Select a model or an OpenAI Assistant in GPT for Excel

Select the model or OpenAI Assistant that offers the best balance of accuracy, speed, and cost for your use case. GPT for Excel uses the selected model for all AI-generated responses.

Check the following documentation for further guidance:

• List of recommended models

• List of supported models for GPT for Excel with or without your own API keys

• Guide to using OpenAI Assistants as models

Select a model

1. In the GPT for Excel sidebar, expand the model switcher.

   

2. Select a model.

   Models that are available without any setup are listed under No API key needed. Models that are available through API keys and endpoints that you have set up are listed under Use your API key or endpoint. For more information, see AI models.

   

GPT for Excel uses the selected model to generate all responses for GPT functions and bulk AI tools.

info

• When cache is enabled, existing GPT formulas will not automatically update to the new model when you re-execute them.

  To re-execute an existing formula with a different model:

  1. Set the model as a parameter in the formula.

  2. Press Enter to re-execute the formula.

• The GPT_MATCH and GPT_VISION functions, as well as the Analyze images (Vision) bulk AI tool, use specific models, not the default one. For more information, see Features with fixed models.

What's next

• Run bulk AI tools and execute GPT functions in GPT for Excel.

• Configure other settings to customize how the language model operates.