Radar / AI infrastructure / DeepSeek App API
DeepSeek App API: the whole consumer app, now as developer APIs
DeepSeek opened its app's capabilities through its API: web search, file parsing, URL reading, safety checks, voice and OCR, plus an open-source chat client.
Why it matters
One vendor, one bill, one API key now covers the full chatbot stack that used to need five vendors glued together, and the MIT-licensed demo client shows exactly how to wire it up.
What you could build with it
An indie developer could fork the open-source chat demo and ship a niche research assistant that combines DeepSeek's built-in web search and file parsing with a domain-specific workflow, without wiring up separate search, OCR and voice vendors.
Does it hold up?
Too early to judge: the APIs went live Nov 13 and the demo is explicitly a reference prototype, not production-ready; the open question is tool-call pricing, which the docs do not yet publish.
Built with DeepSeek App API
- DeepSeek puts its app features into the API: search, files and voicemedium · Breaks down what is in the chat call vs standalone services, and the per-call pricing for search, fetch and OCR.
- DeepSeek opens its full app toolkit to developers through its APIarticle · Reports the Nov 13 announcement, the deepseek-flash model behind it, and the standalone Search, Fetch, OCR, ASR and TTS services.
- DeepSeek turns chat app into full API suite with voice, OCRarticle · Covers the five standalone APIs, launch pricing (search $0.75 per 1,000 requests, OCR $0.225 per 1,000 pages) and the open-source demo.
Learn more
First spotted on github: source.
More AI infrastructure
vLLM v0.34.0: extensible KV cache by default, Model Runner V2 only, and 10 new modelsThe open inference engine's latest release spans 1,061 commits from 412 contributors, adds 10 models including Mistral…infra · JEV 0.86llama.cpp v1.0.0: the local-AI engine's first stable releasellama.cpp and ggml hit v1.0.0, promising semantic versioning so breaking C API changes only arrive with major bumps.infra · JEV 0.84colibri: run 744B-parameter MoE models on consumer hardwarePure-C inference engine with zero dependencies that streams MoE experts from NVMe disk, keeping hot experts on GPU…infra · JEV 0.78claude-mem: persistent memory plugin that lets coding agents pick up where the last session left offPlugin that hooks five Claude Code lifecycle events, compresses session activity into a local SQLite + Chroma store…infra · JEV 0.74FreeToken: datacenter-scale MoE serving on desktop GPUsAn edge-native mixture-of-experts serving engine from UC Berkeley researchers that runs 290B+ parameter MoE models on…infra · JEV 0.74GBrain: Garry Tan's self-wiring memory layer for AI agentsY Combinator CEO Garry Tan's open-source, markdown-first knowledge layer that gives OpenClaw and Hermes agents…infra · JEV 0.71
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.