Models /GPT-5.4 Mini /Where to run

Provider guide

Where to run GPT-5.4 Mini

6 live listings tracked.

CHEAPEST

$0.75 / $4.50

per 1M tokens in / out

FASTEST MEASURED

76 tok/s

measured throughput · $0.75 input / $4.50 output per million tokens

ProviderIn / 1MOut / 1MThroughputContextQuantSynced

OpenRouter$0.75 in/1M$4.50 out/1M—400K—3 hours ago Microsoft Azure AIzero-retention$0.75 in/1M$4.50 out/1M46 tok/s400K—3 hours ago OpenAICHEAPEST$0.75 in/1M$4.50 out/1M76 tok/s400K—3 hours ago Microsoft Azure AIzero-retention$0.82 in/1M$4.95 out/1M25 tok/s400K—3 hours ago OpenAIflex tier$0.38 in/1M$2.25 out/1M51 tok/s400K—3 hours ago OpenAIfast tier$1.50 in/1M$9.00 out/1M72 tok/s400K—3 hours ago

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