Models /Gemini 3.6 Flash /Where to run

Provider guide

Where to run Gemini 3.6 Flash

6 live offers tracked.

CHEAPEST

$1.50 / $7.50

per 1M tokens in / out

FASTEST MEASURED

Google AI Studio

111 tok/s

measured throughput · $0.75 input / $3.75 output per million tokens

ProviderIn / 1MOut / 1MThroughputContextQuantSynced

OpenRouterCHEAPEST$1.50 in/1M$7.50 out/1M—1M—13m ago Google AI$1.50 in/1M$7.50 out/1M—1M—6h ago Google AI Studio$1.50 in/1M$7.50 out/1M66 tok/s1M—12m ago Google Vertex AIzero-retention$0.75 in/1M$3.75 out/1M17 tok/s1M—12m ago Google AI Studioflex tier$0.75 in/1M$3.75 out/1M111 tok/s1M—12m ago Google AI Studiopriority tier$2.70 in/1M$13.50 out/1M—1M—12m ago

Full specs, hardware verdicts and benchmarks on theGemini 3.6 Flash model page →