---
date: 2025-04-16
title: OpenAI o3 and o4-mini integration for playground, evaluations and cost tracking
seoTitle: "OpenAI o3 and o4-mini in Playground and Evals"
description: Langfuse launches same day full compatibility with OpenAI's latest models o3 and o4-mini
author: Marlies
---

> **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 Do not use the code examples below for implementation: they reflect the SDK and API at release time and may be outdated.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).

Some highlights about o3 and o4-mini from the [OpenAI release notes](https://openai.com/index/introducing-o3-and-o4-mini):

- **Improved Instruction Following**: Both models demonstrate enhanced instruction following and provide more useful, verifiable responses than their predecessors
- **More Natural Interaction**: Responses feel more conversational and personalized by leveraging memory and past conversation context

As OpenAIs best reasoning model yet, o3:

- **Advanced Reasoning**: o3 is OpenAI's most powerful reasoning model, setting new state-of-the-art benchmarks across coding, math, science, and visual perception
- **Reduced Error Rate**: Makes 20 percent fewer major errors than OpenAI o1 on difficult real-world tasks, especially in programming, business consulting, and creative ideation

o4-mini for cost-effective reasoning:

- **Cost-Effective Performance**: o4-mini achieves remarkable performance for its size and cost, particularly excelling in math, coding, and visual tasks
- **Higher Usage Capacity**: Supports significantly higher usage limits than o3, making it ideal for high-volume applications that benefit from reasoning

## Learn more

- [Langfuse LLM playground](/docs/playground)
- [Langfuse model usage and cost tracking](/docs/model-usage-and-cost)

<!-- 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/2025-04-16-o3-o4-mini-support.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>.