LLM gateway & model routing template

Components in this architecture diagram

• Apps & agents
• LLM gateway
• API keys & per-team budgets
• Semantic cache hit?
• Return cached answer
• Route by task
• Small fast model
• Frontier model
• Code-tuned model
• Self-hosted open model
• Provider error?
• Fallback provider
• Prompts, tokens, cost, latency
• Usage & cost dashboard
• PII redaction

How to use this architecture diagram template

1. Click Open in the editor. The architecture diagram opens on a new page in FlowDiagram — nothing is uploaded and there is no sign-up.
2. Rename, add or delete shapes and drag them where you want; connectors stay attached as things move.
3. Drop in vendor logos from the library — 1,160 of them, including every AWS, Azure and Google Cloud service icon — or restyle it with the colour and theme controls.
4. Prefer text? Edit the Mermaid source below and paste it in through ☰ → Import diagram (see the Mermaid editor); it imports as an editable diagram.
5. Export to PNG, SVG or PDF, or press Ctrl+L for a link that carries the whole diagram.

Mermaid source

The whole template is the text below. Paste it into FlowDiagram, keep it in Git next to the code it describes, or hand it to an AI assistant to extend.

flowchart LR
  APPS((Apps & agents)) --> GW[LLM gateway]
  GW --> AUTH[API keys & per-team budgets]
  AUTH --> CACHE{Semantic cache hit?}
  CACHE -->|Yes| RET[Return cached answer]
  CACHE -->|No| ROUTER{Route by task}
  ROUTER -->|Simple| SMALL[Small fast model]
  ROUTER -->|Complex reasoning| LARGE[Frontier model]
  ROUTER -->|Code| CODE[Code-tuned model]
  ROUTER -->|Private data| LOCAL[Self-hosted open model]
  LARGE --> FAIL{Provider error?}
  FAIL -->|Yes| FALLBACK[Fallback provider]
  GW --> LOG[(Prompts, tokens, cost, latency)]
  LOG --> DASH[Usage & cost dashboard]
  GW --> PII[PII redaction]

Related: System architecture diagram tool · Mermaid editor · All agentic ai & multi-agent systems templates · All 521 templates