promptfoo

When I use any of the gpt-5 models and try to see the metrics, like the latency and cost, the latency for gpt-5-nano for example with `reasoning_effort: minimal` gives like 10000~15000 Ms on average and always the cost=0
does anyone have explanation for this??
I'm using the nodejs package!! and here is the provider sent
      "providers": [
        {
          "id": "openai:responses:gpt-5-nano",
          "config": {
            "max_completion_tokens": 4000,
            "max_output_tokens": 4000,
            "apikey": "api-key-here",
            "tools": [],
            "tool_choice": "auto",
            "reasoning": {"effort": "minimal"}
          }
        }
      ],

I'm sending the reasoning effort as minimal, and it still uses the default medium effort, how can I override this?

Hey, I can take a look. Are you on the latest version?

Hey, thanks for replying
It's solved now after updating to the latest version, I was using v0.117.1 but after investigating the latest commit on github, with v0.117.5 it works 
thanks a lot 🙏