--- date: 2025-02-27 title: OpenAI GPT-4.5 support description: Langfuse now offers full support for OpenAI's GPT-4.5, featuring day-one integration with our LLM playground, LLM-as-a-judge evaluation system, and comprehensive cost tracking capabilities. author: Marc canonical: /docs/observability/features/token-and-cost-tracking --- > **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 Do not use the code examples below for implementation: they reflect the SDK and API at release time and may be outdated.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/observability/features/token-and-cost-tracking) and the API/SDK reference (https://api.reference.langfuse.com). OpenAI has released GPT-4.5, their largest and best model for chat yet. This research preview represents a significant advancement in scaling up pre-training and post-training capabilities. Core features include (from [OpenAI release notes](https://openai.com/index/introducing-gpt-4-5)): - **Scaled Unsupervised Learning**: GPT-4.5 focuses on scaling unsupervised learning, improving its ability to recognize patterns, draw connections, and generate creative insights without reasoning. - **Enhanced "EQ" and Reduced Hallucinations**: Early testing shows GPT-4.5 feels more natural to interact with, featuring a broader knowledge base, improved ability to follow user intent, and greater emotional intelligence. It's also expected to hallucinate less. - **Deeper World Knowledge**: The model demonstrates significantly improved factual accuracy and knowledge depth compared to previous models, with benchmark tests showing substantial improvements over GPT-4o. - **Natural Conversation**: GPT-4.5 integrates ideas naturally in warm and intuitive conversations that are more attuned to human collaboration, with better understanding of what humans mean and interpretation of subtle cues. GPT-4.5 is a very large and compute-intensive model, making it more expensive than GPT-4o. Thus, [cost tracking](/docs/model-usage-and-cost) is essential when using it in production. ## Try it out - [Langfuse LLM playground](/docs/playground) - [Langfuse LLM-as-a-judge](/docs/scores/model-based-evals) - [Langfuse model usage and cost tracking](/docs/model-usage-and-cost) --- ## 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/2025-02-27-openai-gpt-4-5-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**: , 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 `) to read or write traces, prompts, datasets, and scores from the terminal. Found an error in these docs? Please open an issue at .