LLMap
Models /Gemini 3 Flash Preview /Where to run
Provider guide

Where to run Gemini 3 Flash Preview

8 live listings tracked.

CHEAPEST
Google AI
$0.50 / $3.00
per 1M tokens in / out
FASTEST MEASURED
Google Vertex AI
131 tok/s
measured throughput · $0.90 input / $5.40 output per million tokens
Google Vertex AIzero-retention$0.50 in/1M$3.00 out/1M89 tok/s1M—1 hour agoOpenRouter$0.50 in/1M$3.00 out/1M—1M—1 hour agoGoogle AI Studio$0.50 in/1M$3.00 out/1M75 tok/s1M—1 hour agoGoogle AICHEAPEST$0.50 in/1M$3.00 out/1M—1M—7 hours agoGoogle AI Studioflex tier$0.25 in/1M$1.50 out/1M58 tok/s1M—1 hour agoGoogle Vertex AIflex tierzero-retention$0.25 in/1M$1.50 out/1M41 tok/s1M—1 hour agoGoogle Vertex AIpriority tierzero-retention$0.90 in/1M$5.40 out/1M131 tok/s1M—1 hour agoGoogle AI Studiopriority tier$0.90 in/1M$5.40 out/1M57 tok/s1M—1 hour ago
Full specs, hardware verdicts and benchmarks on the Gemini 3 Flash Preview model page →