LLMap
Models /Gemini 3.1 Flash Lite /Where to run
Provider guide

Where to run Gemini 3.1 Flash Lite

7 live offers tracked.

CHEAPEST
Google AI
$0.25 / $1.50
per 1M tokens in / out
FASTEST MEASURED
Google AI Studio
113 tok/s
measured throughput · $0.13 input / $0.75 output per million tokens
Google AICHEAPEST$0.25 in/1M$1.50 out/1M—1M—6h agoOpenRouter$0.25 in/1M$1.50 out/1M—1M—14m agoGoogle AI Studio$0.25 in/1M$1.50 out/1M85 tok/s1M—13m agoDeepInfra$0.25 in/1M$1.50 out/1M—1M—6h agoGoogle Vertex AIzero-retention$0.13 in/1M$0.75 out/1M4 tok/s1M—6h agoGoogle AI Studioflex tier$0.13 in/1M$0.75 out/1M113 tok/s1M—13m agoGoogle AI Studiopriority tier$0.45 in/1M$2.70 out/1M62 tok/s1M—13m ago
Full specs, hardware verdicts and benchmarks on theGemini 3.1 Flash Lite model page →