Uncensored LLM API

OpenAI-api-compatible Uncensored Model API

Get a direct OpenAI-compatible endpoint for an uncensored model with a 100,000-token context window and transparent prepaid pricing.

100,000 token context window
No content refusals for lawful adult use
$0.50 per million output tokens

Create key View documentation

curl https://api.openaiapicompatible.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Return the current UTC timestamp in ISO 8601 format"}]
  }'

from openai import OpenAI

client = OpenAI(base_url="https://api.openaiapicompatible.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.openaiapicompatible.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);

$0.15per 1M input tokens
$0.50Output tokens / 1M
100,000token context
$0.50trial credit
300requests per minute

Key features

Drop-in Compatibility

Works with official SDKs by simply changing the base URL and API key.

Streaming Support

Get real-time token usage data via Server-Sent Events with every response chunk.

Tool Use Ready

Enable function calling and JSON mode for structured data extraction and automation.

Crypto Payments Only

Top up with USDT or USDC to receive bonus credit on larger deposits.

Instant Access

Privacy First

Minimal data collection with no phone number required and no training on prompts.

Setup guide

Create Account
Sign up with Google or email to receive your unique API key instantly.
Add Credit
Top up with USDT or USDC to access bonus credit and start using the API.
Start Coding
Update your base URL in your existing client code and send your first request.

Use cases

Uncensored Roleplay

Generate creative content without filters blocking lawful adult or controversial fictional topics.

Local Model Gateway

Connect OpenWeb UI or other tools to your local LLMs via a standard endpoint.

Developer Testing

Test your OpenAI SDK code with a drop-in replacement that ignores content policies.

Data Extraction

Use JSON mode and function calling to structure output for your applications reliably.

Why this openai-api-compatible endpoint matters

This endpoint delivers uncensored completions without filters, enabling direct integration into existing stacks.

Uncensored Content

Lawful adult topics pass through without refusal, ensuring consistent outputs for creative work.

Standard Integration

Use the same SDKs you know. Change the base URL and API key to switch instantly.

Predictable Costs

Pay only for tokens used. Prepaid credit never expires, keeping your operational overhead minimal.

Built for uncensored roleplay, writing, and coding

Developers use this API for creative roleplay, adult fiction, and coding tasks where content filters disrupt workflows.

Generate uncensored text with a 100,000-token context window.
Stream responses efficiently via SSE for real-time applications.
Use JSON mode for structured data outputs.

It is not for teams needing embeddings, image generation, or multi-model routing.

Who needs this API and who should skip it

Use this uncensored LLM API if you need lawful adult content without filters, require a 100,000-token context window, and prefer prepaid crypto billing over subscriptions. Skip it if you need embeddings, image generation, or fine-tuning, as we offer only chat completions. We also do not provide SLA guarantees or multi-model routing. If you require vendor-agnostic multi-model support, this single-model endpoint may not fit your stack.

7-point checklist for choosing an uncensored provider

Verify endpoint compatibility before migrating. Our API supports POST /v1/chat/completions and GET /v1/models. Ensure your client handles streaming responses correctly. Check token pricing transparency; we charge $0.15 per 1M input tokens and $0.50 per 1M output tokens. Confirm crypto-only top-ups via USDT or USDC. Limit request bodies to 8 MB. Verify no hidden subscription fees exist. Our prepaid credit never expires, and errors are free.

Common API migration mistakes and how to avoid them

Developers often misjudge costs by ignoring context window limits. Our uncensored LLM API enforces a strict 8 MB request body. If your payload exceeds this, requests fail immediately, wasting prepaid credits. Always set a max_tokens value. Without it, the model defaults to 2,048 output tokens. This prevents unexpected bill spikes. Verify your client code handles streaming SSE responses correctly to track token usage accurately.

Real token cost calculations using our pricing

Our prepaid model charges $0.15 per million input tokens and $0.50 per million output tokens, ensuring you only pay for actual usage. For a standard 10,000-token prompt generating 1,000 tokens, the cost is roughly $0.002. Errors and refusals are free, while streaming data returns usage in the final chunk. This transparent structure eliminates hidden monthly fees, allowing precise budget tracking for any volume.

Common questions

What is the openai-api-compatible uncensored LLM API?

It is a hosted service providing a drop-in endpoint for chat completions. We serve a single uncensored model via POST /v1/chat/completions. This allows you to integrate without vendor lock-in or content filters, ensuring lawful adult content passes through while keeping account data minimal.

Does the API support streaming responses?

Yes. We support streaming via Server-Sent Events (SSE). Token usage details are included in the final chunk of the stream. This ensures you can process real-time outputs efficiently while maintaining the standard behavior expected from OpenAI-compatible clients and SDKs.

How much does the API cost per token?

Input tokens cost $0.15 per 1 million tokens. Output tokens cost $0.50 per 1 million tokens. Errors and refusals are free. You pay only for what you use with prepaid credit, and your paid credit never expires, ensuring transparent pricing.

Can I use my own OpenAI SDK with this service?

Yes. Our base URL is HTTPS://api.openaiapicompatible.com/v1. You can use any official OpenAI SDK by changing the base_url and providing your API key. This ensures your existing code works immediately without requiring significant refactoring or custom client implementations.

Is there a minimum top-up amount?

No. You can top up any whole amount from $20 to $500. We accept USDT (TRC20) or USDC (Base). Bonus credit applies: +5% from $50, +10% from $100, and +15% from $200.

Does the API support function calling?

Yes. We support tools and tool_choice parameters. You can also use JSON mode via response_format. This ensures you can build complex applications that rely on structured outputs and tool execution without needing a separate infrastructure layer.

Get your API key