# Pricing — Pay-As-You-Go Billing

Source: https://ofox.ai/docs/develop/observability/pricing

OfoxAI uses a **pure pay-as-you-go** model — you only pay for what you use. No subscriptions, no plans, no monthly fees, no minimum spend.

No subscriptions, no plans, no hidden fees. Top up and start using immediately. Balance never expires.

## Billing Method

### Text Models (Per Token)

| Billing Item | Description |
|-------------|-------------|
| **Input Tokens** | Tokens consumed by input (prompt) |
| **Output Tokens** | Tokens consumed by output (completion) |
| **Cached Tokens** | Cache-hit input tokens (discounted rate) |

### Other Models

| Type | Billing Method |
|------|---------------|
| Image generation | Per image |
| Embeddings | Per input token |

## How It Works

1. **Sign up** — Register at the [OfoxAI Console](https://app.ofox.ai)
2. **Top up** — Add funds as needed; balance never expires
3. **Use** — Charged by actual usage, settled in real time

## Viewing Costs

### Console

1. Log in to the [OfoxAI Console](https://app.ofox.ai)
2. Go to the **Billing** page
3. View real-time cost breakdown by model and by date

### API Response

Every API response includes a `usage` field for tracking consumption:

```json
{
  "usage": {
    "prompt_tokens": 100,
    "completion_tokens": 50,
    "total_tokens": 150
  }
}
```

## Cost Optimization Tips

1. **Choose the right model** — Use lightweight models for simple tasks; you don't need flagship models for every scenario
2. **Enable Prompt Caching** — Repeated system prompts can save 50-90% on input costs
3. **Control max_tokens** — Set reasonable output length limits to avoid unnecessary token consumption
4. **Batch requests** — Combine multiple short requests into one to reduce repeated prompt overhead

For real-time pricing of each model, check the [Model Catalog](https://ofox.ai/models).