Provider guide
Where to run GPT-5.1
5 live offers 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
90 tok/s
measured throughput · $1.25 input / $10.00 output per million tokens
OpenAICHEAPEST$0.63 in/1M$5.00 out/1M31 tok/s400K—32m agoOpenRouter$1.25 in/1M$10.00 out/1M—400K—33m agoOpenAI$1.25 in/1M$10.00 out/1M—128K—6h agoMicrosoft Azure AIzero-retention$1.25 in/1M$10.00 out/1M90 tok/s400K—32m agoMicrosoft Azure AIzero-retention$1.38 in/1M$11.00 out/1M59 tok/s400K—32m ago
OpenRouterFull specs, hardware verdicts and benchmarks on theGPT-5.1 model page →