Use with Groq API (LLaMA 3, Mixtral 8x7b, Gemma 7b)

You can use AI models through Groq API on TypingMind.
Groq currently supports:
  • LLaMA 3 8b, LLaMA 3 70b
  • Mixtral 8x7b
  • Gemma 7b
Check out how to set it up on TypingMind! (Text guideline below)

Step 1: Log into Groq API

First, you will need to sign up for a DeepSeek AI account at https://console.groq.com/login
Image without caption

Step 2: Get Groq API key

  • Create a new API key
  • Copy the generated API key
Image without caption

Step 3: Set up Groq on TypingMind

  • Go to Manage Models
  • Add Custom Models
  • Updates the following information to set up Groq models:
    • Name: LLaMA 3 via Groq (or you can give it any name you want)
    • Icon URL (suggested): https://groq.com/favicon.ico
    • Endpoint: https://api.groq.com/openai/v1/chat/completions
    • Model ID: it can be llama3-8b-8192, llama3-70b-8192, llama2-70b-4096, mixtral-8x7b-32768, gemma-7b-it
    • Add Custom Headers:
    • Authorization: Bearer {{YOUR_API_KEY}} (enter the copied API key)
      Image without caption
  • Click Test
  • Click Update model

Step 4: Chat with Groq models

Now, you can choose the model and interact with it! Below is an example chat with LLaMA 3
Image without caption
Please note that plugins and streaming mode don’t work at the same time for Groq models.