# Anthropic (/providers/anthropic)



Anthropic carries the single highest-leverage economics of the five first-class providers: a **90%
cache-read discount**, the deepest of any managed provider. For agent workloads where the system
prompt, tool definitions, and knowledge base are stable across hundreds of requests per session,
Anthropic frequently delivers the lowest effective input-token cost of any frontier provider - and
once cache reads dominate, sometimes below open-source inference.

It is available on both the [managed-provider](/execution/managed-providers) and
[BYOK](/execution/byok) profiles. Requests that resolve here report
`Agent-Resolved-Provider: anthropic`.

## Caching economics [#caching-economics]

Anthropic caching is **explicit**: you place `cache_control` breakpoints at the end of each stable
block (system prompt, tool definitions, long documents). A cache write costs more than a normal token,
so mark only blocks you will actually reuse, and never mark volatile content.

| Fact                    | Value                                  |
| ----------------------- | -------------------------------------- |
| Cache type              | Explicit (`cache_control` breakpoints) |
| Minimum cacheable block | 1,024 tokens                           |
| Cache-read discount     | 90% on cache reads                     |
| Default TTL             | 300 seconds (5 min)                    |
| Extended TTL            | 3,600 seconds (1h) on Claude 3.5+      |
| Cached-token reporting  | Yes                                    |
| Manual cache clear      | Not supported                          |

<Tip>
  Measure `cache_creation_input_tokens` against `cache_read_input_tokens` per session to verify your
  capture rate. The 90% discount only compounds if reads dominate writes - which is exactly what a
  stable prefix across many turns produces.
</Tip>

## Batch [#batch]

The **Message Batches API** delivers a 50% cost reduction at up to 24h turnaround. Use it for the same
non-interactive classes as everywhere else: background evaluations, diagnostic reprocessing,
pre-computable tool calls, replay experiments. Anthropic exposes a single `standard` service tier;
there is no flex/scale split to match to QoS.

## Retention [#retention]

Anthropic's `data_retention_class` is `zero_retention_available`. That makes it a strong fit for
[BYOK](/execution/byok) when an account-level zero-retention policy has to apply to the inference
calls, and it factors into the purge guarantee the platform can offer for Anthropic-cached state. See
[retention and purge](/concepts/retention-and-purge).

## When the broker routes here [#when-the-broker-routes-here]

<CardGroup cols="2">
  <Card title="Repeated long-context prompts" icon="repeat">
    Route here when stable prefixes exceed \~1,024 tokens and recurrence is high - the 90% cache-read
    discount compounds faster than any other provider mechanism.
  </Card>

  <Card title="Stable agent context" icon="layer-group">
    A fixed system prompt, tool registry, and knowledge base reused across hundreds of requests is the
    canonical Anthropic win.
  </Card>

  <Card title="Zero-retention requirements" icon="shield-halved">
    Workloads that need zero-retention available at the account level, typically under BYOK.
  </Card>

  <Card title="Reasoning-heavy tasks" icon="brain">
    Extended thinking for reasoning work; gate the added latency behind the right alias class rather
    than enabling it everywhere.
  </Card>
</CardGroup>

## At a glance [#at-a-glance]

| Capability           | Value                      |
| -------------------- | -------------------------- |
| Context window       | 200,000 tokens             |
| Multimodal input     | Yes                        |
| Live search          | No                         |
| Dedicated deployment | No                         |
| Service tiers        | standard                   |
| Data retention       | zero\_retention\_available |
| Regions              | us                         |

Manifest revision `cap_2026_06_09`. The [capability manifest](/concepts/capability-manifests) records
that Anthropic holds the deepest cache discount in the set; the broker uses these facts to decide where
a repeated long-context prompt is cheapest.