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

# Cost, Batch & Cache

> Spend less per result: budgets, prompt caching, batching, and Headroom compression.

**ELI5:** four dials control spend. **Budgets** cap a run. **Caching** makes
repeated context nearly free. **Batching** trades latency for \~50% off.
**Headroom** compresses context before the provider ever sees it.

## Budgets (always set these)

```yaml theme={null}
budget:
  tokens: 100000
  wall_clock_minutes: 45
```

Cadence enforces both; a run that hits its budget stops cleanly and the
session ledger records actual usage and cost per event.

## Prompt caching

```yaml theme={null}
cache_policy:
  enabled: true
  strategy: auto
  key_scope: workflow   # workflow | ticket | global
  ttl: 1h
```

`auto` lets the harness place provider cache breakpoints (Anthropic ephemeral
cache blocks, Gemini cached content, OpenAI prompt caching) — you choose
scope and TTL, not provider mechanics. Cache scoping is workspace-isolated on
the vendor side.

## Batching

Batch APIs are implemented for Anthropic (`anthropic.batches.create`) and the
OpenAI batch surface — right for evals, backfills, and bulk classification
where minutes of latency are fine for \~half price. Drive them through a
workflow stage that submits and a later stage (or trigger) that collects.

## Headroom (context compression)

```yaml theme={null}
harness_config:
  sdk_settings:
    anthropic:
      headroom:
        enabled: true
        token_budget: 120000
```

Headroom runs before the provider call, compresses context to the budget,
and emits evidence either way (`headroom.compression` / `headroom.skipped`)
— you can audit exactly what it did.

## When to use what

| Symptom                                    | Dial                                    |
| ------------------------------------------ | --------------------------------------- |
| Same big system context every turn         | `cache_policy`                          |
| Long-running agent blowing context windows | Headroom                                |
| Thousands of independent items             | Batch                                   |
| Runaway spend risk                         | Tighter `budget` + `retry.max_attempts` |

## See also

* [Workflow Schema](/harness/workflow-schema#budget) — field shapes
* Provider pages: [Anthropic batch/cache rows](/harness/providers/anthropic#batch-cost-cache)