Hybrid local/cloud routing with LiteLLM

The goal is not to use local for everything. The goal is to use local for routine, private, or low-cost work, and scale to an external model only when the use case justifies it and it is logged.

Design model groups by task, cost, and sensitivity.
Use fallbacks without hiding important errors.
Log when a task moved from local to cloud.

Terminal

model_list:
  - model_name: local-fast
    litellm_params:
      model: ollama/qwen2.5:7b
      api_base: http://localhost:11434

  - model_name: local-gpu
    litellm_params:
      model: openai/Qwen/Qwen2.5-14B-Instruct
      api_base: http://localhost:8000/v1
      api_key: none

  - model_name: frontier-review
    litellm_params:
      model: openai/gpt-4.1-mini
      api_key: os.environ/OPENAI_API_KEY

Practical policy

Local-fast: drafts, classification, summaries of non-sensitive documents.
Local-gpu: long tasks, internal RAG, and agents with more context.
Frontier-review: final review, difficult reasoning, or repeated local failure.

Terminal

routing_rules:
  sensitive_data: local_only
  max_local_retries: 2
  allow_cloud_fallback:
    - public_code_review
    - generic_planning
    - final_quality_check
  require_human_approval:
    - customer_data
    - legal_docs
    - financial_docs

Official sources

LiteLLM Docs
LiteLLM routing and load balancing
LiteLLM fallbacks
Ollama API

LiteLLM as a Gateway and Cost Control Migrate a cloud agent to local

Complete Aulafy mapSee how this lesson fits without leaving your path.

Complete Aulafy map

How all courses connect

This is not a checklist. Start with the foundation, choose an outcome, and go deeper only when your project needs more control.

1Understand
2Apply or build
3Operate with confidence

Choose an application

Turn the foundation into a visible outcome: a website, a business improvement, media, or an interactive experience.

AI for small businesses and freelancersUse AI where it improves real work.Beginner to intermediate · 20 lessonsView course Generative AI: image, voice and videoCreate production-ready media with AI pipelines.Beginner to intermediate · 7 lessonsView course Games, 3D and simulations with AIPrototype interactive worlds with AI-assisted tools.Beginner to intermediate · 6 lessonsView course

Continue into the technical branch when you need to maintain code, data, or infrastructure.

Build with code

Prepare your environment, work with coding agents, and run models while keeping control of your projects.

Aulafy foundationsPython, Git, terminal, and Docker for learning AI smoothly.Beginner · 6 lessonsView course Codex for programmersBuild, test, and ship changes with OpenAI Codex.Beginner to advanced · 10 lessonsView course Claude Code, from zero to proBuild real software by talking to AI in your terminal.Beginner to advanced · 24 lessonsView course Claude Code + Local AIPrivate AI tools that run on your machine.Intermediate · 34 lessonsView course

This branch prepares you to design and operate reliable AI systems.

Take systems to production

Combine retrieval, agents, evaluation, security, deployment, and model adaptation when the problem requires it.

Advanced and secure RAGBuild retrieval systems that answer better and leak less.Intermediate · 14 lessonsView course Agents and automationDesign agents that can work, recover and stay under control.Intermediate to advanced · 20 lessonsView course Production agents with LangGraph and n8nTake agent prototypes into reliable operations.Intermediate to advanced · 9 lessonsView course Self-hosted AI automation for small businessesRun AI workflows on your own infrastructure.Intermediate · 10 lessonsView course AI Router and content systemRoute local and frontier models with quality, cost, and privacy controls.Intermediate to advanced · 6 lessonsView course AI security and evaluationMeasure, test and harden AI systems before trusting them.Intermediate · 7 lessonsView course Local MLOps and model deploymentYou are hereServe, monitor and operate models from your own stack.Intermediate to advanced · 10 lessonsView course Fine-tuning and post-training for LLMsTrain useful adapters without losing control.Intermediate to advanced · 8 lessonsView course

You do not need every course: choose the component your system needs and return as it grows.

View full catalogue