Uncensored API Proxy

OpenAI proxy: uncensored chat completions alternative

Drop-in openai proxy alternative serving the 'uncensored' model with 100,000 token context for developers who want no refusals.

100,000 token context window
Prepaid crypto billing only
No monthly subscriptions

Try with trial credit View documentation

100,000token context

$0.50trial credit

300requests per minute

Test with one call

https://api.proxyopenai.com/v1

curl https://api.proxyopenai.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "list all files in the src directory"}]
  }'

from openai import OpenAI

client = OpenAI(base_url="https://api.proxyopenai.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.proxyopenai.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 features

Drop-in Compatibility

Works with official SDKs by changing base_url and API key.

Uncensored Output

Answers without refusals for lawful adult, fictional, or controversial topics.

Streaming Support

SSE streaming includes token usage data in the final chunk.

Function Calling

Full support for tools and tool_choice parameters in requests.

JSON Mode

Force structured output using the response_format json_object setting.

Prepaid Credits

Pay only for tokens used with no monthly subscription fees.

Setup steps

Get Your Key

Update Configuration

Point your client to api.proxyopenai.com and set the model to uncensored.

Start Sending Requests

Make POST requests to /v1/chat/completions and receive text responses.

Common use cases

NSFW Content Creation

Generate adult content without hitting standard content filter refusals.

Local Model Bridge

Connect existing OpenAI-compatible clients to our uncensored hosted model.

Cost Predictability

Avoid subscription surprises with prepaid crypto billing and clear token costs.

Developer Integration

Use standard Python or Node SDKs with minimal code changes.

What is the openai proxy for uncensored content?

We are a direct API alternative that routes your requests through an uncensored model without content refusals.

Drop-in replacement

Swap your base_url and keep your existing code. This proxy mimics the standard interface.

NSFW content creation

Generate adult themes without blocking. Our model answers lawful topics freely.

Dev testing

Use the $0.50 trial. Test your integration with zero risk.

Switch from your current provider in three steps

Update your base URL and API key. Most OpenAI-compatible clients require only these two changes. Our endpoint uses the standard /v1/chat/completions path. Existing code runs without modification. We support streaming, tools, and JSON mode. Swap your configuration and verify the uncensored model responds correctly. This drop-in replacement works with any SDK that speaks OpenAI protocol.

Who should use this proxy and who should skip it

Use this uncensored LLM API when you need an openai compatible API that answers without refusals. It fits developers swapping OpenAI for proxy mode to enable NSFW content creation or sensitive research. Skip it if you require image generation, embeddings, or fine-tuning capabilities. This proxy handles only chat-completions. It also excludes users needing multiple model routing. Ideal for those seeking a direct, pay-as-you-go alternative without monthly subscriptions.

Worked cost examples: uncensored vs standard pricing

Our pricing is strictly per-token: $0.15 per million input tokens and $0.50 per million output tokens. Unlike standard vendors, errors are free and prepaid credit never expires. For a 10k input and 1k output request, the cost is $0.002. You pay only for what you use. No hidden fees or monthly subscriptions. This transparent model ensures predictable costs for high-volume NSFW content generation without content refusals.

Developers ask: proxy limits and compatibility

Our uncensored LLM API mirrors standard OpenAI endpoints but enforces strict concurrency limits. You get 300 requests per minute and eight simultaneous connections per key. The system accepts POST /v1/chat/completions with streaming support and JSON mode. It does not offer embeddings or image generation. Switching requires only a base URL change. Prepaid crypto billing ensures predictable costs without monthly subscriptions. Errors consume no credit.

Visit the Get API key page and sign up with Google or your email. No phone number is required.
Your unique API key appears instantly. Copy it to your clipboard.
Update your base_url to https://api.proxyopenai.com/v1 and set the key in your SDK.
Send a POST request to /v1/chat/completions with model uncensored to receive your first response.

Frequently asked questions

What is the openai proxy and how does it differ from standard models?

It is a hosted proxy serving one uncensored model. Requests for lawful adult topics rarely trigger refusals. Context windows support up to 100,000 tokens. Input costs $0.15 per million tokens. Output costs $0.50 per million tokens.

Do you support streaming responses for real-time applications?

Yes, we support streaming via Server-Sent Events. You receive tokens as they generate. Token usage data appears in the final chunk. Function calling works during streaming. JSON mode is also supported for structured outputs.

Which payment methods do you accept for topping up credit?

We accept crypto only. You can pay with USDT on TRC20 or USDC on Base. Minimum top-up is $20. Maximum top-up is $500. Bonuses range from 5% to 15% depending on amount.

Are there any monthly subscription fees or hidden costs?

No, we charge only per token usage. You pay for input and output tokens. Errors and refusals cost nothing. Prepaid credit never expires. No monthly subscriptions or recurring fees apply to your account.

What are the request limits per API key?

You can send 300 requests per minute. Only eight requests run simultaneously per key. Request bodies must stay under 8 MB. One active key is allowed per account. New keys replace old ones instantly.

Do you use my prompts to train the model?

No, your prompts are not used for training. We store only what is necessary for billing. Privacy is a core design principle. You can use the service for sensitive data. No phone number is required.

Get your key instantly