---
title: "LLM Fallback"
description: "When no skill or WASM handler matches a task, the broker falls back to an LLM (Language Model) API. The LLM fallback is the last resort in the routing cascade: 1. Skill match — check registered patterns (free) 2. WASM ha"
resource: https://www.aiagents.nexus/docs/broker/llm-fallback
generated: { by: "process:nexus-agent-assets", at: 2026-09-07T09:13:03Z }
status: stable
---

# LLM Fallback

When no skill or WASM handler matches a task, the broker falls back to an LLM (Language Model) API.

## How It Works

The LLM fallback is the last resort in the routing cascade:

1. **Skill match** — check registered patterns (free)
2. **WASM handler** — try local WASM execution (~$0.001)
3. **LLM fallback** — send to language model API (~$0.03+)

## Configuration

```yaml
broker:
  enabled: true
  routing:
    llmAsLastResort: true
    llmProvider: anthropic
    llmModel: claude-3-haiku
```

Set your API key:

```bash
export ANTHROPIC_API_KEY="your-key-here"
```

## Cost Tracking

Every LLM call is tracked in the cost system:

```bash
naos broker stats
```

Output:

```
BROKER STATISTICS (today)
─────────────────────────
Total tasks:     142
Skill matches:   89 (63%)
WASM handlers:   31 (22%)
LLM fallbacks:   22 (15%)

Cost savings:    $3.51 (vs all-LLM)
Avg latency:     45ms (vs 2.1s all-LLM)
```

## Reducing LLM Usage

To minimize expensive LLM calls:

1. **Add more skills** — cover common task patterns
2. **Lower confidence threshold** — match more tasks to skills
3. **Add WASM handlers** — for complex but deterministic tasks
4. **Enable caching** — avoid duplicate LLM calls

```yaml
broker:
  routing:
    confidenceThreshold: 0.6   # lower = more skill matches
  cache:
    enabled: true
    ttl: 3600
```