#model routing
Model Routing: 11 AI articles covering model routing news, analysis, and research
Articles
Perplexity Launches Orchestrator API for Failover and Model Routingβ7
Perplexity's Orchestrator API offers one endpoint for frontier and open-weight models with automatic provider failover, model routing, and a single invoice.
Ramp Hits $60B Valuation as It Doubles Down on AI-Poweredβ9
Ramp raises $1.85B at a $60B valuation, doubling down on AI-powered finance operations as annualized revenue tops $2B and purchase volume surges 175%.
9 Best AI Gateways in 2026: Bifrost, Portkey, LiteLLM, Kong andβ9
Compare the 9 best AI gateways in 2026, including Bifrost, Portkey, LiteLLM, and Kong, with features, rankings, and vendor risk insights for production teams.
Microsoft AI Releases Microsoft-Decision-1: A Qwen3.5-9Bβ8
Microsoft-Decision-1, a Qwen3.5-9B decision-scoring model for routing and agent control, returns calibrated probabilities with 85 ms latency and 83.5% accuracy.
Architect Launches Liquid Inference: A Real-Time Auctionβ9
Architect launches Liquid Inference, a real-time auction marketplace where LLM providers bid per request, letting developers cut costs by swapping a base URL wi...
Together Link: A Free CLI That Runs Open Models Like Kimi K3 andβ9
Together Link is a free MIT-licensed CLI that connects Claude Code, Codex, and OpenCode to open models like Kimi K3 and GLM 5.3 hosted on Together AI.
20 Agentic Use Cases of TypeSafe AI's Jev: A System One Modelβ8
Jev, TypeSafe AI's System One model, turns unstructured state into typed decisions with calibrated probabilities for 20 agentic use cases like routing and orche...
COMED: The Missing Middle Between Routing and Collaboration inβ10
COMED introduces a post-anchor controller for selective multi-LLM collaboration, using rescue-harm decomposition to boost reasoning accuracy while invoking fewe...
Do Small Language Models Know What They Don't Know? New Researchβ9
New research shows token entropy fails as a confidence signal in sub-3B language models, while semantic entropy enables routing gains up to +50 percentage point...
Project HydraFusion: Achieving Frontier-Level Quality Throughβ8
Project HydraFusion uses multi-model orchestration to achieve frontier-level AI quality by routing tasks to specialized models, rivaling monolithic systems by 2...
