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

# The Workload Cost Index

> Daily realized dollars per request for the closed AI labs, plus a mix-purged like-for-like index and tokens-per-request intensity.

The **Workload Cost Index** is the [OTPI](/docs/token-price-index) companion for the price of a call. OTPI prices the token; this prices the request:

```
¢/request = $/MTok × tokens/request
```

Where OTPI blends posted per-token prices, the Workload Cost Index tracks the **settled dollars a lab's paid workload actually generated per request that day**, plus the two things that drive it: same-model unit cost (mix-purged) and tokens per request. It is published for the three closed labs — **Anthropic**, **OpenAI**, and **Google** — and refreshed on the same daily settle as OTPI.

## The three series

Every workload node (a provider or a model class within it) publishes three daily series:

| Series                  | What it measures                                                                                                                                               | Units                                                 |
| ----------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------- |
| **Cost per Request**    | The real blended cost of one call: settled spend over paid calls for the node's model mix that day. Includes mix, so it moves when users shift between models. | cents per request (cents per image for image classes) |
| **Like-for-Like Index** | Mix-purged unit cost. Isolates true price and efficiency change from savings that come from routing to smaller or cheaper models.                              | index points (base = 100 on the seed day)             |
| **Workload Intensity**  | How heavy a typical call is — tokens served per request across the node's mix.                                                                                 | tokens per request                                    |

Read the three together: if Cost per Request falls while the Like-for-Like Index stays flat, the lab is getting cheaper by shifting workload to smaller models rather than because the same model got cheaper. If the Like-for-Like Index also falls, the same model actually got cheaper. Rising Workload Intensity — longer answers, more tool calls, deeper reasoning — can push Cost per Request up even while per-token prices fall.

<Note>
  "Settled" here means the index's official daily computation from venue-reported realized prices and volumes — the same epistemic status as OTPI. It is not audited payments.
</Note>

## Providers and model classes

Model classes are exact partitions of a provider's daily per-model rows, so class-level rows sum back to the provider aggregate. Class-level like-for-like removes only within-class mix.

| Provider    | Aggregate | Model classes                                       |
| ----------- | --------- | --------------------------------------------------- |
| `anthropic` | ✓         | `opus`, `sonnet`, `haiku`, `fable`                  |
| `openai`    | ✓         | `flagship`, `mini`, `nano`, `pro`, `codex`, `image` |
| `google`    | ✓         | `flash`, `pro`, `lite`, `image`                     |

Choose the **aggregate** for a whole-lab view, or a **class** to isolate a family (for example `sonnet` to strip out Opus/Haiku mix effects).

<Note>
  Thin classes (OpenAI `pro`, `codex`, `nano`, and the image families across labs) are accurate partitions but low-volume. Daily wiggles in those series are small-sample noise and should be read with wider windows.
</Note>

## How it's computed

The index rides the existing OTPI settle. For each provider on each settlement day:

1. **Per-model daily rows** are persisted with settled dollars, tokens, and request counts.
2. **Provider and class nodes** are built by summing the partition of models in each node.
3. **Cost per Request** is `settled_dollars ÷ requests` on that day.
4. **Workload Intensity** is `tokens ÷ requests` on that day.
5. **Like-for-Like Index** uses an LMDI decomposition between trailing 7-day windows to separate the same-model unit-cost change from the mix change, then chains the same-model component day over day. Inputs are smoothed, outputs are not, so daily chaining does not drift and model entry/exit lands in the mix term by construction.

Errors in the workload settle are isolated from the OTPI settle — OTPI rows are written first, then workload errors are collected and thrown as an `AggregateError` so the job exits with failure while preserving the token price index.

## Coverage window

* History starts **2026-06-11**. The 2026-06-04 to 2026-06-10 settlement block was backfilled with elevated Opus effective prices and is excluded from the seeded base.
* **2026-06-30 is missing** from settlement inputs for all labs — a one-day gap pending a settlement re-emit upstream.
* Newly settled days advance daily on the same \~36-hour lag as OTPI.

## Accessing the data

Query the index programmatically via [`GET /api/workload`](/docs/api-reference/workload-cost/get-the-workload-cost-index-by-provider). Unlike OTPI, this endpoint has **no free tier** — every request must include an API key. See [Authentication](/docs/authentication) for how to send the `Authorization: Bearer` header, and [Manage API keys](/docs/manage-api-keys) to create one.

## Viewing in the dashboard

The **Workload Cost** tab on [data.ornn.com/analytics](https://data.ornn.com/analytics) plots all three series, with dropdowns for provider and model class. Axes and hover tooltips are unit-aware — cents for cost per request, index points for like-for-like, thousands of tokens for intensity.

## Related

* [The Token Price Index](/docs/token-price-index) — the per-token OTPI this index composes with.
* [LLM coding activity](/docs/llm-coding-index) — daily public-GitHub PR and merge metrics for coding assistants.