Fake LLM Chat Model icon

Fake LLM Chat Model

A fake LLM for testing and development - no API key required

Fake LLM Chat Model

AI-generated

Summary

Generate a fake language model chat response either by echoing the input message or returning a fixed predefined message, with optional prefix and streaming delay customization.

Inputs

  • Response Type (required) — Select how the fake LLM should respond: either echoing the input message or returning a fixed response.
  • Fixed Response — Specify the predefined message to return when Response Type is set to Fixed Response.
  • Options — Configure response behavior including a response prefix to prepend to each response and a stream delay in milliseconds between words when streaming the response.

Output shape

a single AI language model response object containing the generated text under the 'response' field.

Output includes a 'response' property constructed by the FakeLLMChatModel instance based on the selected Response Type and options. Streaming delay affects timing but not output shape. No pagination or error envelope.

Examples

Example 1: To return the input message prepended by '[FAKE] '

Set Response Type to Echo, set Response Prefix to '[FAKE] ', and optionally adjust Stream Delay.

Example 2: To always get a constant message

Set Response Type to Fixed Response and define the Fixed Response text as desired.

Discussion