OpenAI endpoint wrong?

[Xylon2]

I was getting a 404 error when using create-chat-completion. The fix was to set the endpoint to use v1:

(api/create-chat-completion {:model "gpt-5"
                                 :messages messages}
                                {:api-key (:openai api-keys)
                                 :api-endpoint "https://api.openai.com/v1"})

[wkok]

I did a test & am getting a successful response without needing to override the endpoint:

Request:

(api/create-chat-completion {:model "gpt-5"
                             :messages [{:role "system" :content "You are a helpful assistant."}
                                        {:role "user" :content "Who won the world series in 2020?"}
                                        {:role "assistant" :content "The Los Angeles Dodgers won the World Series in 2020."}
                                        {:role "user" :content "Where was it played?"}]})

Response:

{:id "chatcmpl-CPtq3PIcXqxZ46VJT11IMgXxqCKjx",
 :object "chat.completion",
 :created 1760288879,
 :model "gpt-5-2025-08-07",
 :choices [{:index 0,
            :message {:role "assistant",
                      :content "Globe Life Field in Arlington, Texas.",
                      :refusal nil,
                      :annotations []},
            :finish_reason "stop"}],
 :usage {:prompt_tokens 54,
         :completion_tokens 146,
         :total_tokens 200,
         :prompt_tokens_details {:cached_tokens 0, :audio_tokens 0},
         :completion_tokens_details {:reasoning_tokens 128,
                                     :audio_tokens 0,
                                     :accepted_prediction_tokens 0,
                                     :rejected_prediction_tokens 0}},
 :service_tier "default",
 :system_fingerprint nil}

Ate you still experiencing this?

[Xylon2]

I tried today and I no-longer need to specify the endpoint. I wonder what happened?

Thanks for your work on this library BTW.