Uncensored API

OpenRouter pricing: The Uncensored Alternative

Get an openai compatible API endpoint for uncensored text generation at $0.15 per 1M input tokens with prepaid crypto billing that never expires.

100,000 token context window
Prepaid credit never expires
Crypto only top-ups

Start now View documentation

Test with a single request

curl https://api.pricingopenrouter.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Set the budget limit to five dollars for this week."}]
  }'

from openai import OpenAI

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

Core features

OpenAI Compatible

Works with official SDKs by changing base_url and the API key.

Uncensored Output

Open-weight model tuned to answer without refusals for lawful adult use.

Streaming Support

Get real-time tokens via SSE with usage details in the last chunk.

JSON Mode

Force structured output using response_format json_object for reliable parsing.

No Vendor Lock-in

Drop-in replacement that runs the same client code as other providers.

Transparent Billing

Errors and refusals are free; you only pay for real token usage.

Setup guide

Create Account

Top Up Crypto

Add USDT or USDC to your prepaid credit balance instantly.

Make Requests

Send POST requests to /v1/chat/completions using your uncensored model.

Common use cases

Creative Writing

Generate unrestricted fiction without hitting standard content filters or refusals.

Data Aggregation

Process large batches of text with a 100k context window efficiently.

Developer Testing

Test your integration code with a stable uncensored LLM endpoint.

API Integration

Swap in this API as a drop-in alternative for existing clients.

Who Uses This API and Who Should Skip It

Developers needing a single, uncensored LLM for unrestricted content generation use this API. Creators building agent workflows or fine-tuning data pipelines value the 100,000-token context window and OpenAI-compatible endpoint. Skip it if you require image generation, embeddings, or model routing between multiple vendors. This service delivers one specific uncensored model via standard chat-completions endpoints, not a multi-model aggregator.

Four Concrete Signs This Is Not a Proxy

Our API runs a single uncensored model on our own servers, eliminating the proxy markup and vendor lock-in common in typical alternatives.

Feature	Typical Alternative	Ours
Routing	Complex routing across multiple vendors	Single direct model
Billing	Monthly subscriptions or per-model fees	Prepaid crypto, no expiry
Costs	Hidden tier costs	Transparent token math
Content	Variable refusal rates	Uncensored for lawful use

openrouter pricing: Real-World Cost Scenarios

The raw math shows our uncensored API costs significantly less than proxy aggregators for high-volume text generation.

Chat Completion Efficiency

A standard 100-token prompt generates 50 tokens of output for $0.04. This is cheaper than most multi-model aggregators.

Streaming Overhead

Streaming via SSE adds zero extra latency cost. You pay for the final token count, not the connection duration.

Error Resilience

Server errors do not consume your prepaid credit. Only successful completions bill against your balance.

Common Billing Mistakes in the Uncensored Niche

Developers often assume uncensored LLM APIs charge per request or bill for refusals, inflating costs unexpectedly. Our model charges strictly by token usage; errors and refusals are free. Avoid hidden proxy markups by verifying the base API rate. Unlike aggregators adding 5.5% fees, we offer transparent, direct pricing. Always check your token math against real usage, not just request counts, to ensure accurate budgeting for your uncensored AI projects.

Start generating text in under two minutes using this straightforward workflow.

Create an account: Sign in with Google or email; no phone number required.
Get your key: Your API key appears immediately on the dashboard.
Configure your client: Update your base URL to our endpoint and insert the key.
Send a request: Use the standard chat-completions endpoint with the uncensored model ID.
Receive output: Get a direct text response with no hidden routing fees.

What Developers Actually Ask About This Setup

They ask if our uncensored LLM is a proxy, whether the prepaid crypto billing truly lacks hidden fees, and how our pricing compares to alternatives like DeepSeek or OpenRouter. We confirm it is a direct API with no vendor lock-in, charging only for real token usage. Errors and refusals remain free. You can top up via USDT or USDC with bonus credit tiers, while maintaining a transparent, open-weight model experience without monthly subscriptions or complex routing.

Frequently asked questions

What is the openrouter pricing comparison for this uncensored API?

Our rates are $0.15 per 1M input tokens and $0.50 per 1M output tokens. Errors and refusals incur zero charges. You pay only for actual usage with prepaid credit that never expires.

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 does the trial credit work for new accounts?

Every new account receives $0.50 in trial credit. Sign up via Google or email to claim it immediately.

Is the uncensored model the same as GPT or Claude?

No. We serve our own open-weight model, not a vendor's product. It runs on our servers and does not include GPT, Claude, or other external model routing.

What are the limits on requests per minute?

You can send 300 requests per minute per key. Concurrent requests are limited to 8 at the same time. Each request body must not exceed 8 MB.

Do prompts get used to train the model?

No. Your prompts are not used for training. Privacy is maintained because we do not reuse your data for model improvement, ensuring your conversations remain private.

Generate your API key

Start now