Uncensored Inference

OpenAI compatible endpoint for uncensored inference

Drop-in openai compatible endpoint serving one uncensored LLM with 100,000 token context for reliable chat-completions without content refusals.

Claim trial key View documentation

100,000 token context window
$0.15 per 1M input tokens
No card needed for trial

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 a single call

curl https://api.openaicompatibleendpoint.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Return list of supported file formats"}]
  }'

from openai import OpenAI

client = OpenAI(base_url="https://api.openaicompatibleendpoint.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.openaicompatibleendpoint.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

Strict single model

We serve one uncensored model, not a router.

Standard SDK support

Works with any official OpenAI compatible client library.

Function calling ready

Full tool_choice and JSON mode support included.

Transparent per-token pricing

Pay only for real tokens used in requests.

Crypto top-ups only

USDT or USDC with bonus credits on deposit.

No training on prompts

Your data stays private and is never used for training.

Setup guide

Generate your key

Add trial credit

Receive $0.50 valid for 7 days to test the uncensored LLM.

Swap base URL

Point your SDK to our endpoint and start streaming responses.

Integrations

RAG systems

Leverage the 100,000 token context for long document processing.

Coding agents

Integrate uncensored reasoning into Cursor or other dev tools.

Content generation

Produce adult or controversial fiction without standard refusals.

API proxy routing

Use as a reliable drop-in replacement for standard providers.

Drop-in openai compatible endpoint for any OpenAI SDK

Our openai compatible endpoint delivers uncensored inference via standard chat-completions APIs, requiring zero code changes for existing integrations.

Direct SDK Integration

Connect using official libraries by updating only the base_url and API key.

Streaming Support

Receive real-time token streams via Server-Sent Events with usage data in the final chunk.

Structured Outputs

Enforce JSON mode for reliable parsing in automated workflows.

Tool Execution

Enable function calling with flexible tool_choice parameters.

Why developers choose an uncensored LLM for content

Provider Checklist

Verify the endpoint returns chat/completions without extra wrappers.
Confirm 100k context and 16k output limits.
Check for streaming SSE support.
Ensure function calling works with standard tools.
Validate JSON mode reliability.
Confirm no hidden content filters block lawful adult topics.
Verify per-token pricing matches advertised rates.
Test error handling for refusals.

How to swap your base_url in 3 lines of code

Replace your base URL and API key to connect instantly.

This change directs requests to our uncensored model without modifying your application logic.

Update the endpoint in your SDK configuration.
Insert your new key.
Run your existing code.

Our endpoint accepts standard parameters like temperature and top_p.

Streaming responses include token usage in the final chunk.

Pricing that scales with your token usage

You pay strictly for tokens used, not for idle capacity. Input tokens cost $0.15 per million and output tokens $0.50 per million. Errors and refusals incur zero charges. You can top up with USDT (TRC20) or USDC (Base) in whole amounts from $20 to $500. Bonus credits apply: +5% at $50, +10% at $100, and +15% at $200. No subscriptions. No monthly fees. Paid credit never expires.

Migrate Your Client Library in Three Steps

Switching providers requires only three configuration changes to your existing integration. First, update your base URL to point to our hosted endpoint. Second, replace your current API key with the one issued on your dashboard. Third, verify the model identifier is set to "uncensored". This drop-in replacement works with standard SDKs without code modifications. Your application continues processing text normally.

Who needs an uncensored LLM for coding and creative writing?

Developers integrating chat-completions into apps use this uncensored LLM for coding agents, self-hosted setups, and content generation without refusals. It powers Cursor workflows and custom integrations where standard models block creative or technical outputs. This is NOT for teams needing embeddings, audio, or fine-tuning. It is NOT for users requiring multiple model routing or enterprise SLAs. It is for developers who want raw inference utility via a single, reliable endpoint.

Common questions

What is an openai compatible endpoint and how does it work with standard SDKs?

It is a standardized API interface that accepts standard JSON payloads. You can switch to our service by updating the base_url in your existing code. The official OpenAI SDKs work without modification. This allows for a drop-in replacement that requires zero code changes. Your application logic remains intact.

Does this uncensored LLM refuse lawful adult content?

No. Our model is tuned to answer without content refusals for lawful adult use. It does not block controversial or fictional topics. The only hard limit is sexual content involving minors. Requests of that kind are refused. You get raw inference utility without arbitrary gates.

Is there a minimum amount required to top up credit?

The minimum top-up amount is twenty dollars. You can add up to five hundred dollars at once. Payments are accepted only via crypto. We support USDT on the TRC20 network. USDC on the Base network is also available.

How many tokens can the model process in a single request?

The context window supports one hundred thousand tokens total. This includes both the prompt and the completion. You can request a maximum output of sixteen thousand tokens. If you do not set max_tokens, the limit is two thousand four hundred eight tokens.

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.

Can I use function calling and JSON mode with this endpoint?

Yes. We support tools, tool_choice, and JSON mode. You can set the response_format to json_object. Streaming via SSE is also available. You can control temperature, top_p, stop sequences, and seed. All standard parameters work as expected.

Unlock your API key

Claim trial key