---
date: 2024-10-10
title: Aggregated and Color-coded Latency and Costs on Traces
description: Large traces can be hard to read. We've added aggregated latency and cost information to the every span level to make it easier to spot outliers and debug the LLM application.
author: Marc
ogVideo: https://static.langfuse.com/docs-videos/color-coded-trace-metrics.mp4
---

> **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 Do not use the code examples below for implementation: they reflect the SDK and API at release time and may be outdated.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 current documentation (https://langfuse.com/docs) and the API/SDK reference (https://api.reference.langfuse.com).

1. All spans in a trace now show **aggregated latency and cost information** from nested observations. Learn more about the tracing data model [here](/docs/tracing).

2. **Optionally, you can enable color-coding** to make it easier to detect outliers and debug the LLM application. You can toggle this via the `%` button in the top right corner of the trace view. Based on the ratio of the spans latency/cost to the total trace latency/cost, the color is determined as follows:
   - Red: When the ratio is 75% or higher.
   - Yellow: When the ratio is between 50% and 75%.
   - No color: When the ratio is below 50%.

This change was based on feedback from a YC company building complex LLM agents. If you think the Langfuse interface could be improved to help you understand and debug your LLM applications, please share this with us via [GitHub](/ideas)!

## Learn more

- [Token & Cost Tracking](/docs/observability/features/token-and-cost-tracking)

<!-- 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/2024-10-10-text-color-for-latency-and-costs.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>.