Prenz LLM Gateway Chat Model icon

Prenz LLM Gateway Chat Model

Use the Prenz LLM Gateway as the Chat Model for an AI Agent or LLM Chain

Prenz LLM Gateway Chat Model

AI-generated

Summary

Drive an AI Agent or LLM chain using a selected persona from the Prenz LLM Gateway.

Inputs

  • personaId — Identifier of the assistant (persona) to use; leave empty for default LLM.
  • timeout — Timeout in milliseconds for the API request.
  • temperature — Sampling temperature (0–2) for response generation.
  • maxTokens — Maximum tokens to generate; -1 uses provider default.

Output shape

a configured language model instance

The node returns the instantiated ChatModel object for use by downstream AI nodes; no additional payload is emitted.

Examples

Example 1: Run a chat with a custom support persona, 5‑second timeout, temperature 0.8.

personaId set to a loaded assistant, timeout 5000, temperature 0.8, maxTokens -1.

Example 2: Generate a short answer using default LLM with max 100 tokens.

personaId left empty, maxTokens 100, temperature 0.7, timeout 60000.

Links

Discussion