---
title: How do I track LLM cost and tokens in Langfuse?
tags: [observability]
---

# How to track LLM Cost and Tokens in Langfuse

You can track the cost and token usage for any large language model (LLM) and endpoint in Langfuse. There are two main ways to do this:

1. Automatic calculation by Langfuse: For [supported models](/docs/model-usage-and-cost#infer), Langfuse can infer the cost. This requires you to use the correct model names. We currently support OpenAI and Anthropic models out of the box. Refer to the _Models_ tab in Langfuse for the exact model names.

2. Explicit cost and token ingestion: You can [ingest](/docs/model-usage-and-cost#infer) the cost and token counts for your LLM calls that you already track with Langfuse. Some model providers return the cost and tokens as part of the response payload. You can pass these back to Langfuse. Token counts are automatically captured across our [native integrations](/integrations), such as OpenAI SDK, LangChain, LlamaIndex, and others.

For more information and examples, please see the [cost and tokens in Langfuse](/docs/model-usage-and-cost) documentation.

  <span><strong>Stay updated:</strong> Star Langfuse on [GitHub](https://github.com/langfuse/langfuse) to get instant notifications about new releases.</span>
  <a href="https://github.com/langfuse/langfuse" style={{ marginLeft: 'auto' }}>
    <img src="https://img.shields.io/github/stars/langfuse/langfuse?style=social" alt="Langfuse GitHub stars" style={{ width: 'auto', height: 'auto' }} />
  </a>

<!-- 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/faq/all/costs-tokens-langfuse.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>.