Uncensored API
OpenAI compatible api key for uncensored models
Get an openai compatible API key for instant chat completions with a 100,000 token context window and zero monthly fees.
- 300 requests per minute
- $0.15 per 1M tokens
- Crypto top-ups only
Test with one call
curl https://api.openaicompatibleapikey.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "Calculate the total price including tax"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.openaicompatibleapikey.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.openaicompatibleapikey.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);- $0.15
- per 1M input tokens
- $0.50
- Output tokens / 1M
- 100,000
- token context
- $0.50
- trial credit
- 300
- requests per minute
Core features
Prepaid credit
Pay only for tokens used and errors cost nothing.
Standard endpoints
Use POST /v1/chat/completions with any compatible SDK.
Long context
Process up to 100,000 tokens in a single request.
Streaming support
Receive real-time tokens via Server-Sent Events efficiently.
Tool use
Enable function calling for complex automated workflows.
JSON mode
Force structured output with response_format json_object.
Setup process
Sign up
Create an account using Google or email.
Get key
Retrieve your API key immediately upon registration.
Start coding
Configure your client with the base URL and key.
Common use cases
Cline integration
Connect the uncensored model to your coding assistant.
Hermes desktop
Add a custom endpoint to your desktop chat app.
NSFW generation
Generate unrestricted content without standard filters applied.
Research tools
Run secure local analysis without data training policies.
Your openai compatible API key for unlimited generation
Use this uncensored AI API key as a drop-in replacement for standard chat completions.
- Direct Integration: Swap your base URL and inject your key into any OpenAI SDK.
- Zero Filters: Generate adult or controversial content without unexpected refusals.
- Prepaid Tokens: Pay only for what you consume, not a monthly subscription.
Drop-in SDK Replacement
Point your existing client at our endpoint and keep your code unchanged.
Unrestricted Content
Get text output for any lawful topic without hidden guardrails.
Token-Based Billing
Credits never expire and errors cost nothing.
Uncensored LLM Access: Direct Key vs. Proxy Gateway
Direct API keys grant immediate access to our endpoint. Proxies add routing layers but strip streaming details. Our solution delivers unfiltered completions without intermediaries. You retain full control over parameters like temperature and top_p. No subscription fees apply. Pay only for consumed tokens via crypto top-ups. This approach ensures lower latency and precise token counting for NSFW content generation.
Stop wasting credits on refusals and filters
Most API keys charge you even when the model refuses your request. Our uncensored AI API key only bills for real token usage. Errors and refusals are free. You pay $0.15 per 1M input tokens and $0.50 per 1M output tokens. No monthly fees exist. Credit never expires. Use this key for unrestricted generation without paying for filtered outputs.
Get Your Uncensored API Key in 60 Seconds
Start generating text immediately after signing up with Google or email. You receive a unique API key instantly. Top up with crypto, then configure your client. Set the base URL to HTTPS://api.openaicompatibleapikey.com/v1. Use the model id "uncensored" for your requests. That is all you need to begin.
Is this the right uncensored API for your project?
Yes, if you need a drop-in OpenAI compatible API key for unrestricted generation without monthly fees. Unlike proxy services that resell expensive models, we provide direct access to a single uncensored LLM optimized for adult and creative use cases. Our pricing is strictly prepaid: $0.15 per 1M input tokens and $0.50 per 1M output tokens. You only pay for real usage; errors and refusals are free. Top-ups via crypto ensure instant credit with bonuses. This model avoids the subscription traps and filter overhead of typical alternatives.
Who should use our uncensored API and who should skip it
Use this uncensored API for NSFW chatbots, Cline, or Hermes where strict filters block creative work. It handles 100k context windows and streaming via SSE without monthly fees. Skip it if you need image generation, embeddings, or model routing. We serve one open-weight model, not a suite. It runs on any OpenAI-compatible SDK, but lacks fine-tuning or voice features. Ideal for developers needing unrestricted lawful adult content, not enterprise SLA requirements.
Frequently asked questions
What is an openai compatible API key and how does it work here?
It is a credential for the standard chat completions endpoint. You send POST requests to /v1/chat/completions using your unique key. This works with any OpenAI-compatible client or SDK without code changes, enabling immediate integration into your existing workflows.
Does the uncensored model block adult or controversial topics?
No, it does not block lawful adult, fictional, or controversial topics. The model is tuned to answer without standard content refusals. The only hard limit that always applies is sexual content involving minors, which is strictly refused.
How much does it cost to use the uncensored AI API?
Input tokens cost $0.15 per 1M, and output tokens cost $0.50 per 1M. Errors and refusals are free. You pay only for real token usage from your prepaid credit, which never expires, with no monthly subscription fees.
Can I add this key to Hermes Desktop or Cline?
Yes, you can use it with any OpenAI-compatible client. Set the base URL to HTTPS://api.openaicompatibleapikey.com/v1 and paste your key. The model ID is "uncensored". This works with Cline, Hermes, and other compatible tools.
What is the maximum context window for requests?
The context window supports 100,000 tokens for prompt and completion together. You can generate up to 16,000 tokens per request. If max_tokens is unset, the default output limit is 2,048 tokens, ensuring reliable performance for long conversations.
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.
Get your key now
Sign up, copy the key, update your base URL. That’s all there is to the configuration.
