Multimodal understanding
Reads text, images and more together — ideal for cross-modal analysis.
Frontier intelligence with action
Gemini 3.5
Google DeepMind's frontier model — frontier intelligence with action, spanning multimodal understanding and long context.
- Provider
- Access
- Unified API
Model overview
Gemini 3.5 is Google DeepMind's frontier model, built around intelligence 'with action' — strong at multimodal understanding, long-context processing and tool use, breaking complex tasks into executable steps.
Once connected through XylemNode, a single key calls it — sparing you a separate integration with Google's ecosystem.
Key capabilities
Long context
Fits long documents and large material in one pass, with fewer truncations and re-feeds.
Built to act
Designed for tool use and agent orchestration, turning intent into executable steps.
Specs
Bring this model into your workflow