Uncensored LLM API. Prepaid. No fluff.

uncensored LLM API: independent guide and drop-in alternative

A direct, prepaid API for uncensored LLM inference. Drop-in OpenAI compatible code, zero vendor lock-in, and transparent token billing.

Get API key Read the docs

Try it in one request

curl https://api.ornith.top/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
  }'

from openai import OpenAI

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

Prepaid billing by card or crypto
100k context window
No data training

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

What you get

Uncensored Inference

Open-weight model tuned to answer without refusals for lawful adult, fictional, or controversial topics. It is not GPT, Claude, or any other vendor model.

Transparent Billing

Pay per token with prepaid credit that never expires. Errors and refusals are free. Top up by card (Visa, Mastercard, Apple Pay, Google Pay) or crypto (USDT on TRC20, USDC on Base) starting at $20.

OpenAI Compatible

Uses standard /v1/chat/completions endpoints. Works with official SDKs by changing base_url and API key. Supports streaming, JSON mode, and tools.

Privacy First

Prompts are not used for training. Sign up with Google or email. No phone number required, and credit is non-refundable but perpetual.

Generous Context

100,000 token context window for prompt and completion combined. Max output is 32,000 tokens per request, or 2,048 if unspecified.

Simple Limits

300 requests per minute per key with 8MB body limit. One active key per account; a new key replaces the old one instantly.

How it works

Sign Up
Create an account with Google or email to receive your API key immediately.
Top Up
Add prepaid credit by card (Visa, Mastercard, Apple Pay, Google Pay) or crypto (USDT on TRC20, USDC on Base) for instant activation.
Integrate
Update your OpenAI SDK client to point to our base URL and use your key.

What people build with it

Content Generation

Uncensored model ideal for creative writing or roleplay without standard refusals. Use JSON mode to structure outputs reliably.

Security Research

Analyze prompts or code without content filters blocking legitimate technical queries. No training on your data ensures privacy.

Developer Prototyping

Drop-in alternative for testing prompt engineering with standard OpenAI SDK code. Get started quickly with a free trial.

Data Annotation

Generate labels or classifications without bias from standard safety layers. Pay only for actual tokens used in requests.

Why Ornith?

Ornith provides a straightforward, uncensored API for developers who want control without enterprise complexity. Unlike major vendors that bundle features you may not need, we offer a single, open-weight model optimized for direct inference. The model is tuned to answer without refusals for lawful adult use, making it suitable for content generation, security research, and creative tasks. We do not train on your data, ensuring your prompts remain private. The billing is transparent: you pay per token, and errors are free. Prepaid credit never expires, so you only pay for what you use. This is a no-nonsense alternative for developers who prefer crypto simplicity and zero vendor lock-in.

Pricing: Pay Per Token

Our pricing is simple and transparent. Input tokens cost $0.15 per 1M, and output tokens cost $0.50 per 1M. You preload credit by card (Visa, Mastercard, Apple Pay, Google Pay) or crypto (USDT on TRC20, USDC on Base), and usage is deducted in real-time. Errors and refusals do not consume your balance. Top-ups start at $20 and go up to $500. Credits never expire, so you can top up when convenient. No monthly fees, no subscriptions. If you make a mistake, such as a double charge, contact support. The trial gives you $0.50 for 7 days, no card needed. Claim this credit with one click on your API key page.

How It Works

Getting started is fast. Sign up with Google or email to get your API key instantly. The key is shown immediately and works with any OpenAI-compatible client. Update your base_url to https://api.ornith.top/v1 and set your model to uncensored. The API supports streaming via SSE, JSON mode, and function calling. You can use parameters like temperature, top_p, and stop. Requests are limited to 8MB body size. You get 300 requests per minute and 8 concurrent requests. One key per account; a new key replaces the old one. This is an API, not a chat app.

Who This Is Not For

This API is not for you if you need embeddings, image generation, audio, or video. We do not offer fine-tuning, model routing, or SLA guarantees. If you need SOC2, HIPAA, or ISO certifications, this is not the right fit. We do not offer a chat website or app; this is for developers using SDKs. If you require multiple model choices or on-prem deployment, look elsewhere. We focus on a single uncensored model with straightforward, prepaid billing. No enterprise SLAs, no complex tiers. Just text in, text out, with transparent token costs.

Questions and answers

What is the uncensored model?

It is an open-weight model run on our servers, tuned to answer without content refusals for lawful adult use. It is not GPT, Claude, Gemini, Grok, DeepSeek, Qwen, Llama, or any other vendor's model. It accepts standard OpenAI SDK code.

How do I top up my credit?

You can top up by card (Visa, Mastercard, Apple Pay, Google Pay) or crypto (USDT on TRC20, USDC on Base). Any whole amount from $20 to $500 is accepted. Credits never expire. You get +5% bonus from $50 or more, +10% from $100 or more, and +15% from $200 or more.

Is there a free trial?

Yes. New users get $0.50 of trial credit valid for 7 days, one per person, no card needed. Claim this credit with one click on your API key page. You can sign up with Google or email. The trial is sufficient to test the API and integration.

Do you use my data for training?

No, prompts are not used for training. We value privacy and do not store your data for model improvement. An account needs only an email, and you can sign up without a phone number.

What are the rate limits?

You get 300 requests per minute and 8 concurrent requests per key. The request body limit is 8 MB. You can have one active key per account; a new key replaces the old one. Errors and refusals are free and do not count against your tokens.

Your key is one form away

Create an account, copy the key, change the base URL. That is the whole setup.

Get API key