.png?width=60&height=60&name=AI%20Copilot%20logo%20(mega%20menu).png)
.png?width=29&height=29&name=twitter%20(1).png){kind=small}
The 2026.9 release of Cognigy expands your LLM options with native support for the Gemini 3 model family, giving you more flexibility when selecting the right model for your AI Agent use cases.
This update allows you to easily upgrade to Google's latest models — with no additional integration work required. The Gemini 3 family brings performance and efficiency improvements across the board, and the three variants follow the same tiered structure you're familiar with:
- gemini-3.1-pro-review targets complex, reasoning-intensive tasks where output quality is the priority.
- gemini-3-flash-review balances speed and capability, making it a strong default for latency-sensitive production deployments.
- gemini-3.1-flash-lite-preview is optimized for high-throughput, cost-conscious scenarios where reliable performance at scale matters more than raw capability.
See all supported LLM vendors and models here.
Other Improvements
Cognigy.AI
- Removed the End Handover on Participant Change setting from the Salesforce MIAW handover provider. Handover ending is now handled automatically on the Salesforce side
- Added NiCE branding by introducing a wordmark logo in Cognigy.AI installations integrated with the NiCE environment. A configurable CXone button was also added to the sidebar and user menu for quick access to the CXone application
Cognigy Voice Gateway
- Added support for changing the media path during an active transferred call via the Voice Gateway API. This improvement lets you remove Voice Gateway from the audio stream during sensitive payment exchanges, reducing PCI data exposure.
- Improved search in the Voice Gateway Self-Service portal. Now, results include all records, not just the current page in paginated lists
