Update OpenAI model info and remove duplicate modelsinfo.py

[Pwuts]

Background

• OpenAI launched a set of new models last Monday
  • pricing was also updated
• We have data duplication between autogpt.llm.providers and autogpt.llm.modelsinfo

Changes

• Add new models to autogpt.llm.providers.openai
• Deduplicate model info definitions using aliases
• Remove completion_token_cost from EmbeddingModelInfo since embedding models don't output tokens
• Update test_api_manager
  • Add a test for recording embedding model cost

Documentation

x

Test Plan

• CI
• Ran Auto-GPT for a couple of cycles, seems to work fine

PR Quality Checklist

• My pull request is atomic and focuses on a single change.
• I have thoroughly tested my changes with multiple different prompts.
• I have considered potential risks and mitigations for my changes.
• I have documented my changes clearly and comprehensively.
• I have not snuck in any "extra" small tweaks changes.
• I have run the following commands against my code to ensure it passes our linters:

  black .
  isort .
  mypy
  autoflake --remove-all-unused-imports --recursive --ignore-init-module-imports --ignore-pass-after-docstring autogpt tests --in-place

[Pwuts]

Changes here are mostly to make sure it works as a unit:

• Semi-random values for token cost, instead of using values from the llm.providers module
• Avoid using the same value in different variables to make sure the test also asserts correct usage of the different variables