Drop-in uncensored API

LLM router for uncensored API access

A single uncensored LLM router with a 100,000 token context window, ready to replace your current provider by changing one base_url.

OpenAI-compatible chat-completions endpoint
100,000 token context window
Prepaid crypto, no subscriptions

Try with trial credit View documentation

Test with one call

curl https://api.routerllm.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the top five python libraries for web scraping."}]
  }'

from openai import OpenAI

client = OpenAI(base_url="https://api.routerllm.cc/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.routerllm.cc/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

Drop-in compatibility

Swap your base_url and API key to use our uncensored model with existing OpenAI SDKs.

Uncensored responses

The model answers without content refusals for lawful adult use, except for minors.

Large context window

Process up to 100,000 tokens per request for complex document analysis.

Standard features

Supports streaming, function calling, JSON mode, and standard sampling parameters.

Transparent pricing

Pay only for tokens used, with no monthly fees or expiration dates.

Privacy focused

Minimal data collection and no training on your prompts during usage.

Setup process

Create account
Sign up with Google or email to get an API key instantly.
Top up crypto
Add credit via USDT or USDC to start using the API immediately.
Update endpoint
Change your client base_url to api.routerllm.cc/v1 and send requests.

Common implementations

Developer testing

Switch models for CLI tools to handle different task difficulties efficiently.

Content generation

Generate uncensored creative writing or roleplay without content filter interruptions.

Data analysis

Process large documents using the 100,000 token context window effectively.

API integration

Use as a drop-in replacement for OpenAI in existing applications.

Common Developer Questions About Uncensored Gateways

Does it support OpenAI SDKs? Yes. Change the base URL and API key to use our endpoint. Which model runs here? We serve one uncensored model tuned for adult content. How does pricing work? We charge $0.15 per million input tokens and $0.50 per million output tokens. Errors are free. Can I stream responses? Absolutely. We support Server-Sent Events for real-time streaming.

Why this LLM router fits your stack

This LLM router replaces complex routing logic with a single, uncensored endpoint.

Drop-in Compatibility

Change your base_url and API key. Keep existing code working without refactoring.

Predictable Pricing

Pay per token with prepaid crypto. Errors cost nothing. No monthly subscriptions.

Minimal Privacy

Get an API key instantly via Google or email. Your prompts stay yours.

Cost examples: uncensored vs. major providers

Our pricing is transparent and strictly per-token: $0.15 per 1M input tokens and $0.50 per 1M output tokens. Unlike complex routing tiers, this flat rate eliminates hidden fees for standard requests. For a 5,000-token prompt and 500-token response, you pay less than half a cent. Errors and refusals incur zero charges, ensuring you only pay for actual content generated. This predictable arithmetic simplifies budgeting for high-volume applications without vendor lock-in.

Common mistakes in LLM routing and pricing

Developers often confuse proxy routing with model selection. We serve one uncensored model, not a marketplace. Another error assumes all input tokens cost the same. Our pricing is $0.15 per 1M input and $0.50 per 1M output. You pay only for tokens actually used. Refusals and errors are free. This transparency prevents surprise bills when streaming long responses.

Who uses RouterLLM and who should skip it

Developers needing a single, uncensored model for lawful adult use without refusals.

Teams replacing complex routing with one base_url and key.
Users of CLI tools switching models based on task difficulty.

Skip if you need embeddings, image generation, or vendor model choice.

We serve only one open-weight model with a 100,000-token context window.

How to get started with our API

Sign up via Google or email to receive your API key instantly.
Top up prepaid credit using USDT or USDC, starting at $20.
Update your client’s base URL to HTTPS://api.routerllm.cc/v1.
Send requests to POST /v1/chat/completions with model uncensored.
Receive text responses with streaming support and real token usage.

Frequently asked questions

What is an LLM router and how does RouterLLM work?

It is a gateway that standardizes API calls. RouterLLM provides a single endpoint for one uncensored model. You send requests to our base URL and receive text responses without content refusals for lawful adult use.

Do I need to change my code to use this service?

No, you only update the base URL and API key. Our interface is fully OpenAI compatible. You can keep your existing SDKs and client libraries without modifying the core logic of your application code.

How much does uncensored API access cost per token?

It costs $0.15 per million input tokens and $0.50 per million output tokens. Errors and refusals incur no charge. You pay only for actual token usage with prepaid crypto credit that never expires.

Can I use this for streaming responses with function calling?

Yes, streaming via SSE is supported with token usage in the final chunk. You can also enable function calling tools and JSON mode. The model supports parameters like temperature, top_p, and stop sequences.

What is the context window limit for requests?

The context window is 100,000 tokens for prompt and completion combined. You can generate up to 16,000 tokens per request. If you do not set max_tokens, the default output limit is 2,048 tokens.

How do I top up my account balance?

You top up using USDT on TRC20 or USDC on Base. Minimum deposits start at $20. You receive bonus credit for larger amounts, with a 15% bonus for deposits of $200 or more.

Get your API key

Try with trial credit