Spring AI model router sample: auto-tier prompts across four OpenAI models
therealdanvega · x · 2026-09-22
- Dan Vega released a Spring Boot sample app using Spring AI and the community TypeSafe AI Starter that picks the right OpenAI model per request.
- Not every prompt needs the most capable model: the app routes prompts into four tiers via Jev—luna (greetings, simple formatting), terra (summaries, short functions), sol (multi-step reasoning, cross-file code), and astra (research, architecture, hard debugging).
- Jev returns a label, confidence, and probability per tier; the controller sets that model on the ChatClient call and returns the routing decision. Cheaper tiers are preferred unless the prompt clearly needs more.
More from coding & agent
- WeChat becomes China's AI agent gatekeeper: a Tencent-controlled A2A channel decides who gets in — bookwormengr · 2026-09-22
- Scale AI's Alexandr Wang hypes user giving Muse agent access to their bank account — alexandr_wang · 2026-09-22
- Xiaomi MiMo's CodeMIDAS scales agentic coding RL environments from code itself — _akhaliq · 2026-09-22
- New research: browser agent predicts your next action from page and history alone — aidangch · 2026-09-22
- Meituan launches CatPaw enterprise agent platform, already powering 30,000 active agents for 90,000 employees — bookwormengr · 2026-09-22
- Dev is building a game engine in C with Grok 4.7: "really good" — elonmusk · 2026-09-22