GPT-3.5-turbo error 404: not supported in the v1/chat/completions

API
1

This is what I copied from OpenAI:

curl https://api.openai.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{
     "model": "gpt-3.5-turbo",
     "messages": [{"role": "user", "content": "Say this is a test!"}],
     "temperature": 0.7
   },

Then I call it in postman and report this error:

{
    "error": {
        "message": "This is not a chat model and thus not supported in the v1/chat/completions endpoint. Did you mean to use v1/completions?",
        "type": "invalid_request_error",
        "param": "model",
        "code": null
    }
}

Is any mistake here?

2

Encountering the same issue, is there any update on this?

3

Are you using an application or command that was working before?

Works for me at this moment, specifying “gpt-3.5-turbo”:

“model”: “gpt-3.5-turbo-0613”,
“choices”: [
{
“index”: 0,
“message”: {
“role”: “assistant”,
“content”: “My name is CrazyBot. How can I assist you today?”
},
“finish_reason”: “stop”
}
],

The retry techniques for rate limiting outlined below can also be used for other error codes and messages that would indicate an intermittent service problem:

https://github.com/openai/openai-cookbook/blob/main/examples/How_to_handle_rate_limits.ipynb