Use gpt3.5 model reponse choices is empty

[chenfchengmsg]

i use model ‘gpt-3.5-turbo’ or ‘gpt-3.5-turbo-0301’ , the repsonse choices is empty
url ： https://api.openai.com/v1/chat/completions
request : {“body”:{“top_p”:1,“max_tokens”:1800,“temperature”:0.2,“messages”:[{“content”:“You answer questions factually based on the context provided”,“role”:“system”},{“content”:“ChatGPT and Whisper models are now available on our API, giving developers access to cutting-edge language (not just chat!) and speech-to-text capabilities. Through a series of system-wide optimizations, we’ve achieved 90% cost reduction for ChatGPT since December; we’re now passing through those savings to API users. Developers can now use our open-source Whisper large-v2 model in the API with much faster and cost-effective results. ChatGPT API users can expect continuous model improvements and the option to choose dedicated capacity for deeper control over the models. We’ve also listened closely to feedback from our developers and refined our API terms of service to better meet their needs.”,“role”:“system”},{“content”:“Give me a brief one sentence summary of the article”,“role”:“user”}],“model”:“gpt-3.5-turbo-0301”},“headers”:{“Content-Type”:[“application/json”],“Accept-Charset”:[“application/json”],“Authorization”:[“${api key}”]}}
response : {“choices”:[{}],“id”:“chatcmpl-6pXqb3a3yvYeg6jHoKBbq6psAZO2M”,“model”:“gpt-3.5-turbo-0301”,“object”:“chat.completion”}

[joseicarobc]

@chenfchengmsg

request : {“body”:{“top_p”:1,“max_tokens”:1800,“temperature”:0.2,“messages”:[{“content”:“You answer questions factually based on the context provided”,“role”:“system”},{“content”:“ChatGPT and Whisper models are now available on our API, giving developers access to cutting-edge language (not just chat!) and speech-to-text capabilities. Through a series of system-wide optimizations, we’ve achieved 90% cost reduction for ChatGPT since December; we’re now passing through those savings to API users. Developers can now use our open-source Whisper large-v2 model in the API with much faster and cost-effective results. ChatGPT API users can expect continuous model improvements and the option to choose dedicated capacity for deeper control over the models. We’ve also listened closely to feedback from our developers and refined our API terms of service to better meet their needs.”,“role”:“system”},{“content”:“Give me a brief one sentence summary of the article”,“role”:“user”}],“model”:“gpt-3.5-turbo-0301”},“headers”:{“Content-Type”:[“application/json”],“Accept-Charset”:[“application/json”],“Authorization”:[“${api key}”]}}
response : {“choices”:[{}],“id”:“chatcmpl-6pXqb3a3yvYeg6jHoKBbq6psAZO2M”,“model”:“gpt-3.5-turbo-0301”,“object”:“chat.completion”}

Can you share an example of your POST?

Official documentation
> API Reference - OpenAI API