Baseten Adds Server-Side Web Search for Open-Weight Models via One-Line Tool Config
PolarBearby · x · 2026-09-17
- Baseten launched Hosted Tools and Grounded Inference (preview): open-weight models on Baseten can now call real-time web search server-side with a single config—no orchestration code, no extra vendor keys.
- Four launch search partners: Exa, Kena, p0, and You.com.
- Baseten claims 15% lower latency vs. client-side execution and avoids resending a growing context every turn.
- You.com's integration needs one line in the tools array ({"type": "basetenyousearch"}); same model, same request.
- The pitch: give open-weight models frontier-level web search parity at a fraction of closed-model prices.
Related event: Baseten Launches Hosted Tools and Grounded Inference for Open-Weight Models(6 posts)→
More from coding & agent
- Production Incident Investigation: A Six-Step Playbook from Triage to Postmortem — _jaydeepkarale · 2026-11-02
- Google's open-sourced "Elephant-Goldfish" workflow separates planning from review to curb sloppy AI output — gaganghotra_ · 2026-11-02
- InfoQ: A Systemic Approach to Memory, Knowledge, and Context in Agentic AI Architectures — AdiPolak · 2026-11-02
- Autonomous's Harness Pro uses an ESP32-P4, not a mini PC, to monitor AI coding agents — dee_hw · 2026-11-02
- RL-trained LFM2.5-24B adapter matches accuracy with 20% fewer tool calls — yb2698 · 2026-11-02
- Debugging production AI agents: error surfaces at step 5, root cause at step 3 — Ok-Machine7983 · 2026-11-02