OpenAI-compatible API for one uncensored model.
Uncensored GPT: an independent guide and a drop-in alternative
Drop-in uncensored gpt API for developers who want direct, refusal-free text generation without model routing complexity. Instant key generation and transparent per-token pricing.
- OpenAI-compatible endpoint
- $0.25 per 1M input tokens
- Zero-config streaming support
Try it in one request
curl https://api.uncensoredgpt.cc/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.uncensoredgpt.cc/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.uncensoredgpt.cc/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);What you get
Direct Model Access
We serve a single open-weight uncensored model, not an aggregator routing between vendors. This avoids hidden latency and ensures consistent behavior for your prompts.
Standard SDK Compatibility
Use the official OpenAI SDKs or any OpenAI-compatible client by simply updating the base_url and API key. No custom libraries or complex setup required.
Streaming & Tools
Full support for Server-Sent Events (SSE) streaming, function calling (tools), and JSON mode. Token usage details are included in the final chunk.
Transparent Pricing
Pay only for what you use: $0.25 per 1M input tokens and $1.00 per 1M output tokens. Errors and refusals do not consume credit.
Crypto Top-Ups
Top up with USDT (TRC20) or USDC (Base). No cards, no PayPal, no monthly fees. Credit never expires and bonuses apply at higher tiers.
Privacy Focused
Account creation requires only an email. Your prompts are not used for training data, ensuring your conversations remain private and secure.
How it works
- 1
Generate Key
Sign up with Google or email to receive your API key instantly.
- 2
Add Credit
Top up via crypto with USDT or USDC to start sending requests.
- 3
Integrate
Update your client base_url to https://api.uncensoredgpt.cc/v1 and begin.
What people build with it
Content Generation
Generate creative text, stories, or marketing copy without standard content filters blocking mature or controversial themes. Ideal for adult-oriented or unrestricted creative writing projects.
Security Research
Run prompt injection tests and vulnerability scans on LLMs without refusal mechanisms interfering with your test cases. Get raw model responses for accurate analysis.
Data Extraction
Extract structured data from text using JSON mode without the model refusing to output based on semantic content. Perfect for automated pipelines and ETL processes.
Roleplay & Chat
Build chat applications that allow users to explore diverse personalities and topics without arbitrary censorship. Supports long context windows for immersive interactions.
What is the Uncensored GPT API?
The uncensored gpt API is a hosted, OpenAI-compatible endpoint serving a single, high-performance open-weight model. Unlike aggregators that route requests across multiple vendors, we provide direct access to one tuned model designed to answer without content refusals for lawful adult use. This approach ensures predictable latency and consistent behavior, which is critical for developers building reliable applications.
Our API handles text input and output via standard endpoints. It does not offer embeddings, image generation, audio, video, or fine-tuning. The model is not GPT, Claude, Gemini, or any other vendor's model; it is an independent open-weight solution running on our servers. This simplicity means you get exactly what the model can do, without the complexity of managing multiple model IDs or routing logic.
OpenAI SDK Compatibility
Integration is straightforward because we adhere strictly to the OpenAI chat-completions standard. You can use the official OpenAI SDKs for Python, Node.js, and other languages by simply changing the base_url and providing your API key. The base URL is https://api.uncensoredgpt.cc/v1.
from openai import OpenAI
client = OpenAI(base_url="https://api.uncensoredgpt.cc/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)Key features include streaming via Server-Sent Events (SSE), function calling with tools and tool_choice, and JSON mode for structured outputs. Parameters like temperature, top_p, stop, seed, and penalties are fully supported. Context window is 64,000 tokens total, with a max output of 16,000 tokens per request.
Pricing: Pay Per Token
We charge transparently per token: $0.25 per 1M input tokens and $1.00 per 1M output tokens. Errors and refusals are free. There are no monthly subscriptions or hidden fees. Prepaid credit never expires, so you can top up when needed.
Top-ups are crypto-only via USDT (TRC20) or USDC (Base). You can add any whole amount from $10 to $500. Bonuses apply automatically: +5% for $50+ and +10% for $100+. New accounts receive $0.50 in trial credit valid for 7 days, no card required. Credit is not refunded, but double charges are fixed via Support.
Get Your API Key & Technical Specs
Sign up with Google or email + password to get your key immediately. No phone number is needed. Each account has one active key; generating a new one replaces the old. Rate limits are 300 requests per minute and 8 concurrent requests per key. Request bodies are capped at 8 MB.
Who this is NOT for: If you need model routing, embeddings, image generation, or SLA guarantees, this is not the right tool. We are a pure text API for developers who want direct, uncensored access. If you require SOC2/HIPAA certifications or on-prem deployment, look elsewhere. This is a developer-focused service, not a consumer chat app.
Questions and answers
Is this the official GPT model?
No. We serve an open-weight model tuned for uncensored responses. It is not GPT, Claude, or any other vendor's model. It is compatible with the OpenAI API format but runs on our own infrastructure.
What payment methods are accepted?
We accept only crypto: USDT (TRC20) or USDC (Base). No credit cards, PayPal, or bank transfers. Top-ups range from $10 to $500. New accounts get $0.50 trial credit, no card needed.
How does streaming work?
We support Server-Sent Events (SSE) for real-time token streaming. Token usage details, including input and output counts, are included in the final chunk of the stream. This allows you to track costs in real-time.
Is my data used for training?
No. Your prompts are not used for training data. We only require an email for account creation. Your conversations remain private and are not shared or used to improve other models.
What content is blocked?
The model is uncensored for lawful adult, fictional, and controversial topics. However, we enforce a hard limit: sexual content involving minors is always refused. All other content is permitted if lawful.
Your key is one form away
Create an account, copy the key, change the base URL. That is the whole setup.
