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

# DecisionsResponseUsage

## Example Usage

```typescript theme={null}
import { DecisionsResponseUsage } from "@openrouter/sdk/models";

let value: DecisionsResponseUsage = {
  inputTokens: 569479,
  outputTokens: 170740,
};
```

## Fields

| Field | Type | Required | Description | Example |
| - | - | - | - | - |
| `cost` | *number* | ➖ | What OpenRouter charges for the request, in credits. On a BYOK request this is the OpenRouter fee only. | |
| `costDetails` | [models.CostDetails](../models/costdetails.mdx) | ➖ | Breakdown of upstream inference costs | \{ "upstream\_inference\_completions\_cost": 0.0004, "upstream\_inference\_cost": null, "upstream\_inference\_prompt\_cost": 0.0008 } |
| `inputTokens` | *number* | ✔️ | N/A | |
| `inputTokensDetails` | [models.DecisionsUsageInputTokensDetails](../models/decisionsusageinputtokensdetails.mdx) | ➖ | Of `input_tokens`, those the provider served from its prompt cache. | |
| `isByok` | *boolean* | ➖ | Whether a request was made using a Bring Your Own Key configuration | |
| `outputTokens` | *number* | ✔️ | N/A | |