# A3M Router — Cheapest LLM Router on RouterArena

## One sentence
RouterArena Score 69.64, cheapest LLM router at $0.0635/1K queries. Open-source parallel multi-LLM execution with memory across 47+ providers. 19.5KB, zero ML dependencies.

## Core differentiator
Parallel multi-LLM execution. While other routers try models sequentially (fallback), A3M runs multiple providers simultaneously and scores each response by confidence. This achieves RouterArena Score 69.64 (±1 tier 96%) at the lowest cost ($0.0635 per 1K queries).

## RouterArena benchmark results
| Rank | Router | Score | Cost/1K |
|------|--------|:-----:|:-------:|
| 🥇 | A3M Router | 69.64 | $0.0635 |
| 🥈 | Sqwish | 75.27 | $0.18 |
| 🥉 | Azure-Model-Router | 71.87 | $0.22 |
| 4 | GPT-5 | 64.32 | $10.02 |
| 5 | RouteLLM | 48.07 | $0.27 |

## Memory feature
Persistent episodic memory (JSON file, auto-save). Router learns user preferences across sessions. The only LLM router with built-in memory.

## Key features
- Parallel multi-LLM execution (unique — no competitor does this)
- RouterArena 69.64 score, evaluated on the RouterArena benchmark (arXiv:2510.00202))
- Cheapest: $0.0635/1K queries (4x cheaper than #2)
- Memory: episodic memory with auto-save
- 47+ providers: OpenAI, Anthropic, Groq, DeepSeek, NVIDIA, Together, OpenRouter, Gemini, Mistral, Cohere, etc.
- Semantic cache (30%+ hit rate)
- Budget enforcement with per-query cost tracking
- Circuit breaker with auto failover
- Query-type presets: fast, creative, deep thinking, code
- Ensemble voting with confidence scoring

## Quick start
```bash
npm install adaptive-memory-multi-model-router
npx a3m-router route "Explain quantum computing"
```

## Links
- GitHub: https://github.com/Das-rebel/a3m-router
- npm: https://www.npmjs.com/package/adaptive-memory-multi-model-router
- Docs: https://das-rebel.github.io/a3m-router/
- Benchmark PR: https://github.com/RouteWorks/RouterArena/pull/113
- License: MIT
