Codex CLI error: Rate limit exceeded, try later

[sameermahajan]

While trying to follow the documentation, I noticed that my organization does not seem to have code-davinci-002 model / engine. When I greped for davinci in models output by CLI I only see:

models:      "id": "davinci",
models:      "id": "text-davinci-edit-001",
models:      "id": "code-davinci-edit-001",
models:      "id": "text-davinci-001",
models:      "id": "davinci-search-document",
models:      "id": "davinci-instruct-beta",
models:      "id": "text-search-davinci-query-001",
models:      "id": "davinci-search-query",
models:      "id": "text-search-davinci-doc-001",
models:      "id": "text-similarity-davinci-001",
models:      "id": "text-davinci-002",
models:      "id": "text-davinci-003",
models:      "id": "davinci-similarity",

So I set my engine id to be gpt-3.5-turbo which seems to exist (in API output as well as UI). However when I try some simple command / example I get the error of:

~/Codex-CLI$ # # Codex CLI error: Rate limit exceeded, try later

I just created my OpenAI account and key so there shouldn't be any issue with its expiry... Or does it take some time to propagate / trickle down?