Drop-in Uncensored API
Uncensored LLM API for Developers
A single, purpose-built uncensored LLM with OpenAI-compatible endpoints. Change your base_url and key, keep your code.
- OpenAI-compatible endpoints
- No content refusals
- Privacy-first design
Try it in one request
curl https://api.llmmodelsapi.com/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.llmmodelsapi.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.llmmodelsapi.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);What you get
Drop-in Compatibility
Use the official OpenAI SDKs with zero code changes. Only update the base_url and API key.
Uncensored Output
Answers without refusals for lawful adult, fictional, or controversial topics.
100k Context Window
Supports 100,000 tokens for prompt and completion combined.
Simple Pricing
Pay-as-you-go prepaid credit. No monthly fees or subscriptions required.
Privacy First
Prompts are not used for training. Minimal data collection.
Streaming Support
SSE streaming and tool/function calling supported via standard endpoints.
How it works
Get Your Key
Sign up with email and password to receive your API key immediately.
Update Configuration
Set the base_url to https://api.llmmodelsapi.com/v1 and insert your key.
Send Requests
Call POST /v1/chat/completions with model id 'uncensored'.
What people build with it
AI Agent Development
Build agents that need reliable, non-refusal responses for complex reasoning tasks. Use the standard chat completions endpoint for structured output.
Content Generation
Generate creative fiction or adult content without unnecessary filters. Ideal for applications where creative freedom is prioritized over safety guardrails.
Security Research
Test model behavior on controversial topics without getting blocked. Run prompt injection tests using the 100k context window.
Chatbot Integration
Replace existing LLM providers with a drop-in uncensored alternative. Maintain your existing code structure with simple configuration changes.
Drop-in Compatibility
Most AI model API providers require you to rewrite your integration logic. Our API is designed to be a direct replacement for OpenAI's chat completions. You only need to change two things: the base_url and the API key. The endpoint remains POST /v1/chat/completions. Streaming works via Server-Sent Events (SSE), and tool calling functions exactly as you expect. This predictability means you can swap providers without debugging custom adapters.
from openai import OpenAI
client = OpenAI(base_url="https://api.llmmodelsapi.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)We do not route between multiple models. We run one uncensored large language model on our own GPU servers. This eliminates the latency and unpredictability of aggregator networks. You get consistent performance from a single, purpose-built engine.
Uncensored Output
Our model is tuned to answer without content refusals for lawful adult use. It does not block controversial, fictional, or security-research topics. This is critical for developers building AI agents that need to reason through edge cases or generate creative content without artificial constraints. The model is not GPT, Claude, Gemini, or any other vendor's model. It is an open-weight model optimized for direct responses.
There is one hard limit: sexual content involving minors is always blocked. Everything else is fair game. This clarity helps you design your application logic without guessing when the API might refuse a valid request.
100k Context Window
We support a 100,000 token context window for both prompt and completion combined. This allows you to process large documents or maintain long conversation histories in a single request. For most developer use cases, this is sufficient to handle complex reasoning tasks without splitting contexts.
Our uncensored llm api does not offer embeddings, image generation, or audio processing. If you need multimodal capabilities, this API is not the right choice. We focus exclusively on text-to-text chat completions with high reliability.
Simple Pricing
Pricing is transparent and usage-based. You pay $0.15 per 1M input tokens and $0.50 per 1M output tokens. There are no monthly fees or subscriptions. You preload credit and use it as needed. Credit never expires.
import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.llmmodelsapi.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);You can top up from $20 by crypto (USDT on TRC20, USDC on Base). We offer bonus credits: +5% from $50, +10% from $100, +15% from $200. New accounts get $0.50 in trial credit for 7 days, no card needed. This low barrier to entry lets you test the API before committing funds. Claim this credit with one click on your API key page. Limits are 300 requests per minute per key and an 8 MB request body.
Questions and answers
Is this API compatible with the OpenAI SDK?
Yes. It uses the same POST /v1/chat/completions endpoint and response format. You only need to update the base_url to https://api.llmmodelsapi.com/v1 and provide your API key. Streaming and tool calling work as expected.
What is the model id to use?
Use the model id 'uncensored' in your API requests. This is the single model we host, tuned for no refusals.
Do you use prompts for training?
No. We do not use your prompts for training. Your data privacy is protected. You only need an email and password to sign up.
How do I get started with trial credit?
Sign up on the 'Get API key' page with your email and password. You receive $0.50 in trial credit valid for 7 days. Claim this credit with one click on your API key page. No credit card is required to start.
What are the rate limits?
You are limited to 300 requests per minute per API key. The maximum request body size is 8 MB. You can regenerate your key at any time to invalidate the old one.
Your key is one form away
Create an account, copy the key, change the base URL. That is the whole setup.
Guides
Practical articles on setup, pricing and integration.
LLM API in Python: Chat, Streaming and Tool CallsA short llm api python walkthrough with the OpenAI SDK: first call, streaming, tool calling, JSON mode, 429 retries and token costs against an…
LLM API vs Subscription: Which Costs Less?LLM API vs subscription, worked out: break-even math for pay-per-token at $0.15 and $0.50 per 1M against a flat monthly plan, for three types of user.
LLM Models API for Agents: Tool Calling GuideBuild an agent loop on an OpenAI-compatible LLM models API for agents: system prompt, tool calling, retries on 429, context limits and a worked…
How to Use an LLM Model Through an API, Step by StepLearn how to use LLM model endpoints with working code: get a key, send a chat request, stream tokens, force JSON and call tools using the OpenAI SDK.
Free LLM API to Use: Trial, Limits and Real CostsIs there a free LLM API to use? Here is what the $0.50 trial buys, what each request costs per token, and when prepaid credit from $20 makes more…
Best AI API: A Production ChecklistAccess an uncensored LLM API with pay as you go pricing. No censorship, OpenAI-compatible. Start using it now.