Search
Aliyun Bailian Unveils Price Cut for DeepSeek-V4-Pro Model's Implicit Caching
19 hour ago /
Read about 0 minute
Author：小编
On April 29, 2026, Alibaba Cloud's large-scale model service platform, Bailian, made an announcement. It stated that starting from 23:59:59 on the same day, the billing rate for implicit caching of the DeepSeek-V4-Pro model would be slashed to 1 yuan per million Tokens. Implicit caching comes into play solely when a request successfully retrieves data from the cache. In such scenarios, input Tokens are charged as cached_tokens. Conversely, input Tokens that fail to hit the cache will continue to be billed at the standard input_token rate. It's important to note that this price adjustment is specific to the implicit caching aspect, leaving the model's base inference price untouched.
-
C114 Communication Network -
Communication Home
7 X 24 Track global technological trends
