AI Briefing#model-routing
The latest AI and developer news about #model-routing, with the original source and a short summary.
The latest AI and developer news about #model-routing, with the original source and a short summary.
Model routing for efficient AI agents is not simple classification but a systems optimization problem that must account for cost, complexity, and latency.
Cognition unveiled Devin Fusion, a multi-model harness that cuts costs by 35% while maintaining frontier-level performance.
As AI agents' token usage surges, automated routing technology that optimizes costs without sacrificing quality is becoming critical.
GitHub Copilot boosts the efficiency of agentic tasks through prompt caching and automatic model selection (Auto).
A 65k-scale hybrid router that efficiently switches between local and cloud models has been unveiled.
OpenSquilla has unveiled an open-source AI agent runtime that reduces token costs.
Starting June 15, Anthropic will separate Claude Code and Agent SDK usage into distinct credits.
Manifest Router has begun supporting routing for GPT-5.5 and GPT-5.5 Pro.
SMG separated serving CPU work into a Rust gateway to eliminate the Python GIL bottleneck.
Zo Computer cut its retry rate by 20x using Vercel's AI SDK and AI Gateway.
By splitting work between GLM and Sonnet, OpenClaw operating costs were cut to under $30 per month.