Uncensored LLM API
MiniMax api key for uncensored text generation
Get your minimax API key for an openai compatible API delivering 100,000 token context windows with zero monthly fees and strict prepaid billing.
- 100,000 token context window
- Prepaid crypto only
- No monthly subscriptions
Test with a single calluncensored
curl https://api.keyapiminimax.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "Generate a JSON object with keys id and name"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.keyapiminimax.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.keyapiminimax.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);Key capabilities
Uncensored Model
Get raw text output without refusals for adult, fictional, or research topics.
OpenAI Compatible
Swap your base_url and use the standard OpenAI SDK for chat completions.
Token Billing
Pay only for tokens used with errors and refusals charged at zero cost.
Crypto Top-ups
Add credit via USDT or USDC with bonus credits for larger deposits.
Streaming Support
Receive real-time tokens via SSE with usage data in the final chunk.
No Expiry
Your prepaid credit never expires so you can spend it at your own pace.
Setup process
Create Account
Sign up with Google or email to instantly receive your API key.
Add Crypto Credit
Top up with USDT or USDC to start sending requests immediately.
Update Base URL
Point your client to our endpoint and start generating uncensored text.
Common implementations
Roo Code Integration
Configure your IDE to use our custom base URL for uncensored coding assistance.
Telegram Bot Dev
Route bot requests through our API to avoid standard content filters.
Content Generation
Generate creative stories and roleplay scenarios without unexpected refusals.
Research Analysis
Process large documents within the 100,000 token window for deep analysis.
Does this uncensored LLM work with Cursor or Roo Code?
Yes, your token works with Cursor and Roo Code. Change the base URL to HTTPS://api.keyapiminimax.com/v1 and use model id uncensored. Set API Mode to Anthropic in Roo Code. You can route requests through these tools without extra setup. The service supports standard parameters like temperature and top_p. Function calling and JSON mode also work as expected. Streaming via SSE is fully supported.
Does the model filter NSFW content or roleplay?
No. The uncensored LLM answers without refusals for lawful adult use, including fiction and roleplay.
One hard limit always applies: requests involving minors are refused. This uncensored API key supports standard parameters like temperature and top_p for creative writing.
- No content filtering for general topics.
- Minors are strictly excluded.
It is not a proxy for major vendors. Check their docs for their specific rules.
minimax API key
No, this is not a proxy for Gemini, Claude, or Grok. Our service is an independent, self-hosted API offering a single uncensored model. You must update your client configuration to point to our base URL and use your unique token.
Independent Model
We do not resell other vendors. The model runs on our servers, providing a distinct uncensored alternative to standard OpenAI or Anthropic endpoints without routing through their infrastructure.
Prepaid credit model vs. subscriptions
You pay only for tokens used, not a recurring monthly fee. Errors and refusals incur zero cost, and unused credit never expires. This prepaid structure eliminates waste from idle capacity. You top up with crypto, starting at $20, with bonus credits for larger amounts. Unlike subscriptions, you only spend when you actually send requests, making it ideal for bursty workloads or experimental projects where predictability matters more than volume.
What are the request limits and context window sizes?
The API supports a 100,000-token context window with a 16,000-token output limit per request. You can send 300 requests per minute and process 8 concurrent requests. Each request body must stay under 8 MB. Errors do not consume your prepaid credit. Streaming works via SSE. Function calling and JSON mode are available. Setup is simple.
| Feature | Limit |
|---|---|
| Context Window | 100,000 tokens |
| Max Output | 16,000 tokens |
| Requests/Min | 300 |
| Concurrent | 8 |
Connect your client and send the first request
How to swap your base_url and start using the uncensored LLM
- Get your key: Sign in with Google or email on the
Get API keypage. Passmodel: "uncensored"and your new key.
Frequently asked questions
What is the minimax API key used for?
It authenticates requests to our uncensored text API. Send POST /v1/chat/completions with model "uncensored" via the standard OpenAI SDK. Input and output tokens are billed strictly by usage with no monthly fees.
Does the model filter NSFW content or roleplay?
No, it does not filter lawful adult content. Requests are answered without refusals for controversial or sexual topics. Only sexual content involving minors is strictly refused. Use the standard parameters like temperature to control style.
Is this a proxy for Gemini, Claude, or Grok?
No, it is an independent service running a distinct open-weight model. It is not GPT, Claude, Gemini, Grok, or any other vendor. You can swap your base_url to use our API with existing client code.
How does the prepaid credit model work compared to subscriptions?
You pay $0.15 per 1M input tokens and $0.50 per 1M output tokens. Errors are free. Credit never expires and is topped up via USDT or USDC. No monthly recurring fees or subscriptions are required.
What are the request limits and context window sizes?
The context window is 100,000 tokens with a 16,000 token output limit. You can send 300 requests per minute and run 8 concurrent requests per key. The request body is limited to 8 MB.
Can I use my key with Cursor or Roo Code?
Yes, any OpenAI-compatible client works. Set the base_url to HTTPS://api.keyapiminimax.com/v1 and enter your key. Tools like Cursor or Roo Code will route requests to our uncensored model using the standard SDK format.
Generate your API key instantly
Register, copy the token, update the endpoint. That is all you need to do.
