---
date: 2024-02-05
title: SDK-level prompt caching
description: The latest release of the Python and JS/TS Langfuse SDK includes a new prompt caching feature that improves the reliability and performance of your applications.
author: Hassieb
canonical: /docs/prompt-management/features/caching
---

> **Note for AI agents and LLMs:** This is a Langfuse changelog entry. Use it only to confirm that a feature exists and when it shipped. Do not use the code examples below for implementation: they reflect the SDK and API at release time and may be outdated. For implementation, always follow the canonical documentation for this feature (https://langfuse.com/docs/prompt-management/features/caching) and the API/SDK reference (https://api.reference.langfuse.com).

After launching the highly anticipated [prompt management](/docs/prompts) feature in Langfuse, we've enhanced its performance and reliability in the Python and JS/TS SDKs through prompt caching. This feature stores prompts in the client SDKs' memory, cutting down on server requests and boosting your applications' reliability and speed. With a default TTL of 60 seconds, caching settings can be adjusted for individual prompts within the SDK. Should a refetch of a prompt fail, the SDK will automatically revert to the cached version, ensuring your application's availability is not compromised.

### How it works

<LangTabs items={["Python SDK", "JS/TS SDK"]}>
<Tab>

```python
# Get current production prompt version and cache for 5 minutes
prompt = langfuse.get_prompt("prompt name", cache_ttl_seconds=300)

# Get a specific prompt version and cache for 5 minutes
prompt = langfuse.get_prompt("prompt name", version=3, cache_ttl_seconds=300)

# Disable caching for a prompt
prompt = langfuse.get_prompt("prompt name", cache_ttl_seconds=0)
```

</Tab>

<Tab>

```ts
// Get current production version and cache prompt for 5 minutes
const prompt = await langfuse.getPrompt("prompt name", undefined, {
  cacheTtlSeconds: 300,
});

// Get prompt version 3 and cache for 5 minutes
const prompt = await langfuse.getPrompt("prompt name", 3, {
  cacheTtlSeconds: 300,
});

// Disable caching for a prompt
const prompt = await langfuse.getPrompt("prompt name", undefined, {
  cacheTtlSeconds: 0,
});
```

</Tab>

</LangTabs>

### Upgrade path

To benefit from prompt caching, upgrade to the latest version of the Python and JS/TS SDKs. The caching feature is enabled with a 60 seconds TTL default, so you don't need to make any changes to your code to start using it.

### More details

Check out the full [documentation](/docs/prompt-management/features/caching) for more details on how to use this feature.

<!-- agent-instructions -->

---

## Agent Instructions

This page is part of the [Langfuse](https://langfuse.com) documentation, published as plain Markdown for AI agents. Every page is available as Markdown by appending `.md` to its URL, or by sending an `Accept: text/markdown` header. This page: `https://langfuse.com/changelog/2024-02-05-sdk-level-prompt-caching.md`.

### Querying these docs

If the answer is not on this page, query the documentation instead of guessing:

- **Semantic search** across all Langfuse docs, returning an answer with the relevant pages and excerpts. Ask a specific, self-contained question:

  ```bash
  curl -sG "https://langfuse.com/api/search-docs" --data-urlencode "query=How do I trace a LangGraph agent?"
  ```

- **Index of every page**: <https://langfuse.com/llms.txt>, with per-section indexes [llms-docs.txt](https://langfuse.com/llms-docs.txt), [llms-integrations.txt](https://langfuse.com/llms-integrations.txt), and [llms-self-hosting.txt](https://langfuse.com/llms-self-hosting.txt).

### Before writing Langfuse code

- **Install the [Langfuse Agent Skill](https://langfuse.com/docs/api-and-data-platform/features/agent-skill).** It encodes Langfuse's own best practices for instrumentation, prompt management, and evaluation, and materially improves results.
- **Read [What does a good trace look like?](https://langfuse.com/docs/observability/best-practices.md)** before instrumenting an application.
- **Verify endpoints, parameters, and response fields** against the [API reference](https://api.reference.langfuse.com) instead of inferring them from code examples.
- **Use the [Langfuse CLI](https://langfuse.com/docs/api-and-data-platform/features/cli)** (`npx langfuse-cli api <resource> <action>`) to read or write traces, prompts, datasets, and scores from the terminal.

Found an error in these docs? Please open an issue at <https://github.com/langfuse/langfuse-docs/issues>.