The new Claude-Opus-4-6 dynamic thinking model automatically decides whether to engage in deep thinking based on prompts, with suffixes such as -max, -high, -medium, and -low determining the level of thinking.
Các nhóm token có giá khác nhau. Đơn vị: triệu token (M)
/v1/chat/completionsPOST/v1/messagesPOST