Keenable 1.0 tops AI web search benchmarks, 330ms queries, 50% fewer tokens
Scobleizer · x · 2026-11-13
Keenable launched 1.0 of its agent-focused web search API, claiming #1 across major AI search benchmarks: 83 on the Artificial Analysis Search Index (vs Exa 80, Perplexity 80), 87 on BrowseComp, 88 on DeepSearchQA, and 77% on its open-source NEEDLE benchmark, with 330ms per query vs Perplexity's 1,070ms.
The index learns from every agent query, returns only the needed document portions to cut tokens 50% on research tasks, and adds 100M knowledge cards.
A free API key includes 100K requests/month (no card needed), then $4 per 1,000 requests. It also launched an agent storefront (via llms.txt) where agents can self-serve purchase. The company previously raised $26M from Accel and Conviction.
More from coding & agent
- Open-source flight search MCP server refuses to answer what it can't confirm, curbing model hallucination — Fast_Entrance7839 · 2026-11-13
- Amplitude launches Wave: AI that decides what to build next from product data — testingcatalog · 2026-11-13
- jxnlco: when AI makes you faster, go deep on new things and grow your taste — jxnlco · 2026-11-13
- Vibe-coded space-defense game ORBITAL SIEGE shows Three.js gameplay from one prompt — kimmonismus · 2026-11-13
- AI-generated WebGL2 shader bends light around a black hole on the first try — kimmonismus · 2026-11-13
- Sententos puts a personal agent in your Mac's notch that can take over your screen — ycombinator · 2026-11-13