Uncensored LLM API Quickstart Guide

Prerequisites: Your API key and base URL

Start by generating your groq ai api key via the Get API key page. You can sign in with Google or use an email and password to receive your credential instantly. No phone number is required for this process.

Set your base URL to https://api.groqaiapikey.com/v1 in your client configuration. This endpoint supports the standard OpenAI SDKs, allowing you to swap providers without rewriting your integration logic. You only need one active key per account, as generating a new one replaces the previous key immediately.

First request: Sending a prompt to /v1/chat/completions

Send a POST request to /v1/chat/completions using your key in the Authorization header. The model identifier is simply uncensored, which processes text inputs and returns text outputs without content refusals for lawful adult use.

Ensure you set the Content-Type header correctly to avoid common 404 errors. Our API does not support embeddings, image generation, or audio processing, so keep your payloads focused on chat completions. This direct approach ensures you get transparent token pricing without multi-vendor proxy overhead.

Install the SDK: OpenAI compatible libraries

Install the official OpenAI Python package to interact with our endpoint using familiar methods. This library handles authentication and JSON serialization automatically when you point it to our base URL. You can use the same code structure you would use for GPT-4, but with our uncensored model.

For JavaScript developers, install the openai Node.js package. Both environments allow you to override the base URL easily. This compatibility means you can switch between different LLM providers by changing just two configuration lines in your code.

Handling streaming: SSE and token usage

Enable streaming by setting stream: true in your request parameters. The API returns Server-Sent Events (SSE) that deliver tokens incrementally as they are generated. This reduces perceived latency for users waiting for long responses.

Token usage statistics are included only in the final chunk of the stream. You must accumulate these deltas to calculate the total tokens consumed for billing purposes. Errors and refusals do not incur charges, so you can stream safely without worrying about unexpected costs for failed requests.

Advanced parameters: Temperature, JSON mode, and tools

Use temperature and top_p to control randomness and creativity in your responses. Set response_format to {"type": "json_object"} to force structured JSON output for reliable parsing in your applications. This is essential for building robust NSFW chatbot APIs or data extraction tools.

Enable function calling by providing a tools array. The model supports standard tool definitions and can choose to call functions based on your prompt context. You can also set max_tokens to 16,000, which is the maximum output per request. The context window supports 100,000 tokens total, including both prompt and completion.

Limits, errors, and billing specifics

Expect a 401 error if your key is invalid, a 402 error if you have insufficient prepaid credit, and a 429 error if you exceed the rate limit. You are limited to 300 requests per minute and 8 concurrent requests per key. The request body must stay under 8 MB.

Prices are $0.15 per 1M input tokens and $0.50 per 1M output tokens. Top-ups are crypto-only (USDT on TRC20 or USDC on Base) from $20 to $500. You receive a 5% bonus on $50, 10% on $100, and 15% on $200. Your prepaid credit never expires, so you can use it whenever you need it.

cURL

Copycurl https://api.groqaiapikey.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "What is the current API rate limit?"}]
  }'

Python

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.groqaiapikey.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)

Node.js

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.groqaiapikey.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);

Streaming

Copystream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)