Skip to main content

Groq

Prefer guided AI setup?

Instead of following these steps manually, you can use the AI Credential Assistant — describe what you want to connect and the AI will walk you through the setup step by step, tailored to your account.

Overview​

Connect your Groq account to Nirvai to access ultra-fast AI inference powered by Groq's custom LPU (Language Processing Unit) technology. Groq offers some of the fastest inference speeds available for large language models.

Supported Authentication Methods​

  • API Key - Required

Prerequisites​

  • A Groq account
  • Access to the Groq Console

Setup Instructions​

Step 1: Create a Groq Account​

  1. Go to Groq Console
  2. Sign up for a free account or log in

Step 2: Generate an API Key​

  1. Navigate to the API Keys page in your Groq console
  2. Click Create API Key
  3. Enter a display name for your key (e.g., Nirvai Integration)
  4. Click Submit
  5. Copy the generated API key immediately (it won't be shown again)

Step 3: Add to Nirvai​

  1. In Nirvai, go to create a new Groq credential
  2. Paste your API key in the API Key field
  3. Save the credential

Important Notes​

  • Organization-bound keys: Groq API keys are bound to the organization, not the user
  • Free tier available: Groq offers a free tier with rate limits for testing
  • Fast inference: Groq's LPU technology provides extremely low latency responses

Available Models​

Groq provides access to various open-source models with ultra-fast inference:

  • Llama 3 (various sizes)
  • Mixtral
  • Gemma
  • And more

Troubleshooting​

API Key Not Working​

  • Verify you copied the complete key
  • Check if your key has been revoked in the console
  • Ensure you have available quota

Rate Limit Errors​

  • Check your current usage in the Groq console
  • Consider upgrading your plan for higher limits

Documentation adapted for Nirvai platform


Next Steps​

Got your credential? Connect it to an agent

Use the AI Tool Creator to turn this credential into agent-callable tools. Describe what your agent should be able to do and the AI investigates the API, configures the endpoints, and gives you a reviewable toolkit before saving anything.