Alibaba Cloud Baolian announces price reduction for implicit caching of DeepSeek-V4-Pro model

robot
Abstract generation in progress

Golden Finance reports that on April 29th, Alibaba Cloud announced that the Baolian large model service platform will lower the billing price for the implicit cache of the DeepSeek-V4-Pro model starting from 23:59:59 Beijing time on April 29, 2026.
The new price will be 1 yuan per million tokens.
The implicit cache only takes effect when the request hits the cache, and the input tokens that hit the cache are billed as cached_token;
input tokens that do not hit the cache are still billed at the standard input_token rate;
this adjustment only involves the implicit cache part, and the basic inference price of the model remains unchanged.

View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments