Skip to content

Chat Groq

Run open models on Groq for fast, low-latency inference.

Provides access to open-weight models served on Groq’s low-latency inference infrastructure for AI agent nodes. Groq exposes an OpenAI-compatible API, so this node runs the OpenAI client against Groq’s base URL.

Connect this to AI agents when you want fast, low-latency inference on open models such as llama-3.3-70b-versatile.

SettingNotes
ModelThe Groq model to use, e.g. llama-3.3-70b-versatile. Placeholder: llama-3.3-70b-versatile.
AuthenticationCredential used to authenticate: “Use your Groq API key as a Bearer token.”
Options → TemperatureThe temperature to use for the model.
Options → Max RetriesThe maximum number of retries to use for the model. Defaults to 2.

Returns a chat model dependency that can be connected to AI agent nodes.

  • Requires an Authentication credential holding your Groq API key, sent as a Bearer token.
  • The node throws an error if Model is empty.

Connect Chat Groq to an AI agent or dependency input that accepts this dependency type, set the Model to a Groq-hosted model such as llama-3.3-70b-versatile, attach your Groq API key credential, then run the agent with data from previous nodes.

  • Ensure Model is filled in — the node rejects an empty value.
  • If it calls an external service, verify credentials, permissions, and rate limits.
  • No dedicated source test was found next to this node; verify behavior manually when changing this page.