DeepSeek opens its full app API for developers

DeepSeek has officially opened its full suite of app APIs, bringing the app's interactive features into its existing interfaces. Developers can turn on extra settings to unlock features like deep thinking search and file input. Voice capabilities are also open as standalone APIs, including OCR, ASR and TTS, usable alone or together.

The V4.1-Flash model now supports web search, deep thinking search, file input, link reading and safety checks. It can process PDF, Office and image files into chat context. Tool calls and context stitching are handled automatically on the server side.

Besides token fees, tool calls cost extra: text and image search is 5 yuan per 1,000 calls, web scraping is 5 yuan per 1,000 calls, OCR is 1.5 yuan per 1,000 pages, speech recognition is 0.39 yuan per hour at a limited-time half price, and speech synthesis is 1.5 yuan per 10,000 characters.

DeepSeek also open-sourced a lightweight frontend demo based on the new API, which supports importing past chats, making it easy for developers to try it out and plug it into their own workflows.