# Claude prompt caching: cache_control, 1-hour caching and confirming hits

Source: https://ofox.ai/docs/develop/models/claude/caching

This page explains how to enable prompt caching for Claude and confirm cache hits. For model IDs and endpoints, see the [Claude family overview](https://ofox.ai/docs/develop/models/claude).

**Key point**:Claude caching requires an explicit cache_control marker; neither endpoint caches automatically.

Put long, fixed content (system prompts, documents, tool definitions) at the start of the request, and set `cache_control` on the last fixed content block. Subsequent requests whose prefix is exactly identical will hit the cache.

**Anthropic-native API**

```python filename="claude_cache.py"
import os
import anthropic

client = anthropic.Anthropic(base_url="https://api.ofox.ai/anthropic", api_key=os.environ["OFOX_API_KEY"])
LONG_DOC = open("manual.txt", encoding="utf-8").read()  # a long, fixed document

for question in ["What does chapter 3 cover?", "Summarize the key points of the whole document."]:
    message = client.messages.create(
        model="anthropic/claude-sonnet-4.6",
        max_tokens=1024,
        system=[
            {"type": "text", "text": "Answer questions based on the document below."},
            {"type": "text", "text": LONG_DOC, "cache_control": {"type": "ephemeral"}},
        ],
        messages=[{"role": "user", "content": question}],
    )
    u = message.usage
    print("Write:", u.cache_creation_input_tokens, "Read:", u.cache_read_input_tokens)
```

**OpenAI-compatible API**

```python filename="claude_cache_openai.py"
import os
from openai import OpenAI

client = OpenAI(base_url="https://api.ofox.ai/v1", api_key=os.environ["OFOX_API_KEY"])
LONG_DOC = open("manual.txt", encoding="utf-8").read()

for question in ["What does chapter 3 cover?", "Summarize the key points of the whole document."]:
    resp = client.chat.completions.create(
        model="anthropic/claude-sonnet-4.6",
        max_tokens=1024,
        messages=[
            {"role": "system", "content": [
                {"type": "text", "text": LONG_DOC, "cache_control": {"type": "ephemeral"}},
            ]},
            {"role": "user", "content": question},
        ],
    )
    details = resp.usage.prompt_tokens_details
    print("Read:", details.cached_tokens if details else 0)
```

| Item | Details |
|---|---|
| TTL | 5 minutes by default, reset on each hit; `"cache_control": {"type": "ephemeral", "ttl": "1h"}` sets 1 hour |
| Confirming hits (native API) | On the first request `usage.cache_creation_input_tokens` is greater than 0; on a hit `usage.cache_read_input_tokens` is greater than 0 |
| Confirming hits (OpenAI-compatible API) | On a hit `usage.prompt_tokens_details.cached_tokens` is greater than 0 |
| Minimum length | Content that is too short is not cached, and both fields are 0. For each model's minimum cacheable length, see the [Anthropic docs](https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching) |
| Billing | Writes and reads are billed at the cache write and cache read rates respectively — see the [model page](https://ofox.ai/models/anthropic/claude-sonnet-4.6) |

For general information on caching, see [Prompt caching](https://ofox.ai/docs/develop/advanced/prompt-caching).

For other errors, see [Common errors](https://ofox.ai/docs/develop/models/claude#errors).