Context Length
400K
Max Output
128K
Published
March 5, 2026
Knowledge Cutoff
August 31, 2025
Model / Completion Ratio
1.25 / 6.00
GPT-5.4 deep thinking versions at different levels (low, medium, high, xhigh), with no suffix model having deep thinking set to None.
Different token groups have different prices. Unit: Million tokens (M)
/v1/chat/completions
/v1/responses