Llm Router

LLM Router

Selects the optimal LLM model for each task. The single biggest cost lever in multi-agent systems — intelligent routing saves 45-85% while maintaining 95%+ of top-model quality.

---

When to Use

✅ Use for:

• Deciding which model to call for a specific task
• Assigning models to DAG nodes in agent workflows
• Optimizing LLM API costs across a system
• Building cascading try-cheap-first patterns

❌ NOT for:

• Prompt engineering (use prompt-engineer)
• Model fine-tuning or training
• Comparing model architectures (academic research)

---

Routing Decision Tree

flowchart TD
  A{Task type?} -->|Classify / validate / format / extract| T1["Tier 1: Haiku, GPT-4o-mini (~$0.001)"]
  A -->|Write / implement / review / synthesize| T2["Tier 2: Sonnet, GPT-4o (~$0.01)"]
  A -->|Reason / architect / judge / decompose| T3["Tier 3: Opus, o1 (~$0.10)"]
  
  T1 --> Q1{Quality sufficient?}
  Q1 -->|Yes| Done1[Use cheap model]
  Q1 -->|No| T2
  
  T2 --> Q2{Quality sufficient?}
  Q2 -->|Yes| Done2[Use balanced model]
  Q2 -->|No| T3

---

Tier Assignment Table

---

Three Routing Strategies

Strategy 1: Static Tier Assignment (Start Here)

Assign model by task type at DAG design time. No runtime logic. Gets 60-70% of possible savings.

nodes:
  - id: classify
    model: claude-haiku-4-5     # Tier 1: $0.001
  - id: implement
    model: claude-sonnet-4-5    # Tier 2: $0.01  
  - id: evaluate
    model: claude-opus-4-5      # Tier 3: $0.10

Strategy 2: Cascading (Try Cheap First)

Try the cheap model; if quality is below threshold, escalate. Adds ~1s latency but saves 50-80% on nodes where cheap succeeds.

1. Execute with Tier 1 model
2. Quick quality check (also Tier 1 — costs ~$0.001)
3. If quality ≥ threshold → done
4. If quality < threshold → re-execute with Tier 2

Best for nodes where you're genuinely unsure which tier is needed.

Strategy 3: Adaptive (Learn from History)

Record success/failure per task type per model. Over time, the router learns:

• "Classification nodes always succeed on Haiku" → stay cheap
• "Code review nodes fail on Haiku 40% of the time" → upgrade to Sonnet
• "Architecture nodes succeed on Sonnet 90% of the time" → don't need Opus

Gets 75-85% savings after ~100 executions of training data.

---

Provider Selection

Once model tier is chosen, select the provider:

---

Cost Impact Example

10-node DAG, "refactor a codebase":

---

Anti-Patterns

Always Use the Best Model

Wrong: Route everything to Opus/o1 "for quality." Reality: 60%+ of typical DAG nodes are classification, validation, or formatting — tasks where Haiku performs identically to Opus. You're burning money.

Always Use the Cheapest Model

Wrong: Route everything to Haiku "for cost." Reality: Complex reasoning, architecture design, and quality judgment genuinely need stronger models. Haiku will produce plausible-looking but subtly wrong output on hard tasks.

Ignoring Latency

Wrong: Only optimizing for cost, ignoring that Opus takes 5-10x longer than Haiku. Reality: In a 10-node DAG, model choice affects total execution time as much as cost. Route time-critical paths to faster models.

No Feedback Loop

Wrong: Setting model tiers once and never adjusting. Reality: As models improve (Haiku gets smarter every generation), tasks that needed Sonnet last month may work on Haiku today. Record outcomes and adapt.

Changelog: llm-router

v1.0.0 (2026-02-05)

Created

• Routing decision tree (task type → model tier)
• Tier assignment table (13 task types mapped to 3 tiers with costs)
• Three routing strategies: static tier, cascading try-cheap-first, adaptive from history
• Provider selection matrix
• Cost impact analysis (76-92% savings demonstrated)
• 4 anti-patterns (always-best, always-cheapest, ignoring latency, no feedback loop)
• Based on research: Martian Model Mapping, Unify.ai neural scoring, RouteLLM preference-data routing