Syrus AI Chat Model (Gemma 4)
AI-generatedSummary
Generate AI chatbot responses using the Syrus AI Chat Model (Gemma 4) with configurable generation parameters.
Inputs
- Temperature — Controls randomness in output; higher values mean more random responses (default 0.7).
- Top P — Limits token selection to top probability mass (default 0.95).
- Top K — Limits token selection to top K tokens by probability (default 40).
- Max Output Tokens — Maximum number of tokens in the generated response (default 8192).
Output shape
a single AI language model generation containing the generated text and any invoked tool calls wrapped as an AIMessage object
Returns an object with a 'generations' array containing one generation. The generation includes 'text' (the response) and 'message' (an AIMessage instance embedding response text and optional tool call details). No pagination or multiple responses are returned.
