EdTech Tracker

← Coding lens

model routing

architecture judged 100% likely a named technique or architecture

First seen
2025-10-23
Independent sources
12
Articles
31
Last 4 weeks vs prior
0 vs 12

See how it has spread across media tiers

Mentions over time

Articles per week (by publish date) using the term, in any spelling.
04.592025-W422026-W282026-W41
Table view
WeekArticlesSources
2025-W4211
2026-W0931
2026-W1181
2026-W1411
2026-W1811
2026-W2511
2026-W2811
2026-W3422
2026-W3711
2026-W3922
2026-W4095
2026-W4111

In their words

ports : - " 8000:8000" environment : - QDRANT_URL=http://qdrant:6333 - OLLAMA_URL=http://ollama:11434 - EMBEDDING_MODEL=bge-large-en-v1.5 - GENERATION_MODEL=llama3.1:8b depends_on : - qdrant - ollama volumes : - ./data:/app/data volumes : qdrant_data : ollama_data : Kubernetes Deployment # k8s/rag-deployment.yaml apiVersion : apps/v1 kind : Deployment metadata : name : rag-api spec : replicas : 3

A model router for Claude Code, benchmarked: 82% cheaper, 2 tests lost

The level — What you have· The tell for gaps - 0 - Notebook — a prompt, a model, a happy-path demo · “it works on my examples” - 1 - Determinism— agents propose (never act); fixed graph per capability; model contained to one node; loops bounded · the agent can write business state; behavior depends on the path it wandered - 2 - Evaluation — evals as a CI gate; baselines for drift; shadow evals fro

Cost: model routing Opus primary plans, synthesises and reviews; cheaper worker subagents execute in parallel.

You will spot runaway context growth, repeated identical calls and wrong model routing in minutes.

Candidate material is sensitive operational data even when the article's main concern is model routing.

OpenRouter One API for accessing multiple model providers Useful for model routing experiments; it does not replace document retrieval, reranking, or field-level evidence rules.

Build an AI model router Modern AI applications often have access to several models, and sending every request to the most expensive model is rarely necessary.A simple question might be handled by a small model, while a complex coding task could require a more capable model.