DeepSeek opens its app toolkit via API: web search, voice, file input and safety checks
AGI Hunt · wechat · 2026-11-13
DeepSeek has opened up the full capability suite behind its app to developers: web search, URL reading, file input (PDF/Office/images), ASR + TTS voice, and safety checks — all available on the V4.1-Flash model via Messages, Responses, and Chat Completions endpoints.
The author's hands-on test: deep-thinking search completed 3 reasoning rounds, 2 searches and 4 page opens in 11.4s with all answers correct; the standalone OCR API parsed a price-sheet image in 2.2s; TTS supports 10 languages at 1 fen per sentence, ASR supports 21 languages. Safety checks return 400 errors on flagged input. Pricing: web search 0.5 fen per query (counted per query word), OCR 0.15 fen per page. DeepSeek also open-sourced an MIT-licensed pure-frontend demo (chat-demo) that replicates the app, running entirely in the browser with just an API key.
More from Models
- Cloudflare hosts Thinking Machines' inkling 2 small on Workers AI at day-0 speed — michellechen · 2026-11-14
- Masked decoding trick tames text rivers in Gemma 3 12B, with a width-aware LoRA and coherence RL — cephaloform · 2026-11-14
- 250,000-human AI mafia game finds OpenAI models lie most, Anthropic snitches — Scobleizer · 2026-11-14
- Developer downgrades Claude Ultra to Pro and moves all work to Codex over 5-hour rate limits — umeshonai · 2026-11-14
- Pangram details per-domain false positive rates (1 in 10,000), enabling profitable AI detection — soldni · 2026-11-14
- Blogger predicts GPT-6.2 launches before Nov 19, floats three reasons for the delay — kimmonismus · 2026-11-14