Drop-in Uncensored API

Open router api: Drop-in Compatibility

Get an uncensored LLM endpoint with a 100,000 token context window for reliable, OpenAI-compatible generation without subscription lock-in.

POST /v1/chat/completions
Streaming via SSE
Crypto prepaid billing

Create key View documentation

Test with one API call

curl https://api.apirouteropen.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Show me the current status of the api endpoint"}]
  }'

from openai import OpenAI

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

Platform capabilities

Drop-in Compatible

Change base_url and key; keep your existing code.

Uncensored Inference

No refusals for lawful adult content or controversial topics.

Large Context Window

Handle 100,000 tokens for prompt and completion combined.

Streaming Support

Receive tokens in real-time via Server-Sent Events.

Function Calling

Use tools and tool_choice for structured interactions.

Prepaid Crypto Billing

Pay with USDT or USDC; credit never expires.

Setup workflow

Create Account

Get Your Key

Receive your API key immediately upon signup.

Top Up Crypto

Add credit via USDT or USDC to start.

Common use cases

High-Volume Text Gen

Scale uncensored inference without monthly subscription surprises.

AI Application Integration

Drop into existing OpenAI SDK clients easily.

Content Creation Tools

Generate unrestricted creative or adult content reliably.

Research Automation

Process large contexts without content refusal interruptions.

Common mistakes people make in this niche and how to avoid them

Developers often assume all endpoints handle streaming identically.

Mistake: Expecting image or embedding support in a chat-only proxy.
Avoid: Check the GET /v1/models response first.
Mistake: Sending large payloads without checking the 8 MB limit.

Always verify the content array structure before coding. This uncensored LLM endpoint supports function calling but not fine-tuning. Keep your payload under 8 MB.

open router API: Drop-in compatibility for uncensored inference

Yes, this open router API provides drop-in compatibility for uncensored inference by requiring only a base_url and key change.

Zero Code Changes

Swap the endpoint and key, then keep your existing scripts running without modification.

Standard Endpoints

Use POST /v1/chat/completions with full streaming support for real-time token delivery.

Crypto Billing

Prepaid credit never expires, ensuring no monthly surprises or subscription lock-in.

Worked cost examples with token arithmetic

Costs are transparent and calculated per token, not per request. Input tokens cost $0.15 per million, while output tokens cost $0.50 per million. Errors and refusals incur zero charges. You only pay for tokens successfully generated. Prepaid credit never expires, ensuring your balance remains available for future usage without monthly fees.

1M input tokens: $0.15
1M output tokens: $0.50

Who uses it, and who should skip it

Developers using it for high-volume text generation, automation pipelines, and uncensored AI workflows needing a simple drop-in API.

Best fit: Scripts requiring unlimited context (100k tokens) without subscription lock-in.
Not for: Teams needing image generation, embeddings, or multi-model routing. We serve one uncensored model, so if you need GPT-4 or Claude variants, this endpoint is not the right choice for your infrastructure.

How this differs from a typical alternative on 4-6 concrete signs

We are a single-model uncensored LLM gateway, not a multi-vendor router. You get true OpenAI compatibility with base_url and key changes only. Billing is prepaid crypto-only (USDT or USDC) with no monthly subscription. Credit never expires. We do not offer embeddings, images, or model routing. Errors and refusals cost nothing. Context is 100k tokens. Pricing is $0.15/1M input and $0.50/1M output tokens.

What developers actually ask about this topic

We support standard OpenAI SDKs by overriding the base URL. Streaming via SSE returns token usage in the final chunk. We do not offer embeddings, image generation, or fine-tuning endpoints. Errors and refusals incur zero charge. You can switch models by changing the request payload, though we serve one uncensored model. Top-ups require crypto only, with bonus credit for larger deposits.

Frequently asked questions

What is the open router API and how does it work?

It is a hosted, OpenAI-compatible chat-completions API serving one uncensored large language model. Change the base_url and key, keep your code. POST /v1/chat/completions sends text in, text out. Streaming via SSE provides token usage in the last chunk.

Is this service truly uncensored?

Yes. The model does not refuse lawful adult, fictional, security-research or controversial topics. A hard content limit always applies: no sexual content involving minors. Requests of that kind are refused. It is NOT GPT, Claude, Gemini, Grok, DeepSeek, Qwen, Llama or any other vendor's model.

How much does it cost per token?

$0.15 per 1M input tokens, $0.50 per 1M output tokens. Prepaid credit charged by real token usage; errors and refusals are free. No subscription, no monthly fee. Paid credit never expires. Context window is 100,000 tokens with a 16,000 token max output.

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.

Does it support streaming and function calling?

Yes. It supports streaming via SSE, function calling, and JSON mode. Parameters include temperature, top_p, stop, seed, presence_penalty, and frequency_penalty. Max output is 16,000 tokens per request. Limits are 300 requests per minute per key.

Is there a limit on requests per minute?

Yes. Limits are 300 requests per minute per key, 8 requests at the same time. The request body limit is 8 MB. One active key per account; a new key replaces the old one. Mistakes like double charges are fixed via Support.

Access your API key

Create key