Uncensored LLM API

Open ai proxy for uncensored inference

Drop-in uncensored LLM API for developers: change base_url to proxyaiopen.com, get 100k context, and start generating text instantly.

Pay $0.15 per 1M input tokens.
Zero monthly fees. Crypto only.
100,000 token context window.

Get API key View documentation

Test with one call

curl https://api.proxyaiopen.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Set model to uncensored adult variant"}]
  }'

from openai import OpenAI

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

OpenAI Compatible

Works with existing SDKs by changing base_url and key.

Uncensored Model

Answers without refusals for lawful adult content and fiction.

Transparent Pricing

Real token billing with errors and refusals charged at zero.

Crypto Payments

Top up with USDT or USDC using a simple wallet.

Streaming Support

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

JSON Mode

Enforce structured output using response_format json_object parameter.

Setup guide

Get Your Key

Update Base URL

Point your client to HTTPS://api.proxyaiopen.com/v1 instead of OpenAI.

Send Requests

Call POST /v1/chat/completions with model id set to uncensored.

Community projects

Content Generation

Create unrestricted stories, scripts, and creative writing without content filters.

API Migration

Swap OpenAI endpoints for uncensored inference without changing application code.

Research Analysis

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

Developer Testing

Test model behavior with function calling and streaming responses quickly.

Moving from another OpenAI-compatible provider in three steps

Swap your base URL and API key to enable uncensored inference without code changes.

Generate a new key via Google or email on our dashboard.
Update your client configuration to point to https://api.proxyaiopen.com/v1.
Send requests using the model ID uncensored.

Keep your existing Python or Node logic intact. You get 100,000-token context and streaming support immediately. Errors are free, so you can verify connectivity before spending your prepaid credit.

Why developers choose this open AI proxy for content freedom

Developers choose this open AI proxy for content freedom because it removes arbitrary refusals while maintaining strict OpenAI compatibility.

Zero-config migration

Swap your base_url and API key to access an uncensored LLM without rewriting code. We support streaming, tools, and JSON mode out of the box.

Transparent billing

You pay only for real token usage. Errors are free, and prepaid crypto credit never expires. No monthly fees or hidden subscription tiers.

Strict adult limits

We allow lawful adult content but always refuse sexual content involving minors. This clear boundary ensures reliable inference for diverse use cases.

Calculate your costs: transparent token pricing

Costs scale directly with token volume at $0.15 per million input tokens and $0.50 per million output tokens. For a 2,000-word prompt and 500-word response, you pay $0.0005. Errors and refusals cost nothing, so you only pay for successful content. Prepaid credit never expires, ensuring you retain unused funds indefinitely. This transparent model eliminates hidden fees or surprise charges from complex routing layers.

Who uses our proxy and who should skip it

Developers swap to this uncensored LLM when they need a drop-in base_url change without code refactors. Use it for creative writing or unrestricted research where standard filters block nuanced answers. Skip it if you require embeddings, image generation, or fine-tuning endpoints. It is not for teams needing model routing or multi-vendor billing. With a 100,000-token window, it fits single-turn heavy workflows perfectly.

Checklist: how to pick the right uncensored LLM proxy

Verify these six criteria before committing your production traffic to an LLM proxy.

Confirm strict openai compatible api compliance with the /v1/chat/completions endpoint.
Check for transparent, per-token billing without hidden monthly fees.
Ensure the uncensored LLM allows lawful adult content without arbitrary refusals.
Validate that your API key supports streaming via SSE.
Confirm crypto-only payment options like USDT or USDC.
Review rate limits to ensure they support your request volume.

Proxy vs. Gateway: 4 concrete differences

Proxies pass your requests through while gateways often reroute or pool traffic across multiple models. This proxy offers transparent token pricing at $0.15 per 1M input tokens and $0.50 per 1M output tokens, with no hidden fees. Unlike complex gateways, we provide a simple drop-in endpoint that requires only a base URL change. Our service supports crypto payments exclusively, avoiding traditional banking constraints entirely.

Common questions

What is an open AI proxy and how does it work?

It is a drop-in endpoint that routes requests to an uncensored LLM. Change your base_url and key in the SDK. We host the model, so you keep your code identical to standard OpenAI integrations.

Does the uncensored model refuse adult content?

No, it allows lawful adult topics. The only hard limit is sexual content involving minors. You get unrestricted creative freedom for standard adult use cases without extra configuration or flags.

How much does the uncensored LLM cost per token?

Input tokens are $0.15 per million, output tokens are $0.50 per million. Errors are free. We bill by real usage with prepaid crypto credit that never expires, ensuring transparent pricing.

Can I use streaming with this proxy?

Yes, streaming via SSE is supported. Token usage details appear in the last chunk. You can also use JSON mode and function calling tools with the same standard parameters.

What is the maximum context window size?

The model supports 100,000 tokens for prompt and completion combined. You can generate up to 16,000 tokens per request. Default output is 2,048 tokens if you do not set max_tokens.

Which payment methods do you accept?

Crypto only: USDT on TRC20 or USDC on Base, any whole amount from $20 to $500. Bonus credit applies from $50.

Get your API key

Get API key