Groq
Groq's OpenAI-compatible chat-completions endpoint, selected with LLM_PROVIDER=groq, used to extract facts from conversations.
Enable it
bash
LLM_PROVIDER=groq
OPENAI_API_KEY=<groq-api-key>
OPENAI_BASE_URL=https://api.groq.com/openai/v1
OPENAI_LLM_MODEL=llama-3.3-70b-versatileConfiguration
| Variable | Default | Description |
|---|---|---|
LLM_PROVIDER | openai | Set to groq. |
OPENAI_API_KEY | (none) | Groq API key, sent as a bearer token. |
OPENAI_BASE_URL | https://api.openai.com/v1 | Point at Groq's endpoint: https://api.groq.com/openai/v1. |
OPENAI_LLM_MODEL | gpt-4.1-nano | A Groq-hosted model, e.g. llama-3.3-70b-versatile. |
Notes
- OpenAI-compatible: the provider reuses the OpenAI request handling and only differs by base URL, key, and model.
- You must override
OPENAI_BASE_URLto Groq's endpoint; its default points at OpenAI.