LAB · Operations
Model Routing Matrix
Turn quality, latency, privacy, context, and cost into a testable routing plan without vendor lock-in.
- Suggested time
- 12 min
- Output artifact
- A primary model, fallback, and promotion-gate policy.
- Privacy
- No API is required and your constraints are not transmitted.
Local educational tool. Validate every result before production use.
When to use it
Model router
Use it when comparing models for different tasks or before replacing a production provider.
How to use it well
- 1
Enter a real case without secrets or personal data.
- 2
Run, inspect, and challenge the assumptions; the output is not automatic truth.
- 3
Save the artifact in your project and turn it into a reviewable test or decision.
Related foundations
Production Engineering for LLM Systems
Cost optimization: semantic caching, model routing, and batching
Associated Labs: 03_cache_semantico.py and 04_model_routing.py
Open foundation20 minLab 04 — Auditable model routing between GPT-5.6 Luna, Terra, and Sol
Localized walkthrough. Run the canonical public lab locally and preserve the result as evidence.
Open foundation8 minCurrent Landscape: GPT-5.6, Claude 5, Gemini 3.x, Llama 4, and Mistral
Module 1 · Topic 4 · Estimated study time: 2 h Associated labs: labs/01_primer_llamada_openai.py, labs/02_primer_llamada_anthropic.py Associated exercises: 5, 6, 7, and 10.
Open foundation