LiteLLM Chat Model icon

LiteLLM Chat Model

For advanced usage with an AI chain

LiteLLM Chat Model

AI-generated

Summary

Generate AI-driven chat completions using a selected LiteLLM model within an AI chain or agent context.

Inputs

  • model (required) — Select the LiteLLM model to use for generating the chat completion.
  • options — Configure additional parameters including frequency penalty, presence penalty, max tokens, sampling temperature, max retries, timeout, top P, and response format (text or JSON). Include 'json' in your prompt if JSON response format is selected and ensure using recent models post November 2023.

Output shape

a single AI language model response object with generated chat completions and optional token usage metadata

The node outputs a structured response object representing the model's chat completion result. It should be connected to an AI chain or agent, as it does not accept direct input messages itself. If JSON response format is enabled, the prompt must contain the word 'json' to ensure valid JSON output from the model.

Links

Discussion