Models /GPT-4o /Where to run
Provider guide

Where to run GPT-4o

3 live offers tracked.

CHEAPEST
$2.50 / $10.00
per 1M tokens in / out
FASTEST MEASURED
57 tok/s
measured throughput · $2.50 input / $10.00 output per million tokens
OpenRouterCHEAPEST$2.50 in/1M$10.00 out/1M128K14m agoOpenAI$2.50 in/1M$10.00 out/1M57 tok/s128K13m agoMicrosoft Azure AIzero-retention$2.50 in/1M$10.00 out/1M49 tok/s128K13m ago
Full specs, hardware verdicts and benchmarks on theGPT-4o model page →