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

# Query scorer span token costs with SQL

export const plans_0 = "Any"

export const deployments_0 = "Any"

export const data_plane_version_0 = undefined

export const use_case_0 = "Use case - Calculating total LLM spend including scorer (judge) spans in experiments and live evaluation logs"

<Note>
  **Applies to:**

  * Plan - {plans_0}
  * Deployment - {deployments_0}
  * {data_plane_version_0}
  * {use_case_0}
</Note>

## Summary

**Goal:** Query scorer LLM spend for experiments or project logs, which are excluded from the built-in `estimated_cost()` metric.

**Features:** SQL span queries, `span_attributes.purpose`, `span_attributes.type`, `project_logs()`

## Configuration steps

### Step 1: Understand the default cost exclusion

The **Estimated cost** column on the Experiments page only covers task LLM spans. Scorer spans are filtered out by design. To get scorer costs, you must query token counts directly and calculate costs using your model pricing.

### Step 2: Query scorer token usage

Use the SQL sandbox or API to sum tokens by model for scorer spans. For experiments, an example query is:

```sql theme={"theme":{"light":"github-light","dark":"github-dark-dimmed"}}
SELECT
  SUM(metrics.prompt_tokens) AS scorer_prompt_tokens,
  SUM(metrics.completion_tokens) AS scorer_completion_tokens,
  metadata.model
FROM experiment('<EXPERIMENT_ID>', shape => 'spans')
WHERE span_attributes.purpose = 'scorer'
  AND span_attributes.type = 'llm'
GROUP BY metadata.model
```

For project logs, replace `experiment()` with `project_logs()`:

```sql theme={"theme":{"light":"github-light","dark":"github-dark-dimmed"}}
SELECT
  SUM(metrics.prompt_tokens) AS scorer_prompt_tokens,
  SUM(metrics.completion_tokens) AS scorer_completion_tokens,
  metadata.model
FROM project_logs('<PROJECT_ID>', shape => 'spans')
WHERE span_attributes.purpose = 'scorer'
  AND span_attributes.type = 'llm'
GROUP BY metadata.model
```

Calculate costs by multiplying token counts by your per-model pricing (e.g., `prompt_tokens * (0.04 / 1000000) + completion_tokens * (0.05 / 1000000)`).

### Step 3: Surface costs in the Monitor dashboard (optional)

In the **Monitor** page, create a custom chart with a span filter on `span_attributes.purpose = 'scorer'` and `span_attributes.type = 'llm'`. Use `sum(metrics.prompt_tokens)` as the measure, or create a cost expression like:

```sql theme={"theme":{"light":"github-light","dark":"github-dark-dimmed"}}
sum(metrics.prompt_tokens) * (0.04 / 1000000)
```