OpenAI-Compatible
Uses standard endpoints like /v1/chat/completions. Swap your base URL and API key to run existing OpenAI SDKs against our uncensored model.
Hosted uncensored LLM API
Hosted uncensored LLM API
Drop-in uncensored inference for your existing code. No monthly fees, no refusals, just raw model output via a standard OpenAI-compatible interface.
Try it in one request
curl https://api.ollamaapi.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.ollamaapi.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.ollamaapi.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);Uses standard endpoints like /v1/chat/completions. Swap your base URL and API key to run existing OpenAI SDKs against our uncensored model.
Handle massive prompts and long outputs without context loss. Supports up to 64,000 tokens total, with 16,000 output tokens per request.
Full support for SSE streaming, JSON mode, and function calling (tools). Control temperature, top_p, and seed for precise generation.
$0.25 per 1M input tokens and $1.00 per 1M output tokens. You pay only for real usage; errors and refusals are free.
Top up via USDT (TRC20) or USDC (Base). No credit cards, no PayPal. Get bonus credit on larger deposits.
Sign up with Google or email only. Your prompts are not used for training, and data is kept private.
Sign up with Google or email to get your API key instantly.
Add crypto to your account and receive your prepaid token balance.
Point your existing client to our base URL and start sending requests.
Generate uncensored creative writing, roleplay, or adult content without unexpected refusals. Ideal for applications requiring unrestricted narrative freedom.
Probe model behaviors and jailbreaks without paying for refusals. Test edge cases in a controlled, high-capacity environment.
Process large documents with the 64k context window. Extract insights without the constraints of smaller context limits.
Test your application's integration with LLMs using standard OpenAI-compatible code. Ensure your tools and JSON modes work correctly.
Most major providers filter output based on subjective content policies, often refusing lawful adult or controversial topics. Our API serves a single, high-capacity uncensored model tuned to answer without refusals for lawful use. You get raw model output, meaning fewer surprises when your application generates content. This is not a generic aggregator; we provide one optimized uncensored model with consistent behavior.
Unlike generic AI aggregators, we do not route between multiple vendors. You know exactly what model you are using. If you need multiple model choices or specific vendor features like image generation, this API is not for you. We focus strictly on high-quality, unrestricted text inference.
Our API follows the OpenAI Chat Completions specification. This means you can use the official OpenAI SDKs for Python, Node.js, and other languages without rewriting your code. Simply update the base URL to https://api.ollamaapi.top/v1 and provide your API key. The model ID is 'uncensored'.
Support includes streaming via Server-Sent Events (SSE), JSON mode for structured outputs, and function calling with tools. Parameters like temperature, top_p, stop, and seed are fully supported. Errors and refusals do not consume your credit, so you only pay for actual tokens generated.
from openai import OpenAI
client = OpenAI(base_url="https://api.ollamaapi.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)
We charge $0.25 per 1M input tokens and $1.00 per 1M output tokens. There are no monthly subscriptions, no hidden fees, and no minimum commitments. Your prepaid credit never expires, so you can use it when you need it. If a request fails or is refused, you are not charged for those tokens.
curl https://api.ollamaapi.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."}]
}'This model is not for you if you need a free tier, as we are prepaid only. It is also not for you if you require embeddings, image generation, or fine-tuning, as we offer a text-only API. For high-volume users, the per-token pricing is often more cost-effective than monthly subscriptions with usage caps.
We accept crypto-only billing via USDT (TRC20) or USDC (Base). You can top up any whole amount from $10 to $500. Larger deposits earn bonus credit: +5% for $50 and +10% for $100. We do not process credit cards, PayPal, or bank transfers, keeping overhead low and passing savings to you.
Every new account receives $0.50 of trial credit valid for 7 days. No card is needed to start. If you make a mistake, such as a double charge, contact Support. Credit is not refunded, but it never expires.
Our infrastructure supports 300 requests per minute per key and 8 concurrent requests. The maximum request body size is 8 MB. Each account gets one active API key; generating a new key replaces the old one. This setup is designed for developers who need reliable, high-throughput access without the complexity of managing multiple keys.
import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.ollamaapi.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);
Your privacy matters. An account requires only an email address; no phone number is needed. We do not use your prompts for training purposes. The model does not refuse lawful adult, fictional, or controversial topics, but it does block sexual content involving minors. This hard limit always applies. We are an independent service, not an official partner of any model vendor.
No, it is prepaid. You pay for tokens used. New accounts get $0.50 trial credit for 7 days. Errors and refusals are free.
Yes, it is fully OpenAI-compatible. Update the base URL and API key in your existing code to use our uncensored model.
We accept only crypto: USDT (TRC20) or USDC (Base). No credit cards, PayPal, or bank transfers. Top-ups range from $10 to $500.
It is uncensored for lawful adult, fictional, and controversial topics. It only blocks sexual content involving minors. Refusals do not cost credits.
The context window is 64,000 tokens for input and output combined. You can generate up to 16,000 tokens per request.
Your key is one form away
Create an account, copy the key, change the base URL. That is the whole setup.
Get API key