Models /GPT-5.3-Codex /Where to run

Provider guide

Where to run GPT-5.3-Codex

4 live offers tracked.

CHEAPEST

$1.75 / $14.00

per 1M tokens in / out

FASTEST MEASURED

99 tok/s

measured throughput · $3.50 input / $28.00 output per million tokens

ProviderIn / 1MOut / 1MThroughputContextQuantSynced

OpenRouterCHEAPEST$1.75 in/1M$14.00 out/1M—400K—3h ago OpenAI$1.75 in/1M$14.00 out/1M70 tok/s400K—3h ago Microsoft Azure AIzero-retention$1.75 in/1M$14.00 out/1M57 tok/s400K—3h ago OpenAIpriority tier$3.50 in/1M$28.00 out/1M99 tok/s400K—3h ago

Full specs, hardware verdicts and benchmarks on theGPT-5.3-Codex model page →