Skip to main content
Configure the LLM provider and model parameters for your agent.

Required Fields

Provider Type - Select the LLM provider (e.g., OpenAI, Anthropic, etc.) Model ID - Select the specific model from the chosen provider

Model Parameters (Optional)

Configure model behavior parameters. Leave fields empty to use default values.

Generation Parameters

  • Temperature (0.0-2.0) - Controls randomness in output. Higher values increase creativity.
  • Top P (0.0-1.0) - Nucleus sampling parameter. Controls diversity via nucleus sampling.
  • Max Output Token - Maximum tokens in the response
  • Max Tool Call - Maximum tool calls per response
  • Top Logprob - Number of most likely tokens to return
  • Parallel Tool Call - Enable parallel tool call execution (toggle switch)
  • Reasoning Effort - Level of reasoning effort (Default, Low, Medium, High)
  • Reasoning Budget (Tokens) - Maximum tokens for reasoning (optional)