Tools & keys · AI

Groq setup

The fast backup brain when Gemini is busy.

Recommended
Updated
Free tier
Groq offers a free tier with per-model rate limits and no card required.
checked September 2026
Larvabot's cap
Nothing to cap: rate limits just hand the job to the next provider.
Fallback position
#2 of 7 for AI. See the order

What it does

Groq runs open models (including OpenAI's open-weight gpt-oss models) on its own inference hardware, with an OpenAI-compatible API.

  • Automatic fallback for every AI step when Gemini is rate-limited or overloaded

Get set up

  1. Create an API key in the Groq console
  2. Paste it in Settings → AI → Groq API key
  3. Optional: set a different model name
Open Groq console

Where it goes

In the dashboard, open Settings and find the AI section. Secret values are encrypted before they're saved and only their last four characters are ever shown again.

Settings → AI
Groq API keyencrypted
GROQ_API_KEY
••••••••••••
Groq model
GROQ_MODEL
openai/gpt-oss-120b

Staying free

Larvabot tries AI providers in order and moves on when one is busy or rate-limited, so hitting Groq's limits just means waiting for the next run.

How the quota guard works →

Larva tip

Groq is the best second AI to add: it's fast, free and takes over the moment Gemini is busy.

Fallback order

For AI, Larvabot tries these in order and skips any that aren't set up, are out of free quota or are busy. AI providers also have to pass the quality check on the Jobs & providers page.

  1. 1Google Gemini
  2. 2Groq
  3. 3OpenRouter (:free models)
  4. 4Cloudflare Workers AI
  5. 5Cerebras
  6. 6Mistral
  7. 7Custom OpenAI-compatible (e.g. Ollama)

More AI tools

Curious why Groq made the cut? Groq in the free stack →

Keep going