Models /GPT-5 Nano /Where to run

Provider guide

Where to run GPT-5 Nano

5 live offers tracked.

CHEAPEST

$0.050 / $0.40

per 1M tokens in / out

FASTEST MEASURED

159 tok/s

measured throughput · $0.025 input / $0.20 output per million tokens

ProviderIn / 1MOut / 1MThroughputContextQuantSynced

OpenRouterCHEAPEST$0.050 in/1M$0.40 out/1M—400K—3h ago OpenAI$0.050 in/1M$0.40 out/1M96 tok/s400K—3h ago OpenAIflex tier$0.025 in/1M$0.20 out/1M159 tok/s400K—3h ago Microsoft Azure AIzero-retention$0.050 in/1M$0.40 out/1M61 tok/s400K—3h ago Microsoft Azure AIzero-retention$0.055 in/1M$0.44 out/1M44 tok/s400K—3h ago

Full specs, hardware verdicts and benchmarks on theGPT-5 Nano model page →