Topic · 6 stories
6 stories tagged routing on AI Tamer, newest first.
LiteLLM merged a Rust router core, deleted the Python router and moved proxy Redis traffic to Rust. It ships in v1.110.0-dev.1, not a stable release yet.
Base Labs released mammoth-1 (27B) and elephant-1 (9B) under MIT. They score options in one pass for routing and triage. Free on Baseten until 27 October.
A sparse mixture-of-experts router can choose an expert that has no remaining token slots. Here is what overflow means in Switch Transformer and how capacity changes the tradeoff.
An encoded slash can be identifier data or a path boundary. Parse URL structure before decoding, and give each routing layer one clear interpretation.
Fireworks (Sep 28, 2026) shipped FireRouter with Opus—a cache-aware serverless router among Claude Opus 5.5, GLM 5.3, and GLM 5.3 Flash, in the CLI and as a standalone endpoint.
An inside look at why AI systems switch between models — the cost-saving chooser everyone talks about, and the failover path that's where outages actually hide.
