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

Where to run Gemini 2.5 Flash

9 live offers tracked.

CHEAPEST
Google AI
$0.30 / $2.50
per 1M tokens in / out
FASTEST MEASURED
Google AI Studio
111 tok/s
measured throughput · $0.30 input / $2.50 output per million tokens
DeepInfra$0.30 in/1M$2.50 out/1M—1M—6h agoGoogle AICHEAPEST$0.30 in/1M$2.50 out/1M—1M—6h agoGoogle AI Studio$0.30 in/1M$2.50 out/1M111 tok/s1M—13m agoOpenRouter$0.30 in/1M$2.50 out/1M—1M—13m agoGoogle AI Studioflex tier$0.15 in/1M$1.25 out/1M49 tok/s1M—13m agoGoogle Vertex AIzero-retention$0.30 in/1M$2.50 out/1M88 tok/s1M—13m agoGoogle Vertex AIzero-retention$0.30 in/1M$2.50 out/1M99 tok/s1M—13m agoGoogle Vertex AIzero-retention$0.30 in/1M$2.50 out/1M57 tok/s1M—38h agoGoogle AI Studiopriority tier$0.54 in/1M$4.50 out/1M94 tok/s1M—13m ago
Full specs, hardware verdicts and benchmarks on theGemini 2.5 Flash model page →