Models /GPT-5.4 /Where to run

Provider guide

Where to run GPT-5.4

7 live offers tracked.

CHEAPEST

$2.50 / $15.00

per 1M tokens in / out

FASTEST MEASURED

142 tok/s

measured throughput · $2.75 input / $16.50 output per million tokens

ProviderIn / 1MOut / 1MThroughputContextQuantSynced

OpenRouterCHEAPEST$2.50 in/1M$15.00 out/1M—1.1M—14m ago OpenAI$2.50 in/1M$15.00 out/1M57 tok/s1.1M—13m ago Amazon Bedrock$2.75 in/1M$16.50 out/1M142 tok/s1.1M—13m ago OpenAIflex tier$1.25 in/1M$7.50 out/1M37 tok/s1.1M—13m ago Microsoft Azure AIzero-retention$2.50 in/1M$15.00 out/1M66 tok/s1.1M—13m ago Microsoft Azure AIzero-retention$2.75 in/1M$16.50 out/1M55 tok/s1.1M—13m ago OpenAIpriority tier$5.00 in/1M$30.00 out/1M95 tok/s1.1M—13m ago

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