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

# Usage

> GET /v1/usage for per-model totals, GET /v1/generation for one call, and the x-predev headers.

## Per-call headers

Every inference response carries:

| Header                       | Meaning                                                      |
| ---------------------------- | ------------------------------------------------------------ |
| `x-predev-request-id`        | `pdr_…`; quote it when contacting support                    |
| `x-predev-credits-charged`   | Credits charged for this call                                |
| `x-predev-credits-remaining` | Workspace balance after the call; omitted on unlimited plans |

Send `x-predev-project-id: <projectId>` on a request to attribute it to one of the workspace's projects. Ids of projects the workspace does not own are ignored.

## GET /v1/usage

Returns totals for the last `days` days (1–90, default 30), broken down by model and path.

```bash theme={null}
curl --fail-with-body "https://api.pre.dev/v1/usage?days=30" \
  -H "Authorization: Bearer $PREDEV_API_KEY"
```

```json theme={null}
{
  "workspace": "ws_7f3a9c",
  "project": null,
  "credits_remaining": 412.5,
  "tier": "pro",
  "since": "2026-08-16T00:00:00.000Z",
  "totals": { "requests": 1840, "credits": 87.5, "usd": 6.13 },
  "by_model": [
    {
      "model": "deepseek/deepseek-v4.1-flash",
      "path": "/v1/chat/completions",
      "requests": 1702,
      "credits": 41.2,
      "usd": 2.88,
      "prompt_tokens": 9120000,
      "completion_tokens": 1410000,
      "errors": 3
    },
    {
      "model": "anthropic/claude-sonnet-5",
      "path": "/v1/messages",
      "requests": 138,
      "credits": 46.3,
      "usd": 3.25,
      "prompt_tokens": 610000,
      "completion_tokens": 92000,
      "errors": 0
    }
  ]
}
```

| Field                                             | Meaning                                         |
| ------------------------------------------------- | ----------------------------------------------- |
| `workspace`                                       | The workspace the key belongs to                |
| `project`                                         | Project the totals are attributed to, or `null` |
| `credits_remaining`                               | Current balance; `null` on unlimited plans      |
| `tier`                                            | Plan tier                                       |
| `since`                                           | Start of the window                             |
| `totals.requests`, `totals.credits`, `totals.usd` | Window totals                                   |
| `by_model[].model`, `path`                        | One row per model and endpoint                  |
| `by_model[].requests`, `credits`, `usd`           | Volume and spend for that row                   |
| `by_model[].prompt_tokens`, `completion_tokens`   | Token totals                                    |
| `by_model[].errors`                               | Requests that returned an error                 |

The usage read is not charged.

## GET /v1/generation

Returns the generation metadata for one call, by the `id` from the response body (`gen-…`). Only generations this workspace made are visible.

```bash theme={null}
curl --fail-with-body "https://api.pre.dev/v1/generation?id=gen-1757900000-abc123" \
  -H "Authorization: Bearer $PREDEV_API_KEY"
```

The body reports the model and provider that served the call, latency, native token counts, and the metered cost behind a specific charge.