---
date: 2024-05-14
title: Playground and evaluations with GPT-4o
description: Experiment with OpenAI GPT-4o in the playground and use it to power evaluations 
author: Hassieb
canonical: /docs/administration/llm-connection
---

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 Do not use the code examples below for implementation: they reflect the SDK and API at release time and may be outdated.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

OpenAI has delighted many developers with the [release of GPT-4o](https://openai.com/index/hello-gpt-4o/). The new model comes at improved performance, lower costs, greater speed, and more generous rate limits.

We see many users in the Langfuse community excited about the new model so we are happy to announce that we have added day-1 support for GPT-4o in the [Langfuse LLM playground](/docs/playground) and [evaluations](/docs/scores/model-based-evals). We already support [cost and usage tracking for the GPT-4o](/changelog/2024-05-14-openai-gpt-4o).

Start experimenting with GPT-4o now in the LLM playground and use the improved and cost effective model to power your evaluations 🥳

#### 📚 Learn more

- [🤖 OpenAI GPT-4o](https://openai.com/index/hello-gpt-4o/)
- [📊 Langfuse model usage and cost tracking](/docs/model-usage-and-cost)
- [🛝 Langfuse playground](/docs/playground)
- [💡 Langfuse evaluations](/docs/scores/model-based-evals)

<!-- 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/2024-05-14-openai-gpt-4o-playground-evals.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>.