Models /GPT-5.4 Nano /Where to run

Provider guide

Where to run GPT-5.4 Nano

4 live offers tracked.

CHEAPEST

$0.20 / $1.25

per 1M tokens in / out

FASTEST MEASURED

68 tok/s

measured throughput · $0.20 input / $1.25 output per million tokens

ProviderIn / 1MOut / 1MThroughputContextQuantSynced

OpenRouterCHEAPEST$0.20 in/1M$1.25 out/1M—400K—15m ago OpenAI$0.20 in/1M$1.25 out/1M68 tok/s400K—14m ago OpenAIflex tier$0.10 in/1M$0.63 out/1M63 tok/s400K—14m ago Microsoft Azure AIzero-retention$0.20 in/1M$1.25 out/1M35 tok/s400K—14m ago

Full specs, hardware verdicts and benchmarks on theGPT-5.4 Nano model page →