Uncensored LLM API
Copilot api key for uncensored generation
Get a copilot API key for an uncensored chat endpoint with a 100,000-token context window and transparent token pricing.
- Zero content refusals
- Crypto top-ups only
- OpenAI compatible
Test with one call
curl https://api.copilotapikey.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "Set system time to unix epoch 0."}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.copilotapikey.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.copilotapikey.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);- per 1M input tokens
- $0.15
- Output tokens / 1M
- $0.50
- token context
- 100,000
- trial credit
- $0.50
- requests per minute
- 300
Core capabilities
OpenAI Compatible
Drop into existing SDKs with the standard /v1/chat/completions endpoint.
Uncensored Model
Answer without filters for roleplay, adult themes, or controversial topics.
100k Context
Process massive documents with a 100,000-token combined context window.
Streaming SSE
Receive real-time token usage data and streamed text responses.
Function Calling
Use tools and JSON mode for precise structured output generation.
No Monthly Fees
Pay only for tokens consumed with prepaid credit that never expires.
Setup guide
Generate Key
Sign up with Google or email to receive your key instantly.
Top Up Crypto
Add funds via USDT or USDC to activate your prepaid credit.
Send Requests
Point your client to our base URL and start generating text.
Built with this
- NSFW Roleplay
- Run uncensored chatbots for adult gaming and interactive fiction stories.
- Coding Assistants
- Get unfiltered code suggestions without unnecessary content policy interruptions.
- Data Extraction
- Parse large documents using the extensive 100,000-token context window.
- API Development
- Integrate directly into your app using standard OpenAI compatible tools.
Checklist: 6 Signs Your LLM Provider is Hiding Filters
Verify uncensored capabilities by testing specific content refusals in your target domain. Check if the provider charges for failed requests or hidden usage. Ensure the API supports streaming via SSE for real-time token consumption. Confirm context windows handle your prompt size without arbitrary cuts. Verify that token pricing is transparent, not bundled into opaque subscriptions. Finally, check if the model is open-weight or a black box.
Why You Need a copilot API Key for NSFW and Roleplay
Our uncensored API endpoint delivers unfiltered text generation without content refusals for lawful adult use or creative roleplay scenarios.
Direct Context
Send 100,000 tokens of context to maintain continuity in long narratives.
Zero Filters
Receive raw outputs without curated restrictions on controversial or mature topics.
OpenAI Compatible
Swap your base_url and keep your existing client code working immediately.
Cost Calculator: Real Token Math for Your Project
Cost Calculator: Real Token Math for Your Project
Input tokens cost $0.15 per million, and output tokens cost $0.50 per million. A 50,000-token prompt paired with a 4,000-token completion totals 5.5 units, equating to exactly $0.000825. Errors incur zero charges, and prepaid credit never expires. You only pay for the tokens your uncensored model actually consumes during streaming or function calling.
Migrate from OpenAI or Groq in Three Steps
Switch to our uncensored LLM API by updating your base_url and model ID. First, replace the endpoint with HTTPS://api.copilotapikey.com/v1. Second, set the model to "uncensored" to bypass content filters. Finally, insert your new API key from the dashboard. This works with any OpenAI-compatible SDK. No retraining is required. You get immediate access to the abliterated model with transparent token pricing and zero monthly fees.
Ours vs. Typical Providers: 6 Concrete Differences
6 Concrete Differences
Our API removes content filters, unlike curated providers.
| Feature | Ours | Typical Providers |
|---|---|---|
| Content Filter | None (Uncensored) | Curated |
| Pricing | $0.15/$0.50 per 1M tokens | Complex tiers |
| Subscription | None | Monthly fee |
| Payments | Crypto only | Cards/crypto |
| Top-ups | $20-$500 | Variable |
| Model | Single uncensored model | Multiple vendors |
From Signup to First Token: How It Works
- Register via Google or email; no phone number required. Your API key appears immediately.
- Top up with USDT (TRC20) or USDC (Base) starting at $20.
- Configure your OpenAI-compatible SDK with base_url HTTPS://api.copilotapikey.com/v1 and your key.
- Send requests to
POST /v1/chat/completionswith model uncensored. - Receive raw text responses instantly, billed only for actual token usage.
Common questions
What is a copilot API key and how does it work?
It is a unique token for accessing our uncensored LLM endpoint. You send it in the Authorization header to POST /v1/chat/completions. It enables direct, unfiltered text generation without third-party routing or subscription locks.
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.
Which payment methods are accepted for topping up credit?
We accept only USDT on the TRC20 network and USDC on the Base network. You can top up any whole amount between $20 and $500.
How much does it cost to use the uncensored model?
Input tokens cost $0.15 per million and output tokens cost $0.50 per million. Errors and refusals incur no charge. Credit never expires, so you only pay for the actual tokens your project consumes.
Can I stream responses to see tokens as they generate?
Yes, the API supports streaming via Server-Sent Events (SSE). You receive partial responses in real-time. The final chunk includes the total token usage statistics for your request, allowing accurate billing tracking.
Is there a limit on how many requests I can make?
You are limited to 300 requests per minute and eight simultaneous connections per key. Each request body must not exceed 8 MB. Exceeding these limits results in standard HTTP rate-limit errors from the server.
Generate your token
Register, grab the key, update the base URL. That covers everything.
