AI models

Models are the engines that power GPT for Work. Which model is the right one depends on your specific needs in terms of response quality, speed, privacy, and cost. GPT for Work supports models from OpenAI, Google, Anthropic, Perplexity, and Mistral, and open-source models through Ollama.

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

Use	When	Available for
Models without an API key Setup required: None	You want to get started quickly, using popular models: OpenAI gpt-4o is 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 of service you have with an AI provider, such as cost, privacy, 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 custom capabilities to a model. You want to upload your own files as knowledge for the AI.	Excel, Sheets
Ollama models Setup required: Set up an Ollama server and set the server endpoint in GPT for Work	You want to use the models available through Ollama. You want to run models on a local machine. You do not want to send any data over the internet. ✅ Available models	Excel, Word

What's next

Get started with the option that works best for you:

• Use models without an API key.

• Use models with an API key.

• Use OpenAI Assistants.

• Use Ollama models.