Models /GPT-5.6 Terra Pro /Where to run

Provider guide

Where to run GPT-5.6 Terra Pro

6 live listings tracked.

CHEAPEST

$2.00 / $12.00

per 1M tokens in / out

FASTEST MEASURED

72 tok/s

measured throughput · $2.00 input / $12.00 output per million tokens

ProviderIn / 1MOut / 1MThroughputContextQuantSynced

OpenRouter$2.00 in/1M$12.00 out/1M—1.1M—4 hours ago Microsoft Azure AIzero-retention$2.00 in/1M$12.00 out/1M53 tok/s1.1M—4 hours ago OpenAICHEAPEST$2.00 in/1M$12.00 out/1M72 tok/s1.1M—4 hours ago Microsoft Azure AIzero-retention$2.20 in/1M$13.20 out/1M24 tok/s1.1M—4 hours ago OpenAIflex tier$1.00 in/1M$6.00 out/1M24 tok/s1.1M—4 hours ago OpenAIfast tier$4.00 in/1M$24.00 out/1M32 tok/s1.1M—4 hours ago

Full specs, hardware verdicts and benchmarks on the GPT-5.6 Terra Pro model page →