Uncensored LLM API

MiniMax api: The Uncensored Alternative

Get a drop-in uncensored LLM via standard OpenAI endpoints with a 100,000 token context window for lawful adult use.

Uncensored LLM API for Devs

OpenAI-compatible chat-completions endpoint
Streaming via SSE supported
$0.50 per 1M output tokens

Test with one call

curl https://api.apiminimax.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the top 5 linux kernel versions"}]
  }'

from openai import OpenAI

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

Key features

Uncensored Output

Answers without corporate refusals for lawful adult or controversial topics.

Standard Endpoints

Uses POST /v1/chat/completions for seamless drop-in integration.

Large Context

Supports 100,000 tokens for prompt plus completion together.

JSON Mode

Enables structured outputs via response_format json_object parameter.

Crypto Top-ups

Accepts USDT (TRC20) or USDC (Base) with bonus credit.

Instant Access

Setup guide

Sign Up

Add Credit

Top up with crypto and receive bonus credit on larger deposits.

Send Requests

Point your client to our base URL and start generating text.

Built with API

RPG Narrators

Generate uncensored character dialogues without content filters interrupting the story.

Coding Assistants

Get raw code outputs without unnecessary polite explanations or refusals.

Data Extraction

Parse large documents using JSON mode with high token limits.

Content Research

Explore controversial topics without the model softening its answers.

1. Create your account and get a key instantly

Start by visiting the "Get API key" page and choosing "Continue with Google" or an email password. No phone number is required. The system displays your unique key immediately. You receive $0.50 in trial credit valid for seven days. Your prompts remain private and are not used for training.

Connect your existing OpenAI-compatible client

Redirect your API calls to our endpoint without rewriting logic.

Zero Config Switch

Update base_url to HTTPS://api.apiminimax.com/v1 and inject your key. The OpenAI SDK handles the rest.

Streaming Support

Receive real-time tokens via Server-Sent Events. Monitor usage in the final chunk.

Tool Support

Enable function calling with tool_choice. JSON mode works natively.

3. Send a prompt and receive uncensored output

We deliver raw text without corporate guardrails. Our API accepts standard requests and returns full context without filtering lawful adult or controversial topics. Typical proxies route traffic but may inject headers or limit throughput. We run our own tuned weights to guarantee the experience.

Feature	Typical Proxy	Our API
Model Source	Routes to vendor models	Our own uncensored weights
Refusals	Vendor-dependent	Minimal for adult content
Context Window	Varies by vendor	100,000 tokens

4. Monitor usage and top up your prepaid credit

Track your token consumption directly via the dashboard to avoid unexpected pauses. We charge by real usage: $0.15 per 1M input tokens and $0.50 per 1M output tokens. Errors are free. Add funds anytime using USDT (TRC20) or USDC (Base) from $20 to $500. Bonus credit applies automatically at higher tiers. Credit never expires, so you can top up only when needed without monthly subscription fees.

Common Integration Mistakes

Integrate the model into your application code by matching the expected payload structure. Developers often forget to set max_tokens, triggering the default 2,048 token limit. Always configure response_format for JSON outputs. Streaming via SSE requires parsing the final chunk for token usage. Omitting these details causes silent truncation or parsing errors in production pipelines.

Who Uses This Uncensored LLM API

Developers seeking an uncensored LLM for NSFW chatbot applications use this API for reliable, refusal-free text generation. Prompt engineers testing boundary conditions prefer this model’s direct response style over standard corporate filters. The service suits projects needing raw, open-weight output without enterprise overhead. It is not for teams requiring image, audio, or video generation capabilities. Users needing SOC2 certifications or on-premise deployments should look elsewhere, as this API focuses solely on chat-completions with a single, dedicated model.

Common questions

What is the minimax API and how does it differ from standard models?

It is an uncensored LLM API serving a single tuned model via OpenAI endpoints. Unlike standard models, it rarely refuses lawful adult, fictional, or controversial topics. Context window supports 100,000 tokens, enabling deep conversation without losing context.

How do I get started with the API without paying upfront?

Every new account receives $0.50 of trial credit valid for seven days. The key appears immediately on the dashboard, ready for your first request.

Does the uncensored model handle function calling and structured output?

Yes. It supports streaming, JSON mode, and function calling with tool definitions. You can control parameters like temperature, top_p, and seed. This allows precise control over response formatting for complex application integrations.

What payment methods are accepted for topping up my credit?

Credit is topped up with crypto only: USDT on TRC20 or USDC on Base. Any whole amount from $20 to $500 is accepted. Bonuses range from +5% to +15% depending on the top-up size.

Is there a limit on how many tokens I can generate?

The maximum output is 16,000 tokens per request. If you do not set max_tokens, it defaults to 2,048 tokens. The total context window, including prompt and completion, supports up to 100,000 tokens.

Does the company use my prompts to train other models?

No. Prompts are not used for training purposes. Privacy is prioritized, requiring only an email address for account creation. Your data remains private while you utilize the API for development and production workloads.

Get your key in seconds

Claim trial key

No subscriptions. Credits do not expire.