Farewell, GPT-4.5

"openai.com February 27, 2025 Release Product Introducing GPT-4.5 12–15 minutes A research preview of our strongest GPT model. Available to Pro users and developers worldwide. Listen to article 7:06 We’re releasing a research preview of GPT‑4.5—our largest and best model for chat yet. GPT‑4.5 is a step forward in scaling up pre-training and post-training. By scaling unsupervised learning, GPT‑4.5 improves its ability to recognize patterns, draw connections, and generate creative insights without reasoning. Early testing shows that interacting with GPT‑4.5 feels more natural. Its broader knowledge base, improved ability to follow user intent, and greater “EQ” make it useful for tasks like improving writing, programming, and solving practical problems. We also expect it to hallucinate less. We’re sharing GPT‑4.5 as a research preview to better understand its strengths and limitations. We’re still exploring what it’s capable of and are eager to see how people use it in ways we might not have expected. Scaling unsupervised learning We advance AI capabilities by scaling two complementary paradigms: unsupervised learning and reasoning. These represent two axes of intelligence. Unsupervised learning increases world model accuracy and intuition. Models like GPT‑3.5, GPT‑4, and GPT‑4.5 advance this paradigm. Scaling reasoning⁠, on the other hand, teaches models to think and produce a chain of thought before they respond, allowing them to tackle complex STEM or logic problems. Models like OpenAI o1 and OpenAI o3‑mini advance this paradigm. GPT‑4.5 is an example of scaling unsupervised learning by scaling up compute and data, along with architecture and optimization innovations. GPT‑4.5 was trained on Microsoft Azure AI supercomputers. The result is a model that has broader knowledge and a deeper understanding of the world, leading to reduced hallucinations and more reliability across a wide range of topics. Scaling the GPT paradigm Deeper world knowledge SimpleQA Accuracy (higher is better) 62.5%38.2%47%15%Accuracy SimpleQA Hallucination Rate (lower is better) 37.1%61.8%44%80.3%Hallucination rate SimpleQA measures LLM (large language model) factuality on straightforward but challenging knowledge questions. Training for human collaboration As we scale our models and they solve more complex problems, it becomes increasingly important to teach them a greater understanding of human needs and intent. For GPT‑4.5, we developed new, scalable techniques that enable training larger and more powerful models with data derived from smaller models. These techniques improve GPT‑4.5’s steerability, understanding of nuance, and natural conversation. Comparative evaluations with human testers 56.8%63.2%57.0% GPT-4.5 win-rate vs GPT-4o Human preference measures the percentage of queries where testers preferred GPT‑4.5 over GPT‑4o. Combining deep understanding of the world with improved collaboration results in a model that integrates ideas naturally in warm and intuitive conversations that are more attuned to human collaboration. GPT‑4.5 has a better understanding of what humans mean and interprets subtle cues or implicit expectations with greater nuance and “EQ”. GPT‑4.5 also shows stronger aesthetic intuition and creativity. It excels at helping with writing and design. Use cases Stronger reasoning on the horizon GPT‑4.5 doesn’t think before it responds, which makes its strengths particularly different from reasoning models like OpenAI o1. Compared to OpenAI o1 and OpenAI o3‑mini, GPT‑4.5 is a more general-purpose, innately smarter model. We believe reasoning will be a core capability of future models, and that the two approaches to scaling—pre-training and reasoning—will complement each other. As models like GPT‑4.5 become smarter and more knowledgeable through pre-training, they will serve as an even stronger foundation for reasoning and tool-using agents. Safety Each increase in model capabilities is also an opportunity to make the models safer. GPT‑4.5 was trained with new techniques for supervision that are combined with traditional supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF) methods like those used for GPT‑4o. We hope this work will serve as a foundation for aligning even more capable future models. To stress-test our improvements, we conducted a suite of safety tests before deployment, in accordance with our Preparedness Framework⁠(opens in a new window)⁠. We found that scaling the GPT paradigm contributed to capability improvements across our evaluations. We are publishing the detailed results from these evaluations in the accompanying system card⁠. How to use GPT-4.5 in ChatGPT Starting today, ChatGPT Pro users will be able to select GPT‑4.5 in the model picker on web, mobile, and desktop. We will begin rolling out to Plus and Team users next week, then to Enterprise and Edu users the following week. GPT‑4.5 has access to the latest up-to-date information with search, supports file and image uploads, and can use canvas to work on writing and code. However, GPT‑4.5 does not currently support multimodal features like Voice Mode, video, and screensharing in ChatGPT. In the future, we will work to simplify the user experience so AI “just works” for you. How to use GPT-4.5 in the API We’re also previewing GPT‑4.5 in the Chat Completions API, Assistants API, and Batch API to developers on all paid usage tiers⁠(opens in a new window). The model supports key features like function calling, Structured Outputs, streaming, and system messages. It also supports vision capabilities through image inputs. Based on early testing, developers may find GPT‑4.5 particularly useful for applications that benefit from its higher emotional intelligence and creativity—such as writing help, communication, learning, coaching, and brainstorming. It also shows strong capabilities in agentic planning and execution, including multi-step coding workflows and complex task automation. GPT‑4.5 is a very large and compute-intensive model, making it more expensive⁠ than and not a replacement for GPT‑4o. Because of this, we’re evaluating whether to continue serving it in the API long-term as we balance supporting current capabilities with building future models. We look forward to learning more about its strengths, capabilities, and potential applications in real-world settings. If GPT‑4.5 delivers unique value for your use case, your feedback⁠(opens in a new window) will play an important role in guiding our decision. Conclusion With every new order of magnitude of compute comes novel capabilities. GPT‑4.5 is a model at the frontier of what is possible in unsupervised learning. We continue to be surprised by the creativity of the community in uncovering new abilities and unexpected use cases. With GPT‑4.5, we invite you to explore the frontier of unsupervised learning and uncover novel capabilities with us. Appendix Below, we provide GPT‑4.5’s results on standard academic benchmarks to illustrate its current performance on tasks traditionally associated with reasoning. Even by purely scaling up unsupervised learning, GPT‑4.5 shows meaningful improvements over previous models like GPT‑4o. Still, we look forward to gaining a more complete picture of GPT‑4.5’s capabilities through this release, because we recognize academic benchmarks don’t always reflect real-world usefulness. Model evaluation scores GPT‑4.5 GPT‑4o OpenAI o3‑mini (high) GPQA (science) 71.4% 53.6% 79.7% AIME ‘24 (math) 36.7% 9.3% 87.3% MMMLU (multilingual) 85.1% 81.5% 81.1% MMMU (multimodal) 74.4% 69.1% - SWE-Lancer Diamond (coding)* 32.6% $186,125 23.3% $138,750 10.8% $89,625 SWE-Bench Verified (coding)* 38.0% 30.7% 61.0% *Numbers shown represent best internal performance."

"OpenAI moves forward with GPT-4.5 deprecation in API, triggering developer anguish and confusion Carl Franzen @carlfranzen June 17, 2025 2:52 PM Silhouettes of developers in forest pattern waving at setting sun against blue and pink and orange sky VentureBeat made with Midjourney Want smarter insights in your inbox? Sign up for our weekly newsletters to get only what matters to enterprise AI, data, and security leaders. Subscribe Now Word spread quickly across the machine learning and AI community on the social network X yesterday: OpenAI was sending developers an email notifying them that the company would be removing one of its largest and most powerful large language models (LLMs), GPT-4.5 Preview, from the official OpenAI application programming interface (API) on July 14, 2025. However, as an OpenAI spokesperson told VentureBeat via email, GPT-4.5 Preview will remain an option to individual ChatGPT users through the dropdown model selector menu at the top of the application. But it stil means that any third-party developers who had built applications or workflows atop GPT-4.5 preview (we’ll call it GPT-4.5 from here on out for simplicity’s sake, since a full GPT-4.5 was never made available on this platform), now need to switch over to another one of OpenAI’s nearly 40 (!!!) different model offerings still available through the API. The news quickly spread on X, where developers and AI enthusiasts posted reactions ranging from disappointment to confusion. Some described GPT-4.5 as a daily tool in their workflow, praising its tone and reliability. Others questioned the rationale behind launching the model in the first place if it was going to be short-lived. “This is sad — GPT-4.5 is one of my fav models,” wrote @BumrahBachi. Ben Hyak, the co-founder of AI observability and performance monitoring platform Raindrop.AI, called the move “tragic,” adding: “o3 + 4.5 are the models I use the most everyday.” Another user, @flowersslop asked bluntly, “what was the purpose of this model all along?” Deprecation had been planned since April Despite the strong reaction, OpenAI had in fact already announced the plan to deprecate GPT-4.5 Preview back in April 2025 during the launch of GPT-4.1. At that time, the company stated that developers would have three months to transition away from 4.5. OpenAI framed the model as an experimental offering that provided insights for future development, and said it would carry forward learnings from GPT-4.5 into future iterations — particularly in areas like creativity and writing nuance. In a follow-up response to VentureBeat, OpenAI communications confirmed that the June email was simply a scheduled reminder and that there are currently no plans to remove GPT-4.5 from ChatGPT subscriptions, where the model remains available. Community speculation on cost and model strategy Still, the developer-facing deprecation leaves a gap for some users, especially those who had built workflows or products around GPT-4.5’s specific characteristics. Some in the community speculated that high compute costs might have influenced the move, noting that similar changes had occurred with prior models. Others referenced recent API pricing updates, including a major reduction in cost for GPT-3.5 (internally referred to as o3), which is now priced 80% lower than before. User @chatgpt21 commented that GPT-4.5 is the “best non reasoning model for open ai on all benchmarks and it’s obvious,” and predicted that OpenAI will “they add test time compute it will blow o3 out of the water. In order to scale TTC you need to scale pre training” The end of the road for GPT-4.5 via API — developers encouraged to migrate to GPT-4.1 OpenAI has directed developers to its online forum for questions about migrating to GPT-4.1 or other models. With the API shutdown for GPT-4.5 Preview set for mid-July, teams relying on the model now have less than a month to complete that transition."