How to Sign Up to Groq AI and Use it in SEO Content Machine

questions faq
1

As an alternative to running LLMs on your desktop you can sign up to Groq AI for fast API calls.

If you don’t have a beefy PC + GPU combo, Groq AI is a good option for running hosted AI models from inside SCM.

Advantages

  • You can get started with a free API key.
  • Groq AI inference times are very fast.
  • You can use current hosted models without running them on your PC.
  • Good option if local AI models are too slow for your machine.

Disadvantage

  • Low rate limits. You wont be able to run more than 1 AI thread
  • Rate limit wait times can be long. SCM is able to wait between calls to maximize throughput though

Want to use Groq AI inside SEO Content Machine?

Start SEO Content Machine free trial

Get Groq

Create a free account

image

Get your API key

Click the create api key button

image
image1282×631 28.6 KB

Paste key into SCM

API logins
Find Groq AI
Paste in API key

image
image1430×519 35.1 KB

Select model

Model names can change. At the time of writing, a good model to try is:

llama-3.3-70b-versatile

For a faster/lighter option, try:

llama-3.1-8b-instant

Test

Open AI chat

image
image157×185 2.02 KB

Verify

image
image368×413 12.5 KB

image
image858×425 7.78 KB

SCM can use Groq, Perplexity, OpenAI-compatible APIs, local models and more.>

Start SEO Content Machine free trial

1 Like
Connect SCM to LM Studio (llama3 etc) and run offline AI models for FREE
2

Hey @Tim,

I use Groq to generate short articles, and I see that I have just 6k tokens per minute.

Wouldn’t it be a good solution to add a field so that we can add a time for a pause between an item and another?

I can make 1 item, but when Groq goes to the next one, it rarely happens or makes an error, which could be avoided if you wait 1 minute before going to the next key word on the list, and I would say writing 1 item every 70 seconds would be ideal.

or what acha gives idea?

1 Like
3

Groq uses its own rate limit based on tokens, SCM automatically follows that limit set.

In detail, groq sends back a message when you make to many calls to wait xx number of seconds.

So you can use groq to its full token limit without any worries, SCM will wait as required.