🤖 GenAI Chat

Select models to compare (min 2):

Compare

⚠️ TinyLlama 1.1B (Custom) is selected — first invocation after idle may take up to 5 minutes (ModelNotReadyException — retries automatically).

📈 Model Performance Metrics (All Users)

↻ Refresh

Model	Requests	Avg Latency	Avg First Token	Avg Cost	Total Tokens	Total Cost