GPT for Work - 2025 April updates
This month, we're excited to showcase our new Market Research & Analysis solution using Perplexity AI in Excel & Google Sheets. Explore the demo video below to see it in action!
We've released powerful new features this month, such as API keys for teams for simplified administration. Additionally, we've expanded our model support to include the latest AI models from OpenAI, Perplexity, xAI, Google, and Mistral.
These are just the highlights of our April updates. We've also made numerous improvements and bug fixes that you can find in our release notes.
🔍 Use case presentation: Market research & Analysis
Automate market research and analysis tasks directly within Excel using the GPT for Work add-ons and the Sonar model from Perplexity AI. Pull company descriptions, revenue ranges, business types, product lists, market sizes, and competitor data, all in seconds. You can do the same in Google Sheets!

🔑 API keys for teams - GPT for Excel, Word & Sheets
Managing API keys is now easier for teams. Space owners can set keys (one per AI provider) that work for everyone in the space. Users can still override the space keys with their own keys if needed.

🤖 New AI models in April 2025
OpenAI models
- o3 -
(with API key, without API key)
o3 is currently the most advanced and powerful reasoning model offered by OpenAI. - o4 Mini -
(with API key, without API key)
o4 Mini is a smaller, high-performing model optimized for fast and cost-efficient reasoning. - GPT-4.1, GPT-4.1 Mini, and GPT-4.1 Nano -
(with API key, without API key)
The GPT-4.1 models improve on the GPT-4o models in speed, accuracy, reasoning capabilities, coding performance, context window size, and cost-effectiveness. - Fine-tuned models based on GPT-4o and GPT-4o Mini -
(with API key only)
Fine-tuning allows you to train base models with your own data, tailoring them for your specific needs and applications.
xAI models
- Grok 3 Fast (beta) and Grok 3 Mini Fast (beta) -
(with API key, without API key)
Grok 3 Fast offers significantly faster response times for latency-sensitive tasks, while Grok 3 Mini Fast is a smaller, cost-effective model optimized for quick and efficient outputs. - Grok 3 (beta) and Grok 3 Mini (beta) -
(with API key only)
- Grok-2 is no longer supported
Perplexity models
- Sonar Pro -
(with API key, without API key)
Sonar Pro provides more accurate and detailed results with more comprehensive citations than Sonar. - Sonar Reasoning and Sonar Reasoning Pro -
(with API key, or without API key in GPT functions with the model parameter)
Sonar Reasoning and Sonar Reasoning Pro provide advanced reasoning capabilities powered by DeepSeek R1. - Search effort setting - Available for all Sonar models when using your own API key.
The setting allows you to balance cost against search result quality.
Google models
- Gemini 2.0 Flash -
(without API key)
The model offers fast results, a large context window, advanced multimodal capabilities, and cost-effective performance. - Gemini 2.0 Flash, Gemini 2.0 Flash Lite, and Gemini 2.5 Pro Experimental -
(with API key only)
Mistral models
- Mistral Large, Mistral Small, Ministral 8B, and Ministral 3B -
(with API key only)
Mistral models prioritize cost-efficiency and open-source accessibility, and provide a balanced solution for a wide range of applications.
📖 To go further
Check out our resources to get the most out of GPT for Work:
- 📚 Step-by-step guides for Excel, Word, Sheets and Docs
- 📖 Complete documentation: Find everything you need to know about GPT for Work (this has improved significantly in 2024!)
- 📝 Our blog articles for e-commerce, SEO, or market research
- 📺 Our YouTube channel with video tutorials
- 🎥 Our webinar: Explore GPT for Work in action
- 📄 Release notes: Follow us on X and LinkedIn for an early access to all our new feature announcements
- 🔧 Contact support: Need help? Reach out to our friendly team