The endpoints of gpt-3.5-turbo-instruct model are different.

[nagisa599]

model ,err := openai.New(openai.WithToken(openapikey.OpenApikey), openai.WithModel("gpt-3.5-turbo-instruct"))
    if err != nil {
        log.Fatal(err)
    }
	completion, err := llms.GenerateFromSinglePrompt(ctx, 
		model, 
		"What is the capital of Japan?",
		llms.WithTemperature(0.5),
		llms.WithStopWords([]string{"\n"}))

2024/08/19 17:07:58 API returned unexpected status code: 404: This is not a chat model and thus not supported in the v1/chat/completions endpoint. Did you mean to use v1/completions?
exit status 1

The chat/completions endpoint is hit as shown below.

[tz3]

Are you sure about the OpenApikey you have inserted correctly?