Uncensored LLM API

LLM api gateway for uncensored generation

Swap your base_url and key to access an uncensored LLM API gateway via OpenAI-compatible endpoints, delivering 100,000-token context for reliable generation.

OpenAI chat-completions interface
Prepaid crypto billing only
100,000 token context window

Open account View documentation

Test with one call

curl https://api.gatewayapillm.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Explain how to configure Nginx for reverse proxying HTTPS traffic to a local Node server"}]
  }'

from openai import OpenAI

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

Capabilities

OpenAI Compatible

Use standard SDKs with a simple base_url change and keep your existing code structure.

Uncensored Generation

Our dedicated model answers without refusals for lawful adult, fictional, or controversial topics.

Prepaid Credit

Pay with crypto, get bonus credits, and never worry about monthly subscription renewals.

Large Context

Support prompts and completions totaling up to 100,000 tokens for deep analysis.

Function Calling

Execute tools and enforce JSON mode with standard OpenAI parameters and formats.

No Vendor Lock-in

Transparent per-token pricing ensures you only pay for actual usage without hidden fees.

Setup guide

Create Account
Sign up via Google or email to receive your immediate API key.
Top Up Crypto
Add prepaid credit using USDT or USDC to start your billing cycle.
Integrate Code
Update your client configuration with our base_url and key to generate text.

Community projects

Data Extraction

Parse large documents with high token limits without hitting refusal thresholds.

Creative Writing

Generate unrestricted narratives and stories for adult or mature audiences easily.

Research Analysis

Process complex queries without content filters blocking controversial or niche topics.

Chatbot Backend

Power unfiltered conversational agents with streaming support and tool execution capabilities.

Drop-in LLM API gateway with uncensored model

This LLM API gateway lets you swap your base_url and key to bypass refusals instantly.

Zero-config integration

Keep your existing OpenAI SDK code. Just change the endpoint and start generating.

Strict uncensored output

Get direct answers for adult, controversial, or security topics without content filters.

No vendor lock-in

Use one dedicated model. No hidden monthly fees or tier limits to worry about.

Start generating uncensored content immediately after account creation. Follow these simple steps:

Create your account. Use Continue with Google or enter your email and password on the Get API key page. No phone number required.
Retrieve your key. Your single API key displays instantly.
Configure your SDK. Update base_url to https://api.gatewayapillm.com/v1 and set your key.
Send a request. Call POST /v1/chat/completions with model: "uncensored" and receive your first token.

Transparent per-token billing: pay only for what you use

Real token pricing: no monthly surprises

Costs scale strictly with token volume. Input tokens cost $0.15 per million; output tokens cost $0.50 per million. Errors and refusals incur zero charge. You receive prepaid credit that never expires, billed only for actual usage. This model eliminates hidden monthly fees or tier limits. You pay exactly for the tokens processed in your requests.

Developers ask: proxy, limits, and censorship

Is this a proxy or a dedicated model?

We run a single uncensored model, not a multi-vendor router.

What are the rate limits?

Keys handle 300 requests per minute and 8 simultaneous connections. The API enforces these strictly.

How strict is the censorship?

It allows lawful adult and controversial topics. Only child sexual abuse material triggers a hard refusal.

Does it support streaming?

Yes, via Server-Sent Events. You receive real-time tokens until the final chunk contains usage data.

Pre-buying checklist for API stability

Verify your limits before you integrate.

Confirm the 300 requests per minute and 8 concurrent requests per key.
Check the 8 MB request body size.
Ensure the model supports streaming and JSON mode.
Validate that prepaid credit never expires.
Test that errors incur no token costs.
Confirm crypto-only top-ups from $20.
Verify the 100,000 token context window.

These constraints define your integration's reliability.

Avoid API pitfalls: context and tokens

Many developers ignore that the 100,000-token context window includes both prompt and completion. This often causes unexpected errors when streaming long outputs. Ensure your max_tokens stays below the limit, defaulting to 2,048 if unspecified. Also, verify that the 8 MB request body constraint does not truncate large payloads. Accurate token counting prevents billing surprises and ensures reliable, uncensored generation for your specific use case.

Common questions

What is an LLM API gateway?

It is a unified endpoint that routes requests to large language models. Ours serves a dedicated uncensored model via the standard OpenAI Chat Completions interface. You change your base_url and API key, keeping your existing code intact.

Do you support streaming responses?

Yes. We support Server-Sent Events (SSE) for streaming. The final chunk includes token usage statistics. This allows you to display generated text in real-time within your application or dashboard interface.

What is the context window size?

The model supports a 100,000-token context window. This total includes both the prompt and the completion. You can generate up to 16,000 tokens per request, or 2,048 if you omit max_tokens.

Can I use the official OpenAI SDK?

Yes. The endpoint is fully compatible with the official OpenAI SDK. You simply update your base_url and API key. This enables drop-in integration with any client that supports the standard Chat Completions interface.

How do I top up my credit?

You top up using crypto only. We accept USDT on the TRC20 network or USDC on the Base network. Minimum deposits start at $20. You can receive bonus credit based on your top-up amount.

Is there a free trial available?

Yes. Every new account receives $0.50 of trial credit. It is valid for seven days. This allows you to test the API immediately.

Get your API key instantly

Open account