Features
Auto-routing across 19+ models (Auto pool: Gemini Flash Lite, DeepSeek V3.2, Nemotron 120B, etc.)
Per-response model and cost display
Model comparison (Compare mode) on Teams
Blend mode (consensus/council/MoA synthesis) on Teams
Judge mode for ranking responses on Teams
Mesh failover routing for reliability
OpenAI-compatible API endpoint (base_url: llmwise.ai/v1)
Replay Lab for testing routing policies
Deterministic file generation with preview
Web search tool integration
Semantic memory for cross-session continuity
Bring Your Own Keys (BYOK) support
Zero-retention mode (opt-in)
PDF API for parsing and extraction
Instant answers from PDFs
Multi-document chat (Pro and above)
Single sign-on (Enterprise)
Custom data retention (Enterprise)
Priority processing (Pro)
Collaboration features (Team)
