Skip to main content
This tutorial assigns different models to different tasks in a single workflow — a cheap, fast model for the spec, a capable model for coding, and a different model for review. The routing is controlled by a CSS-like stylesheet.

​
The workflow

Multi-Model workflow: Start → Write Spec (Haiku) → Implement (Sonnet) → Write Tests (Sonnet) → Code Review (Sonnet) → Exit
multi-model.fabro
digraph MultiModel {
    graph [
        goal="Build and review a utility function using multiple models",
        model_stylesheet="
            * { model: claude-haiku-4-5;reasoning_effort: low; }
            .coding { model: claude-sonnet-4-5;reasoning_effort: high; }
            #review { model: claude-sonnet-4-5;reasoning_effort: high; }
        "
    ]
    rankdir=LR

    start [shape=Mdiamond, label="Start"]
    exit  [shape=Msquare, label="Exit"]

    spec      [label="Write Spec", prompt="Write a brief spec for a TypeScript string utility module with 3 functions: slugify, truncate, and capitalize. Output the spec only.", shape=tab]
    implement [label="Implement", prompt="Implement the TypeScript string utility module from the spec. Write it to string-utils.ts.", class="coding"]
    test      [label="Write Tests", prompt="Write tests for the string utility module using Bun's test runner. Write to string-utils.test.ts.", class="coding"]
    review    [label="Code Review", prompt="Review the implementation and tests. Check for edge cases, type safety, and correctness. Provide a brief verdict.", shape=tab]

    start -> spec -> implement -> test -> review -> exit
}

fabro run files-internal/demo/08-multi-model.fabro

​
Model stylesheets

The model_stylesheet graph attribute contains CSS-like rules that assign models to nodes: 
* { model: claude-haiku-4-5;reasoning_effort: low; }
.coding { model: claude-sonnet-4-5;reasoning_effort: high; }
#review { model: claude-sonnet-4-5;reasoning_effort: high; }

​
Selectors

SelectorSyntaxMatchesSpecificity
Universal*All nodes0
Shapebox, tab, etc.Nodes with that shape1
Class.classnameNodes with class="classname"2
ID#nodeidA specific node by ID3
Higher specificity wins. If two rules have the same specificity, the last one in the stylesheet wins.

​
How this workflow routes

NodeMatchesModelWhy
spec* (universal)HaikuSimple generation task — fast and cheap
implement.coding (class)SonnetCoding requires a capable model
test.coding (class)SonnetTest writing also needs coding capability
review#review (ID)SonnetReview needs careful analysis

​
Assigning classes

Set the class attribute on a node to target it with class selectors: 
implement [label="Implement", class="coding"]
Multiple classes are space-separated: class="coding critical".

​
Properties

Stylesheets support four properties:
PropertyDescription
modelModel ID or alias (e.g. claude-sonnet-4-5, opus, gemini-pro)
providerProvider name (optional — auto-inferred from the model catalog when omitted)
reasoning_effortlow, medium, or high
backendapi (default) or cli

​
Why route models?

Not every task needs a frontier model:
  • Spec writing, classification, summarization — use a fast, cheap model (Haiku, Flash Lite)
  • Code implementation, complex reasoning — use a capable model (Sonnet, Opus, GPT-5.2)
  • Cross-critique — use a different provider so the reviewer brings fresh eyes
Model routing lets you optimize cost and latency without changing the workflow structure. Swap claude-haiku-4-5 to gemini-3-flash-preview in the stylesheet and the workflow behaves the same — just with a different model underneath.

​
Explicit overrides

A model set directly on a node attribute always beats the stylesheet: 
implement [label="Implement", class="coding", model="claude-opus-4-6"]
This node uses Opus regardless of what .coding says. See Model Stylesheets for the full reference and Models for available model IDs.

​
What you’ve learned

  • Model stylesheets use CSS-like rules to assign models to nodes
  • Selectors match by universal (*), shape, class (.name), or ID (#name)
  • Specificity determines which rule wins when multiple match
  • Route cheap models to simple tasks and capable models to hard ones

​
Next

Ensemble

Fan out to multiple providers and synthesize their independent opinions.