Provider guide
Where to run Gemini 3.1 Pro Preview Custom Tools
8 live listings tracked.
FASTEST MEASURED
97 tok/s
measured throughput · $1.00 input / $6.00 output per million tokens
Google Vertex AIzero-retention$2.00 in/1M$12.00 out/1M80 tok/s1M—2 hours agoGoogle AI Studio$2.00 in/1M$12.00 out/1M96 tok/s1M—2 hours agoOpenRouter$2.00 in/1M$12.00 out/1M—1M—2 hours agoGoogle AICHEAPEST$2.00 in/1M$12.00 out/1M—1M—2 hours agoGoogle AI Studioflex tier$1.00 in/1M$6.00 out/1M97 tok/s1M—2 hours agoGoogle Vertex AIflex tierzero-retention$1.00 in/1M$6.00 out/1M17 tok/s1M—2 hours agoGoogle AI Studiopriority tier$3.60 in/1M$21.60 out/1M69 tok/s1M—2 hours agoGoogle Vertex AIpriority tierzero-retention$3.60 in/1M$21.60 out/1M42 tok/s1M—2 hours ago
Google Vertex AI
OpenRouterFull specs, hardware verdicts and benchmarks on the Gemini 3.1 Pro Preview Custom Tools model page →