Multi-agent parallelism applies to all LLMs, not just local

LLM-ROUTING.md

@@ -65,14 +65,17 @@ curl http://127.0.0.1:8080/v1/chat/completions \
 - No rate limits
 - No cost accumulation
 
-### 🚀 Parallel Work → **MULTI-AGENT LOCAL**
+### 🚀 Parallel Work → **MULTI-AGENT**
 When speed matters, spawn multiple workers:
 ```bash
-# Flynn can spawn sub-agents hitting local LLMs
+# Flynn can spawn sub-agents targeting any LLM
 # Each agent works independently, results merge
 ```
 - Use for: bulk analysis, multi-file processing, research tasks
-- Coordinate via sessions_spawn with local model routing
+- Coordinate via `sessions_spawn` with model param
+- **Local:** best for privacy + no rate limits
+- **Cloud:** best for complex tasks needing quality
+- Mix and match based on task requirements
 
 ### ⚡ Quick One-Shot → **COPILOT or LOCAL**
 ```bash