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
78 tok/s
measured throughput · $0.38 input / $2.25 output per million tokens
OpenRouter$0.75 in/1M$4.50 out/1M—400K—2 hours agoMicrosoft Azure AIzero-retentionCHEAPEST$0.75 in/1M$4.50 out/1M46 tok/s400K—2 hours agoOpenAI$0.75 in/1M$4.50 out/1M66 tok/s272K—2 hours agoMicrosoft Azure AIzero-retention$0.82 in/1M$4.95 out/1M25 tok/s400K—2 hours agoOpenAIflex tier$0.38 in/1M$2.25 out/1M78 tok/s400K—2 hours agoOpenAIfast tier$1.50 in/1M$9.00 out/1M67 tok/s400K—2 hours ago
Full specs, hardware verdicts and benchmarks on the GPT-5.4 Mini model page →