OpenAI-Compatible
Uncensored llm chat API for Developers
Get your uncensored LLM chat API key instantly and start generating content with a 100,000-token context window today.
- Prepaid token billing
- No hidden subscriptions
- Crypto top-ups only
Test with one call
curl https://api.uncensoredllmchat.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "What is the capital of France?"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.uncensoredllmchat.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.uncensoredllmchat.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);Core capabilities
OpenAI-Compatible
Works with official SDKs by changing base_url and the API key.
Uncensored Output
Tuned model answers without refusals for lawful adult content and fiction.
Streaming Support
Full SSE streaming with token usage details in the final chunk.
Tool Calling
Native function calling with tool_choice and JSON mode support.
No Training
Your prompts are not used for training or data collection.
Simple Limits
300 requests per minute and 8 concurrent requests per API key.
Setup guide
Create Account
Sign up with Google or email and get your key instantly.
Add Credit
Top up via USDT or USDC with no card required for trials.
Start Coding
Point your client to the base URL and send requests now.
Common use cases
Uncensored Roleplay
Run unlimited character chats without hitting standard content filters or blocks.
Creative Writing
Generate long-form stories within the 100k context window without cuts.
Data Extraction
Parse large documents with JSON mode for reliable structured outputs.
Research Testing
Test models on controversial topics without unnecessary refusal interruptions.
How to get your API key and make your first request
Generate your key instantly, then send requests via standard OpenAI-compatible endpoints.
- Sign up: Use Google or email on the
Get API keypage; no phone number required. - Get credentials: Your API key appears immediately for direct use.
- Configure client: Set
base_urltohttps://api.uncensoredllmchat.com/v1and provide your key. - Send request: POST to
/v1/chat/completionswith modeluncensored. Errors and refusals incur zero charge.
See exactly what you pay: token cost examples
Transparent token billing
You pay $0.15 per 1M input tokens and $0.50 per 1M output tokens.
- A 500-token prompt with 1,000 tokens output costs $0.575.
- Errors and refusals incur zero charges.
Prepaid credit never expires. You only fund what you use.
uncensored LLM chat for roleplay, writing, and data
Our uncensored LLM chat API delivers reliable text generation without standard content filters for adult, fictional, or controversial topics.
NSFW Roleplay
Generate character responses that ignore typical guardrails, ensuring consistent tone and uncensored dialogue for immersive experiences.
Content Writing
Create mature narratives and articles without unexpected refusals, leveraging a 100k context window for long-form coherence.
Data Extraction
Parse unstructured text from diverse sources with high accuracy, using JSON mode for structured output without moderation interference.
Why our uncensored API beats the competition
Our uncensored API beats the competition by offering transparent prepaid billing with zero hidden subscription fees. Unlike typical alternatives that charge for refusals or limit context windows, we bill only for actual token usage.
| Feature | Typical Competitors | Our API |
|---|---|---|
| Billing Model | Monthly subscriptions | Prepaid credit |
| Content Policy | Varied refusals | No refusals except CSAM |
| Context Window | 4k-32k tokens | 100,000 tokens |
Migrate from OpenAI or Groq in three steps
Switch your integration by updating the base URL and API key. First, generate your uncensored LLM chat key via the dashboard. Second, update your client’s base_url to HTTPS://api.uncensoredllmchat.com/v1. Third, set the model to "uncensored" and ensure max_tokens is 16,000. This simple change routes requests to our dedicated server, eliminating unwanted refusals while maintaining full OpenAI SDK compatibility.
Avoid common billing and model mistakes
Developers often confuse our uncensored AI API with general-purpose alternatives, leading to unexpected costs or integration errors. We use a single model, "uncensored," not a routed vendor pool. Billing relies on prepaid crypto credit; errors are free, but subscriptions do not exist. Do not assume embeddings or image support are included. Verify your base URL points to api.uncensoredllmchat.com. Remember that max_tokens defaults to 2,048, not 8,192. Always check token counts to avoid rate-limit surprises.
Frequently asked questions
What is the uncensored LLM chat API?
It is a hosted, OpenAI-compatible endpoint. You send POST /v1/chat/completions and receive text. It serves one uncensored model. No images or audio. Use the base URL on this site with standard OpenAI SDKs for immediate integration.
Which payment methods do you accept?
Crypto only: USDT on TRC20 or USDC on Base, any whole amount from $20 to $500. Bonus credit applies from $50.
How much does it cost per token?
Input tokens cost $0.15 per 1M. Output tokens cost $0.50 per 1M. Errors are free. Prepaid credit never expires. You only pay for actual usage, ensuring transparent billing without hidden subscription fees or monthly charges.
What is the context window size?
The window holds 100,000 tokens total. You can request up to 16,000 output tokens. The default max is 2,048 tokens. This limit applies to both prompt and completion combined. Streaming via SSE provides token usage details.
Does it support function calling?
Yes. The API supports tools and tool_choice. You can also force JSON mode with response_format json_object. Parameters like temperature, top_p, and seed are fully available. Streaming returns usage data in the final chunk.
How do I get my API key?
Click Get API key and sign in with Google or email. The key appears immediately. You get one active key per account. A new key replaces the old one. No phone number is required for signup.
Get your API key
Sign up, copy the key, and update the base URL. Done.
