Context Length
400K
Max Output
128K
Published
February 6, 2026
Knowledge Cutoff
August 3, 2025
Model / Completion Ratio
0.875 / 8.00
The version specifically optimized for chat dialogue offers faster response speeds compared to traditional GPT-5+ models.
Different token groups have different prices. Unit: Million tokens (M)
/v1/chat/completions
/v1/responses