Mar 25, 2025 · API chat-completion ashish.rtw March 25, 2025, 10:59am 1 I am using GPT-4o and sometimes completion api returns content None which has finish_reason “tool_call”. I also …

The default used to be 2048, which in case of reasoning models, they cause empty outputs if the limit is reached. If the generated tokens reach the context window limit or the …

Apr 29, 2024 · If responseBody is a VALID JSON but DOESN’T return anything useful, you are left with an empty responseData. Your error handling does not consider this as no error is thrown.

2 days ago · reasoning_effort=none is not being respected in the Chat Completions API. GPT 5.1 is still generating reasoning tokens. What I’m sending to gpt 5.1 is:** n=8, reasoning_effort”: …

Aug 19, 2025 · For example, if the limit’s 250, the reasoning tokens hover around ~300. But when I bump it to 1000, the reasoning tokens shoot past 1000 — which results in an empty …

Apr 21, 2025 · There is only one empty reasoning item that pairs with the first function call but then there are errors on the subsequent function calls in the same loop (ie parrarel calls).

Jan 10, 2024 · I’ve usually found workarounds like upgrading the api_version or fiddling with the messages (in one example, I had to set the content on a message to an empty string), but not …

Jan 12, 2024 · When running a function call, the message is empty despite completion tokens being used and finish_reason = “tool_calls” I am using the Azure OpenAI service.

Sep 16, 2025 · I have multiple prompts in a project, across all models, that hasn’t had any changes that is using both reasoning and output tokens, status is completed, etc. with a …

Apr 27, 2025 · The response to the API call to o models (o3, o1, o3-mini) is simply empty, I see no output in the list. System and User Messages are passed properly, and I can see them in …