Models /GPT-5 /Where to run

Provider guide

Where to run GPT-5

5 live listings tracked.

CHEAPEST

$1.25 / $10.00

per 1M tokens in / out

FASTEST MEASURED

60 tok/s

measured throughput · $1.25 input / $10.00 output per million tokens

ProviderIn / 1MOut / 1MThroughputContextQuantSynced

OpenRouter$1.25 in/1M$10.00 out/1M—400K—3 hours ago Microsoft Azure AIzero-retention$1.25 in/1M$10.00 out/1M49 tok/s400K—3 hours ago OpenAI$1.25 in/1M$10.00 out/1M—128K—3 hours ago OpenAICHEAPEST$1.25 in/1M$10.00 out/1M60 tok/s400K—3 hours ago Microsoft Azure AIzero-retention$1.38 in/1M$11.00 out/1M29 tok/s400K—3 hours ago

Full specs, hardware verdicts and benchmarks on the GPT-5 model page →