Uncensored API

OpenAI gateway: uncensored chat completions

Drop-in uncensored LLM API with 100,000 token context for developers needing reliable, filter-free responses via standard OpenAI-compatible endpoints.

Create key View documentation

100k token context window
$0.15 per 1M input tokens
Crypto top-up only

Test with a single request

curl https://api.gatewayopenai.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List 5 Linux commands for disk usage"}]
  }'

from openai import OpenAI

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

Capabilities

Standard endpoint

POST /v1/chat/completions works with existing OpenAI SDK clients.

Deep context

Process 100,000 tokens per request for complex data analysis.

Direct pricing

Pay only for real token usage with no hidden monthly fees.

Crypto payments

Top up with USDT or USDC for privacy-first transactions.

Streaming support

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

No training usage

Prompts remain private and are not used for model training.

Setup process

Create account

Add credits

Top up with crypto to start using the uncensored model.

Connect code

Update your base_url and API key in your existing client.

Use cases

NSFW chatbot

Deploy adult-themed conversational agents without content filter interruptions.

Creative writing

Generate unrestricted fictional narratives and roleplay scenarios effectively.

Data processing

Analyze large documents using the full 100,000 token window.

Research analysis

Review controversial topics without standard model refusal mechanisms.

Why use an openai gateway for uncensored content?

An openai gateway lets developers route requests to a single uncensored model without proxy markup or vendor lock-in.

NSFW chatbot builders

Direct access to the uncensored model via POST /v1/chat/completions.
Streaming support with SSE for real-time token delivery.

Content creators

No hidden subscriptions; pay only for tokens used.
Crypto-only top-ups with bonus credit tiers.

Privacy-first devs

Prompts never used for training.
Simple email signup with no phone number required.

How to verify your gateway provider choice

Verify your provider by checking for a single model ID like uncensored rather than complex routing logic. Ensure pricing is transparent per token with no hidden subscription fees. Confirm crypto-only payments via USDT or USDC to guarantee privacy. Validate the base URL matches /v1/chat/completions and that streaming works via SSE.

Signs you are using a generic proxy, not a dedicated model

A generic proxy forwards requests to multiple vendors, creating routing complexity and potential latency spikes. Our implementation serves a single uncensored LLM directly, ensuring consistent behavior without hidden subscription fees or model routing overhead.

Feature	Generic Proxy	Our Gateway
Model Variety	Multiple vendors	One dedicated model
Pricing	Complex tiers	Direct token rates
Routing	Automatic	Direct endpoint

Get your uncensored response by creating an account, topping up crypto, and sending a request.

Sign up with Google or email to receive your API key instantly.
Add prepaid credit via USDT or USDC; no cards needed.
Point your OpenAI-compatible SDK to our base URL and send messages.

You receive text output with token counts in the final chunk.

Common gateway mistakes: context limits and token counting

Most developers hit 413 errors by ignoring the 8 MB request body limit, not just token counts. Our uncensored LLM handles 100,000 tokens total, but maxes at 16,000 output tokens per request. Set max_tokens explicitly to avoid unexpected cuts. Streaming via SSE ensures you see token usage in the final chunk, preventing overflows. Always validate payloads before sending.

Developers asking: how does this gateway compare to standard proxies?

We serve one uncensored model directly, avoiding the complexity of model routing found in generic proxies. Unlike standard OpenAI API proxies that simply forward requests to vendor servers, we host our own tuned open-weight model. This means no unexpected deprecations of the underlying model architecture. You get direct token pricing with no hidden subscription fees. Your client code remains compatible, but you gain predictable uncensored output without third-party content filters interfering with your API calls.

Common questions

What is the openai gateway service and how does it work?

It is a hosted API proxy. You send requests to our endpoint. We forward them to an uncensored model. The service handles token counting. Errors cost nothing. Input and output tokens are charged separately.

Does the uncensored LLM filter adult content?

No. The model answers without refusals for lawful adult topics. It only blocks sexual content involving minors. This hard limit always applies. You can use it for fiction or research. No other filters exist.

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.

What is the maximum context window size?

The window supports 100,000 tokens total. This includes both prompt and completion. Max output is 16,000 tokens per request. You can adjust limits via parameters. Streaming works via SSE for real-time updates.

How do I sign up for the API key?

Use Google or email plus password. The key appears immediately after signup. No phone number is required. You get one active key per account. Replace the old key to generate a new one.

Get your API key

Create key