Drop-in Replacement
API compatible uncensored LLM API
Swap your base_url and API key to get an uncensored LLM with a 100,000 token context window via this API compatible endpoint.
Open accountView documentation
- 100,000 token context window
- $0.15 per 1M input tokens
- Streaming, tools, JSON mode
- per 1M input tokens
- $0.15
- Output tokens / 1M
- $0.50
- token context
- 100,000
- trial credit
- $0.50
- requests per minute
- 300
Test with one API call
curl https://api.apicompatible.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "List available models"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.apicompatible.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.apicompatible.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);Key benefits
OpenAI SDK Compatible
Uses standard endpoints so existing code works without changes.
True Uncensored Output
Answers without refusals for lawful adult and controversial topics.
Generous Context Window
Handles 100,000 tokens of prompt and completion data.
Advanced Control Features
Supports function calling, streaming, and JSON response formatting.
Transparent Token Pricing
Pay only for tokens used with no monthly subscription fees.
No Card Required
Start with trial credit using only your email address.
Setup guide
Get Your Key
Sign up with Google or email to receive your key.
Update Base URL
Point your SDK to the provided API compatible endpoint address.
Send First Request
Execute your existing code to receive uncensored text responses.
Community projects
Local Model Gateway
Route traffic from local Llama or DeepSeek models via standard API calls.
Content Generation
Generate unrestricted creative writing or roleplay without content filters.
Automation Scripts
Integrate powerful reasoning into bots without rewriting client code.
Research Agents
Run continuous analysis agents that need long context windows.
The 6-Point Checklist for Choosing an Uncensored API Provider
Verify True Drop-in Compatibility
Check if the provider strictly implements /v1/chat/completions. True compatibility means you swap the base URL and API key without rewriting code.
- Endpoints: Confirm only
POST /v1/chat/completionsandGET /v1/modelsexist. - SDK Support: Test with the official OpenAI SDK to ensure zero code changes.
- Model ID: Ensure the response returns a simple, single model ID like "uncensored".
- Streaming: Verify SSE support with token usage in the final chunk.
- Pricing: Look for pay-per-token billing without monthly subscriptions.
- Content Policy: Confirm no refusals for lawful adult or controversial topics.
4 Concrete Signs You Are Using a True vs. Fake Alternative
True compatibility requires standard endpoints like /v1/chat/completions. Fake alternatives often add custom headers or non-standard behaviors that break your existing code. Verify the model ID returns correctly. Ensure streaming via SSE works without custom logic. Check if tool definitions and JSON modes function as expected. A true alternative behaves identically to the reference implementation, requiring only a base URL change.
| Feature | True Alternative | Fake Alternative |
|---|---|---|
| Endpoints | Standard OpenAI paths | Custom or missing paths |
| Streaming | SSE support | Custom logic required |
| Model ID | Correctly returned | Missing or wrong |
Why This API compatible Endpoint Fits Your Stack
It works because the endpoint strictly follows the OpenAI protocol, letting you swap the base URL and API key without touching your application code.
Drop-in Replacement
Change one variable in your configuration. The official SDKs recognize the response structure immediately.
Streaming Support
Receive tokens via Server-Sent Events for low-latency user experiences without complex parsing logic.
Tool Use Ready
Function calling works out of the box, enabling autonomous agents to execute actions seamlessly.
Who Uses This API and Who Should Look Elsewhere
Automation engineers use this uncensored LLM for unrestricted text generation where content filters cause friction.
- DevOps teams swapping OpenAI endpoints without code rewrites.
- Developers needing 100k context windows for long document processing.
Look elsewhere if you require image generation, embeddings, or fine-tuning, as we offer only chat-completions. We are not for teams needing multi-model routing or third-party vendor SLAs.
Migrate from OpenAI, Groq, or Ollama in Three Steps
Migrate from OpenAI, Groq, or Ollama in Three Steps
Replace your existing provider in three steps by swapping your base URL and API key. First, generate a key on our dashboard; second, update your base_url to our endpoint; third, send requests to the standard /v1/chat/completions path. This approach preserves your existing SDK logic while granting access to an uncensored model. You can immediately start generating text without modifying your codebase or handling complex routing configurations.
From Signup to First Token: How It Works
Start generating in minutes
Create your account via Google or email to receive an API key instantly. Top up with crypto to activate your prepaid credit. Update your client’s base URL to our endpoint and send your first request. You get text output without content refusals.
- Sign up with Google or email. The system generates your key immediately.
- Add crypto credit. USDT or USDC works. Minimum $20.
- Update your base URL. Point your SDK to our server.
- Send a chat completion request. Receive uncensored text output.
Common questions
What is an API compatible endpoint for uncensored text?
It is a standard OpenAI interface for a single uncensored model. Send prompts to POST /v1/chat/completions. Receive text responses. Change your base_url and API key to switch providers instantly without rewriting code.
What is the context window size?
The context window is 100,000 tokens for both prompt and completion. You can generate up to 16,000 output tokens per request. This allows processing large documents efficiently without complex chunking strategies.
How much does the uncensored LLM cost?
Pricing is $0.15 per million input tokens and $0.50 per million output tokens. Errors and refusals do not charge credit. Prepaid balance never expires, ensuring you pay only for actual usage.
What payment methods are accepted?
We accept only crypto for top-ups. You can pay with USDT on the TRC20 network or USDC on the Base network. Minimum deposits start at $20, and bonuses apply for larger amounts.
Is there a free trial available?
Yes, every new account receives $0.50 of trial credit. You can test streaming, function calling, and JSON mode immediately after signing up.
What features does the API support?
It supports streaming via SSE, function calling, and JSON mode. You can adjust temperature, top_p, and seed parameters. Request bodies are limited to 8 MB, with a rate limit of 300 requests per minute.
Get your key in seconds
Sign up, copy the token, update the endpoint URL. That is the entire configuration.
