LLMap
Models /Gemini 3.5 Flash /Where to run
Provider guide

Where to run Gemini 3.5 Flash

7 live offers tracked.

CHEAPEST
Google AI
$1.50 / $9.00
per 1M tokens in / out
FASTEST MEASURED
Google AI Studio
144 tok/s
measured throughput · $1.50 input / $9.00 output per million tokens
Google AICHEAPEST$1.50 in/1M$9.00 out/1M—1M—6h agoOpenRouter$1.50 in/1M$9.00 out/1M—1M—13m agoGoogle AI Studio$1.50 in/1M$9.00 out/1M144 tok/s1M—12m agoDeepInfra$1.50 in/1M$9.00 out/1M—1M—6h agoGoogle Vertex AIzero-retention$0.75 in/1M$4.50 out/1M4 tok/s1M—12m agoGoogle AI Studioflex tier$0.75 in/1M$4.50 out/1M131 tok/s1M—12m agoGoogle AI Studiopriority tier$2.70 in/1M$16.20 out/1M36 tok/s1M—12m ago
Full specs, hardware verdicts and benchmarks on theGemini 3.5 Flash model page →