Temperature Options

TheAgentic LLMs support temperature options for the chat completions. This allows you to control the randomness of the model's output.

The temperature is a value between 0 and 1. A temperature of 0 is deterministic, while a temperature of 1 is random.

Tool Use

🚧

If there are tools present in the request, temperature will be ignored.

response = client.chat.completions.create(
    model="agentic-large",
    messages=[...],
    tools=[...],
    tool_choice="auto",
    temperature=0.5, # ignored because tools are present
)