> ## Documentation Index
> Fetch the complete documentation index at: https://docs.uselumina.io/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Cost Management

> Tips for managing LLM costs with Lumina

Strategies for managing and optimizing LLM costs.

***

## Monitor Costs

**Set up alerts:**

```json theme={null}
{
  "service": "chat-api",
  "costThreshold": 2.0,
  "window": "1h"
}
```

**Track by dimension:**

* Per service
* Per model
* Per user
* Over time

***

## Identify Expensive Queries

Filter high-cost traces:

```bash theme={null}
curl "http://api:8081/api/traces?costUsd[$gt]=0.5"
```

Review and optimize expensive queries.

***

## Model Optimization

**Use cheaper models for simple tasks:**

```typescript theme={null}
const model = complexity === 'simple' ? 'gpt-3.5-turbo' : 'gpt-4';

await lumina.traceLLM(
  () => openai.chat.completions.create({ model, messages }),
  { name: 'chat', system: 'openai' }
);
```

***

## Prompt Optimization

**Reduce token usage:**

* Use concise prompts
* Remove unnecessary context
* Implement semantic caching

**Test with replay:**

```typescript theme={null}
// Test prompt changes before deploying
await lumina.replayTraces({
  replaySetId: 'cost-test',
});
```

***

## Sampling

For high volumes, sample routine operations:

```typescript theme={null}
const lumina = initLumina({
  endpoint: 'http://lumina:9411/v1/traces',
  service_name: 'service',
  samplingRate: 0.1,
  alwaysSampleConditions: {
    costUsd: { $gt: 0.5 }, // Always sample expensive calls
  },
});
```