---
title: "Langfuse June Update"
description: "Langfuse June Update: Lower prices across every Cloud plan, long-awaited features, team growth & more!"
ogImage: /images/blog/2025-06-30-langfuse-june-update/june-update.png
tag: update
date: 2025/06/30
author: "Marc"
---

June was busy at Langfuse: We lowered prices across every Cloud plan thanks to some infrastructure improvements (we’re excited to share these economies of scale with you), added several highly requested features to the new Dashboards and Prompt Management, and made onboarding even faster.

_Missed it? **Langfuse Python SDK v3** is now generally available and ready for production use ([upgrade guide](/docs/sdk/python/sdk-v3#upgrade-from-v2))._

## 💸 Prices down on every Langfuse Cloud plan

  ![Pricing Update Placeholder](/images/blog/2025-06-30-langfuse-june-update/pricing.png)

We've **reduced usage-based pricing across the board** and introduced automatic volume discounts on tracing units. You save more as you grow; no action needed.

→ [See the new pricing details](/docs/get-started#pricing)

## 🕵️‍♂️ Pivot Tables in Custom Dashboards

  ![Pivot Tables Placeholder](/images/blog/2025-06-30-langfuse-june-update/pivot-tables.png)

Big upgrade to custom dashboards in Langfuse. The new pivot table widget lets you analyze multi-dimensional data, making it easier to uncover patterns and insights across different segments and metrics.

→ See [changelog](/changelog/2025-07-01-pivot-tables-custom-dashboards)

By the way, we have also added [histograms](/changelog/2025-06-30-histogram-charts-custom-dashboards) to help you plot the distribution of metrics.

## 🧩 Message placeholders in prompts

  ![Message Placeholders Placeholder](/images/blog/2025-06-30-langfuse-june-update/message-placeholders.png)

This is a much-requested improvement to Prompt Management that allows you to insert arrays of messages at any point within a Langfuse chat prompt. It is fully compatible with Langfuse Prompt Experiments and Playground.

→ [Read the docs](/docs/prompts/get-started#message-placeholders)

## 📂 Organize prompts with folders

  ![Prompt Folders Placeholder](/images/blog/2025-06-30-langfuse-june-update/prompt-folders.png)

Keep your prompt library tidy by adding **folders** directly in the prompt name:

```text
production/email_welcome
```

Anything before the "/" becomes a folder. Organize by use-case, model, or team—no more endless scroll.

→ [Read the docs](/docs/prompts/get-started#prompt-folders)

## 🤖 Agentic Onboarding (Beta)

  ![Agentic Onboarding Placeholder](/images/blog/2025-06-30-langfuse-june-update/agentic-onboarding.png)

Add Langfuse to agents like **Cursor, GitHub Copilot, and Windsurf** via our new MPC endpoint. It's experimental, and we'd love your feedback.

→ [Quick-start guide](/docs/get-started)

## ➕ More June Releases

- **[Histogram charts](/changelog/2025-06-30-histogram-charts-custom-dashboards)** in custom dashboards
- **[Export dataset items](/changelog/2025-06-23-exports-datasets-audit-logs)** via the UI
- **[Download aggregated stats](/changelog/2025-06-17-csv-download-dashboard-charts)** directly from your custom dashboards
- **[Audit-log exports](/changelog/2025-06-23-exports-datasets-audit-logs)** for compliance teams
- **Improved JSON support** for prompts to be consumed via Langchain
- **Edit your LLM Connections** to add new models or update your API key

## 🪄 Customer spotlight: Magic Patterns

  ![Magic Patterns Placeholder](/images/blog/2025-06-30-langfuse-june-update/magic-patterns.png)

See how Langfuse supports Magic Patterns in serving **millions of UI generations**.

→ [Read the story](/users/magic-patterns-ai-design-tools)

<!-- 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/blog/2025-06-30-langfuse-june-update.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>.