Skip to content

Possible issue when GPT API key does not have access to GPT 4 #17

Open
@sollarp

Description

@sollarp

Hi,

This method looks like a legacy.
Unfortunately with my API key the "model": "gpt-3.5-turbo" does not work.

Screenshot_20

I had to change the Model to the following below...
Source : https://platform.openai.com/docs/api-reference/completions/create

   '{
"model": "gpt-3.5-turbo-instruct",
"prompt": "Say this is a test",
"max_tokens": 7,
"temperature": 0,
"stream": true
 }'

As I have been using my API key in my own project works fine with the following request.
The recommended request for GPT 3.5
https://platform.openai.com/docs/api-reference/chat/create

   "model": "gpt-3.5-turbo",
"messages": [
  {
    "role": "system",
    "content": "You are a helpful assistant."
  },
  {
    "role": "user",
    "content": "Hello!"
  }
],
"stream": true

So the default model should be "model": "gpt-3.5-turbo-instruct" Can someone with GPT4 access test this? Thanks

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions