← Playground
AI Lab
AI Intelligence Playground
⥠Gemini Flash
âĒ Intelligent Cascade Active
RPM: 0/10 Flash | 0/30 Lite
Daily Quota: 0%
ð
Google Gemini API Key
Stored client-side in your browser's localStorage
Gemini Flash connects to Google AI Studio. A default demo key is active, or you can paste your personal key for dedicated rate limits.
Using default demo key
Get a free key:
Google AI Studio →
Loading WebGPU Weights...
0%
Downloading model shards into browser cache...
Generation Controls
Presets:
Temperature 0.7
Max Tokens 2048
Top-P 0.95
Chat Console
Ready 0 t/s • 0.0s
AI
Playground Assistant Ready
Welcome to the AI Playground! Powered by an Intelligent Request Queue & 3-Tier Model Fallback Cascade:
- Priority 1 (Primary Cloud):
Gemini Flash(10 RPM / 250 RPD) - Priority 2 (Fast Fallback):
Gemini Flash-Lite(30 RPM / 1000 RPD â auto-routed if Flash >80% RPM, 429, or <100 tokens) - Priority 3 (Local WebGPU):
Qwen 2.5 0.5B/Llama 3.2 3B(100% private in-browser)
Switch models directly from the bottom toolbar dropdown or click Overview Mode above to inspect hardware and model cards.
Try: