# DeepSeek API Input Cache Price Cut by 90%

- Category: Flash (快讯)
- Published: 2026-04-27T11:56:00.000Z
- Source date: 2026-04-27
- HTML: https://www.88z.ai/en/news/flash-20260427-76fdde598cc98760
- Markdown: https://www.88z.ai/en/news/flash-20260427-76fdde598cc98760.md
- Other language: https://www.88z.ai/news/flash-20260427-76fdde598cc98760.md

DeepSeek officially announced that the price for input cache hits across all API services has been reduced to one-tenth of the original rate, aiming to lower developer costs and improve cost-effectiveness in long-context scenarios.

## At a glance

- Input cache hit prices for all APIs reduced to 1/10 of original rates
- Pro models offer a stackable limited-time 75% discount until May 5

## The update

DeepSeek officially announced a significant adjustment to the input cache hit prices for its entire range of API services, reducing them to one-tenth of the original rates. Specifically, the cache hit input price for the DeepSeek-V4-Pro model has dropped to 0.025 yuan, while the DeepSeek-V4-Flash model is now priced at 0.02 yuan. Additionally, the Pro model offers a limited-time 75% discount that can be stacked until May 5. This major price reduction aims to lower invocation costs for developers and significantly enhance the cost-effectiveness of using APIs in long-context scenarios, providing more economical and efficient service support.

## Sources

- [IT之家](https://www.ithome.com/0/943/748.htm) (2026-04-27)

This article is an AI-assisted synthesis by 88Z AI based on the public sources below. Product claims and availability are attributed to their publishers. It does not represent independent testing or first-hand reporting.