Hi all, I’m running into a strange behavior with the gpt-4.1-2025-04-14 model and wanted to check if others have seen this too. We use both the Chat Completions API and the Responses API, with ~10 different tools configured. Most of the time tool invocation works fine. However, in some cases, the …

Facing the same issue, works fine most of the time but in very few cases says, checking but doesnt do a tool call at all.

This is a big problem we also face.

This can be improved a bit, as long as functions are not actually breaking sometimes. Use tool language somewhere that mirrors how you would prompt to inspire such a preamble to be written on models that normally don’t do it. Best following is in the function description itself. By understanding …

You can test what works for you to improve reliability and call it your own; I only provide an example of the type of language AI will respond to.

Thanks for your response. I’ll try that and provide an update here.

GPT-4.1 sometimes says “One moment…” / “Hang tight…” but never calls a tool

API Bugs

baki.kucukcakiroglu August 31, 2025, 1:57pm 5

Could you share your workaround in How to increase reliability? Let's compile best practices?

Topic		Replies	Views
GPT 4o failing to make function call API gpt-4	2	689	November 12, 2024
Inconsistent tool calling on GPT-4o & GPT-4.1 API function-calling , tools	0	208	November 14, 2025
Gpt-4o indicates in textual response that a tool was used, but did not include any toolCalls Prompting api , tools	2	701	October 11, 2024
GPT-4o cannot properly call custom functions more than half the time Bugs gpt-4o	21	6809	April 9, 2025
GPT-5.2 fails to call tools properly API bug , bugs , responses-api	7	1067	April 22, 2026

GPT-4.1 sometimes says “One moment…” / “Hang tight…” but never calls a tool

Related topics