the 8 MB request body limit causes silent failures. Many forget that prepaid crypto credit never expires, so budgeting differs from subscriptions. Verify your client handles the 300 requests-per-minute limit before scaling your automation workflow.

Common questions

What is a claude code proxy?

It is a middleware service rerouting requests to backend LLMs. Our proxy uses an OpenAI-compatible endpoint. It costs $0.15 per million input tokens. Errors incur no charge. This approach bypasses standard subscription limits.

Does the uncensored model refuse adult content?

Generally no, it answers controversial topics freely. However, requests involving minors are always refused. The model handles lawful adult use without standard filters. You retain full control over the content generation parameters.

How much does the API cost per token?

Input tokens cost $0.15 per million. Output tokens cost $0.50 per million. Errors and refusals are free. You pay only for actual usage. Prepaid credit never expires.

What payment methods are accepted for top-ups?

We accept only USDT on TRC20 or USDC on Base. Minimum top-up is $20. Bonus credit increases with larger deposits.

Is there a trial available for new users?

Yes, every new account receives $0.50 of trial credit. This balance is valid for seven days. You can test the API immediately.

What is the maximum output per request?

The limit is 16,000 tokens per request. The total context window is 100,000 tokens. If you omit the parameter, the default is 2,048 tokens. Streaming is supported via SSE.

Generate your key now

Open account