Provider guide
Where to run Gemini 2.5 Pro Preview 05-06
9 live listings tracked — output prices vary 2.0× between the cheapest and most expensive host, so the provider choice matters as much as the model choice.
FASTEST MEASURED
140 tok/s
measured throughput · $0.63 input / $5.00 output per million tokens
Google Vertex AI$1.25 in/1M$10.00 out/1M86 tok/s1M—2 hours agoGoogle Vertex AI$1.25 in/1M$10.00 out/1M72 tok/s1M—2 hours agoOpenRouter$1.25 in/1M$10.00 out/1M—1M—2 hours agoGoogle Vertex AIzero-retention$1.25 in/1M$10.00 out/1M73 tok/s1M—2 hours agoGoogle AI StudioCHEAPEST$1.25 in/1M$10.00 out/1M90 tok/s1M—2 hours agoGoogle AI$1.00 in/1M$20.00 out/1M—8K—8 hours agoGoogle AI Studioflex tier$0.63 in/1M$5.00 out/1M140 tok/s1M—2 hours agoGoogle Vertex AIpriority tier$2.25 in/1M$18.00 out/1M71 tok/s1M—2 hours agoGoogle AI Studiopriority tier$2.25 in/1M$18.00 out/1M44 tok/s1M—2 hours ago
Google Vertex AI
OpenRouterFull specs, hardware verdicts and benchmarks on the Gemini 2.5 Pro Preview 05-06 model page →