One endpoint. Every model. Lowest cost.
The Aelox Model Router is a single endpoint at /v1/chat/completions that sits between you and every major AI provider. Send a query, it reads your intent, picks the cheapest model that can handle it, and routes it through. If that model fails, the next one catches it instantly.
Benchmarked performance
We tested every model across 16 tests in 6 dimensions: factual accuracy, reasoning, coding, instruction following, speed, and safety.
| Model | Score | Cost | Latency |
|---|---|---|---|
| DeepSeek Flash | 94% PRO | $0.15/M | ~3s |
| Tencent HY3 | 100% AGI | FREE | ~12s |
| Nemotron Super | 82% GOOD | FREE | ~4s |
Try it right now
curl -X POST http://66.179.136.203:19002/v1/chat/completions -H "Content-Type: application/json" -d '{"model":"deepseek-flash","messages":[{"role":"user","content":"Hello"}]}'Open source. MIT license. GitHub.