Skip to main content

AI models

Models are the engines that power the responses generated by GPT for Work. Choosing the right model depends on your specific needs, such as privacy, response quality, speed, or cost. Supported AI providers include OpenAI, Google, Anthropic, Perplexity, Mistral, and local models using Ollama.

The following table summarizes the different models available in GPT for Work, from zero setup to more advanced options:

UseWhenAvailable for
Models without an API key
Setup required: None		You want to get started quickly, using popular models:
  • OpenAI gpt-4o, the default model.
  • Other models are available in one click.
📄 Available models		Excel, Sheets, Word
Models with an API key 🔑
Setup required: Set your own API key
  • You want to benefit from the terms you have with an AI provider, such as privacy, cost, and rate limits.
  • You want to use a model that is not available without an API key.
  • You want more control.
📄 Available models		Excel, Sheets, Word, Docs
OpenAI Assistants 🔑
Setup required: Set your own API key and create an OpenAI Assistant
  • You need to add capabilities to a model.
  • You want to upload your own files.
Excel, Sheets
Local models
Setup required: Set up a local Ollama server and set the endpoint in GPT for Work
  • You want to use a local model.
📄 Available models		Excel, Word
What's next?

Get started with the option that works best for you: