LLMap
Models /Gemini 2.5 Flash /Where to run
Provider guide

Where to run Gemini 2.5 Flash

10 live listings tracked.

CHEAPEST
Google AI
$0.30 / $2.50
per 1M tokens in / out
FASTEST MEASURED
Google AI Studio
130 tok/s
measured throughput · $0.15 input / $1.25 output per million tokens
DeepInfra$0.30 in/1M$2.50 out/1M—1M—9 hours agoGoogle AICHEAPEST$0.30 in/1M$2.50 out/1M—1M—9 hours agoGoogle Vertex AIzero-retention$0.30 in/1M$2.50 out/1M94 tok/s1M—3 hours agoGoogle Vertex AIzero-retention$0.30 in/1M$2.50 out/1M56 tok/s1M—21 hours agoGoogle Vertex AIzero-retention$0.30 in/1M$2.50 out/1M73 tok/s1M—3 hours agoOpenRouter$0.30 in/1M$2.50 out/1M—1M—3 hours agoGoogle AI Studio$0.30 in/1M$2.50 out/1M51 tok/s1M—3 hours agoGoogle AI Studioflex tier$0.15 in/1M$1.25 out/1M130 tok/s1M—3 hours agoGoogle AI Studiopriority tier$0.54 in/1M$4.50 out/1M110 tok/s1M—3 hours agoGoogle Vertex AIpriority tierzero-retention$0.54 in/1M$4.50 out/1M76 tok/s1M—3 hours ago
Full specs, hardware verdicts and benchmarks on the Gemini 2.5 Flash model page →