DeepSeek opens its app's features to developers as APIs, including search, OCR and speech

DeepSeek has made the features of its consumer app available to developers through its API, according to a release note dated November 13.

Its V4.1-Flash model now supports web search with citations, a deep thinking search that reads pages during multi-step reasoning, file input for PDFs, Office files and images, automatic reading of links in user messages, and safety checks that return refusal indicators when risks are detected. DeepSeek says the tool calls and context assembly are handled on its servers, across its Messages, Responses and Chat Completions interfaces.

Search, page fetching, optical character recognition, speech recognition and text to speech are also available as standalone APIs. The extra capabilities carry tool usage fees on top of standard token charges. Public-facing apps must enable the safety checks, and developers remain responsible for content moderation, model registration where required and labelling AI-generated content, DeepSeek says.

The company also released an open-source chat frontend demo that can import DeepSeek conversation history. "The DeepSeek App is just one way to interact with AI. Its capabilities are now yours to call and combine freely," the note says.