DeepSeek opens the DeepSeek App's search, file, URL and safety features to developers through its APIs

DeepSeek says it is opening to developers the capabilities behind the conversation experience of its App and web version. Developers enable parameters in the existing APIs, and the service handles the tool calls and context assembly.

According to DeepSeek's API update note, the deepseek-flash model supports these in the Messages, Responses and Chat Completions APIs:

• Web search: with thinking disabled and the deepseek_web_search tool enabled, the model runs web or image searches as the question requires and answers with citations.
• Deep thinking search: with thinking enabled and the same tool, the model searches and reads links on its own over several reasoning steps.
• File input: PDFs, Office files, images and more can be uploaded; after plain-text extraction or rich-layout parsing they are added to the conversation context.
• URL reading: with the deepseek_read_url tool enabled, the model detects links in the user message, fetches the pages and answers with them in context.
• Model safety: a safety check parameter reviews model input and output and returns a refusal marker when it finds a risk. DeepSeek says services offered to the public should enable it and meet obligations such as content safety review, large model registration and AI labeling.

The underlying capabilities and the voice capabilities are also offered as standalone APIs: Search and Fetch, OCR, ASR and TTS. DeepSeek also published an open-source demo chat client built on these APIs, which can import a user's DeepSeek chat history. Prices are on DeepSeek's Models & Pricing page.