Groq api Quickstart

Prerequisites and Dependencies

Start by generating your groq API key on the dashboard. You can sign in with Google or use an email and password. No phone number is required. The key appears immediately for copy-pasting.

Ensure your environment supports the official OpenAI SDKs. Our base URL is HTTPS://api.apigroq.com/v1. This works with any client that accepts standard OpenAI endpoints. You do not need to install extra middleware.

Authenticating Your groq API Key

Pass your key in the Authorization header as a Bearer token. This authenticates every request to the uncensored AI service. If the key is invalid, you receive a 401 error. If you lack credits, you get a 402 error.

• Header: Authorization: Bearer YOUR_API_KEY
• Do not expose keys in client-side code.

Sending Your First Completion

Send a POST request to /v1/chat/completions. Use the model ID uncensored. This model answers without content refusals for lawful adult use. Set top_p to 1 and temperature to 0 for consistent results.

Copycurl https://api.apigroq.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "list dependencies in requirements.txt"}]
  }'

The response returns text only. No embeddings or images are generated. Errors do not consume your prepaid credit.

Handling Streaming Responses

Use Server-Sent Events for real-time token delivery. Set stream: true in your request. Each chunk contains partial text. The final chunk includes token usage details.

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)

This approach reduces perceived latency for large responses. Your client must handle the data: prefix and parse JSON objects.

Python SDK Integration

Install the official OpenAI Python package. Configure the client with our base URL and your key. This allows direct usage of the uncensored LLM without OpenRouter.

Copyfrom openai import OpenAI

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

The SDK handles retries and JSON parsing automatically. You can also enable JSON mode by setting response_format to {"type": "json_object"}.

Node SDK and Limits

Use the Node.js OpenAI client similarly. Set the base URL to our endpoint. Monitor your rate limits closely.

Copyimport OpenAI from "openai";

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

You are limited to 300 requests per minute per key. You can have 8 concurrent requests. The request body must stay under 8 MB. The context window is 100,000 tokens total. Max output is 16,000 tokens unless specified otherwise.