Chat Groq
Chat Groq
Section titled “Chat Groq”Run open models on Groq for fast, low-latency inference.
What it does
Section titled “What it does”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.
When to use it
Section titled “When to use it”Connect this to AI agents when you want fast, low-latency inference on open models such as llama-3.3-70b-versatile.
Inputs and settings
Section titled “Inputs and settings”| Setting | Notes |
|---|---|
| Model | The Groq model to use, e.g. llama-3.3-70b-versatile. Placeholder: llama-3.3-70b-versatile. |
| Authentication | Credential used to authenticate: “Use your Groq API key as a Bearer token.” |
| Options → Temperature | The temperature to use for the model. |
| Options → Max Retries | The maximum number of retries to use for the model. Defaults to 2. |
Outputs
Section titled “Outputs”Returns a chat model dependency that can be connected to AI agent nodes.
Dependencies and credentials
Section titled “Dependencies and credentials”- Requires an Authentication credential holding your Groq API key, sent as a Bearer token.
- The node throws an error if Model is empty.
Example workflow
Section titled “Example workflow”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.
Troubleshooting
Section titled “Troubleshooting”- 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.