Use models without API keys

The GPT for Work add-ons allow you to start using AI models immediately without any setup. The default model is OpenAI gpt-4o. If you want to explore other models, select a different model in the model switcher.

Select a model

note

The models available in the model switcher depend on the GPT for Work add-on you're using.

Excel

1. Open a Microsoft Excel workbook.

2. Click GPT for Excel Word in the Home tab.

   

   info

   You can also go to Home > Add-ins > My add-ins > GPT for Excel Word.

3. Expand the model switcher.

   

4. Select a model.

   Models that are available without any setup are listed under No API key needed.

   

GPT for Excel uses the selected model to generate all responses.

Sheets

1. Open a Google spreadsheet.

2. Select Extensions > GPT for Sheets and Docs > Open.

   

3. Expand the model switcher.

   

4. Select a model.

   Models that are available without any setup are listed under No API key needed.

   

GPT for Sheets uses the selected model to generate all responses.

Word

1. Open a Microsoft Word document.

2. Click GPT for Excel Word in the Home tab.

   

   info

   You can also go to Home > Add-ins > My add-ins > GPT for Excel Word.

3. Expand the model switcher.

   

4. Select a model.

   Models that are available without any setup are listed under No API key needed.

   

GPT for Word uses the selected model to generate all responses.

Docs

1. Open a Google document.

2. Select Extensions > GPT for Sheets and Docs > Launch.

   

3. Expand the model settings.

   

4. Select a model.

   Models that are available without any setup are listed under No API key needed.

   

GPT for Docs uses the selected model to generate all responses.

Recommended models

As a general rule, OpenAI models are more reliable and less likely to decline prompts than models from other providers.

The following table lists our recommended models available without your own API key.

Model	Provider	Description
gpt-4o	OpenAI	Best overall balance of easy prompting, speed, quality, reliability, and cost. We recommend this model for most use cases.
gpt-4.1-nano	OpenAI	Fast, cost-effective model with strong reasoning and language capabilities. Follows instructions closely.
o4-mini	OpenAI	Fast, cost-effective reasoning. Great for analysis tasks.
claude-3.5-sonnet	Anthropic	Great at content creation, summarization, and nuanced reasoning across a wide range of tasks.
gemini-2.5-flash	Google	Cost-effective model ideal for lightweight tasks and rapid responses. Supports reasoning and web search (enabled from the model settings).
sonar	Perplexity	Cost-effective search model optimized for simple queries. Grounded in recent web search data.
sonar-pro	Perplexity	Advanced search model designed for complex queries. Grounded in recent web search data.
grok-3-mini-fast	xAI	Fast, cost-effective reasoning. Good alternative to OpenAI's reasoning models.

To learn more about a model, hover over the model name in the model switcher. A tooltip opens with detailed information about the model.

What's next

If you need a model that's not available in the model switcher, set up your own API keys.