Baseten launches server-side web search for open models, claiming 15% lower latency
AccBalanced · x · 2026-09-18
- Baseten introduced Hosted Tools and Grounded Inference, bringing server-side real-time web search to open-weight models via a single configuration.
- Until now, adding web search to open models meant hand-wiring orchestration, managing separate vendor keys, and paying latency taxes on every round trip.
- Baseten claims 15% lower latency vs. client-side execution, no extra vendor key, zero orchestration; launch partners include Exa, Keeable AI, P0, and You.com.
- A former Groq executive noted GroqCloud shipped a similar feature last year, calling the move of search tool calls into the inference server a clear performance win.
Related event: Baseten Launches Hosted Tools and Grounded Inference for Open-Weight Models(6 posts)→
More from coding & agent
- awa-video-reel: free Claude Code skill auto-edits shorts and records website B-roll — TawohAwa · 2026-11-02
- Econ PhD Job Market Database Hits 900+ Candidates, Open to Codex and Claude Code — aniketapanjwani · 2026-11-02
- Cron works by hand, fails on schedule: a 7-point debugging checklist — petrusenko_max · 2026-11-02
- Local quants vs Claude on 9 real private bugs: 3-bit costs thinking time, not score — FeydRowan · 2026-11-02
- Build products for AI, not humans: MCP lets Claude Code run everything — gefei55 · 2026-11-02
- Solo dev launches hosted MCP server with 31 tools scheduling to 20+ social networks — troyizzle · 2026-11-02