# Helicone: LLM Observability

Helicone adds observability to any LLM provider. Track costs, latency, and usage patterns.

## Why Helicone?

- **Cost Tracking** — Per-request cost breakdown
- **Latency Monitoring** — P50, P99 metrics
- **Request Logging** — Full prompt/response history
- **Caching** — Reduce costs with response caching

## Setup

Proxy your requests through Helicone:

```json
{
  "provider": "openai",
  "baseUrl": "https://oai.hconeai.com/v1",
  "headers": {
    "Helicone-Auth": "Bearer your-helicone-key"
  }
}
```

* * *

_Get started: [Download Ishi](/content/download/index.html) \| [Helicone Docs](https://docs.ishi.so/providers/#helicone)_

## Try Ishi Today

Download Ishi and start automating your workflow with the Glass Box philosophy.

[Download Free](/content/download/index.html)