Input
Executionexec_in
Execution trigger to start the tool-enabled invocation
AI/Generative
Invokes an LLM that can call Flow tools/functions and routes each call to execution pins.
Scores range from 0 to 10. Higher values mean more impact, exposure, or operational weight.
Execution trigger to start the tool-enabled invocation
Bit describing the provider/model to execute
Conversation history the model should continue from
JSON array of tool/function definitions (OpenAI format)
Controls whether the model must, may, or must not call tools
Signals when the invocation and tool routing finished
LLM response if the model answered directly without tool calls
Parsed JSON arguments for the latest tool call
Token usage, cost, and model statistics