March 9, 2026

You can now control the reasoning effort of supported OpenAI reasoning models using the new reasoning_mode parameter in the think provider configuration. This parameter maps to OpenAI's reasoning_effort and accepts low, medium, or high.

Example:

{
  "type": "Settings",
  "agent": {
    "think": {
      "provider": {
        "type": "open_ai",
        "model": "gpt-5",
        "reasoning_mode": "medium"
      }
    }
  }
}

For more details, visit the Configure the Voice Agent documentation.