Models /GPT-5.4 Nano /Where to run

Provider guide

Where to run GPT-5.4 Nano

5 live listings tracked.

CHEAPEST

$0.20 / $1.25

per 1M tokens in / out

FASTEST MEASURED

77 tok/s

measured throughput · $0.10 input / $0.63 output per million tokens

ProviderIn / 1MOut / 1MThroughputContextQuantSynced

OpenRouter$0.20 in/1M$1.25 out/1M—400K—30 min ago Microsoft Azure AIzero-retention$0.20 in/1M$1.25 out/1M53 tok/s400K—29 min ago OpenAICHEAPEST$0.20 in/1M$1.25 out/1M66 tok/s400K—29 min ago Microsoft Azure AIzero-retention$0.22 in/1M$1.38 out/1M11 tok/s400K—29 min ago OpenAIflex tier$0.10 in/1M$0.63 out/1M77 tok/s400K—29 min ago

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