>
o
Model Details
Domain:
Model Access:
API access
Introduction
We’re releasing OpenAI o3-mini, the newest, most cost-efficient model in our reasoning series, available in both ChatGPT and the API today. Previewed in December 2024, this powerful and fast model advances the boundaries of what small models can achieve, delivering exceptional STEM capabilities—with particular strength in science, math, and coding—all while maintaining the low cost and reduced latency of OpenAI o1-mini. OpenAI o3-mini is our first small reasoning model that supports highly requested developer features including function calling(opens in a new window), Structured Outputs(opens in a new window), and developer messages(opens in a new window), making it production-ready out of the gate. Like OpenAI o1-mini and OpenAI o1-preview, o3-mini will support streaming(opens in a new window). Also, developers can choose between three reasoning effort(opens in a new window) options—low, medium, and high—to optimize for their specific use cases. This flexibility allows o3-mini to “think harder” when tackling complex challenges or prioritize speed when latency is a concern. o3-mini does not support vision capabilities, so developers should continue using OpenAI o1 for visual reasoning tasks. o3-mini is rolling out in the Chat Completions API, Assistants API, and Batch API starting today to select developers in API usage tiers 3-5
Benchmarking
Notes: We can’t make a precise estimate, but seems unlikely to exceed 10^25 FLOP. We think active parameter count is 10-30B. This would require >55T tokens to reach 10^25 FLOP at the large size, i.e. well beyond 10x overtraining relative to Chinchilla.
Parameters
Notes: Can't get an exact estimate, but we suspect total parameter count around 60B-120B, active parameters around 10B-30B. Given these models are served at 150-200 tok/s, at $4.40/Mtok output, inference economics (https://epoch.ai/blog/inference-economics-of-language-models) suggests total parameter count around 60-120B parameters, with mixture-of-experts active parameters around 10-30B. MoEs make a given model roughly comparable to a ~50% smaller dense model (https://epoch.ai/gradient-updates/moe-vs-dense-models-inference), which lines up decently with Magistral Small pricing (24B dense, served at a similar speed for the cheaper $1.50/Mtok).
Authors
Training
Brian Zhang, Eric Mitchell, Hongyu Ren, Kevin Lu, Max Schwarzer, Michelle Pokrass, Shengjia Zhao, Ted Sanders
Eval
Adam Kalai, Alex Tachard Passos, Ben Sokolowsky, Elaine Ya Le, Erik Ritter, Hao Sheng, Hanson Wang, Ilya Kostrikov, James Lee, Johannes Ferstad, Michael Lampe, Prashanth Radhakrishnan, Sean Fitzgerald, Sebastien Bubeck, Yann Dubois, Yu Bai
Frontier Evals & Preparedness
Andy Applebaum, Elizabeth Proehl, Evan Mays, Joel Parish, Kevin Liu, Leon Maksin, Leyton Ho, Miles Wang, Michele Wang, Olivia Watkins, Patrick Chao, Samuel Miserendino, Tejal Patwardhan
Engineering
Adam Walker, Akshay Nathan, Alyssa Huang, Andy Wang, Ankit Gohel, Ben Eggers, Brian Yu, Bryan Ashley, Chengdu Huang, Christian Hoareau, Davin Bogan, Emily Sokolova, Eric Horacek, Eric Jiang, Felipe Petroski Such, Jonah Cohen, Josh Gross, Justin Becker, Kan Wu, Kevin Whinnery, Larry Lv, Lee Byron, Manoli Liodakis, Max Johnson, Mike Trpcic, Murat Yesildal, Rasmus Rygaard, RJ Marsan, Rohit Ramchandani, Rohan Kshirsagar, Roman Huet, Sara Conlon, Shuaiqi (Tony) Xia, Siyuan Fu, Srinivas Narayanan, Sulman Choudhry, Tomer Kaftan, Trevor Creech
Search
Adam Fry, Adam Perelman, Brandon Wang, Cristina Scheau, Philip Pronin, Sundeep Tirumalareddy, Will Ellsworth, Zewei Chu
Product
Antonia Woodford, Beth Hoover, Jake Brill, Kelly Stirman, Minnia Feng, Neel Ajjarapu, Nick Turley, Nikunj Handa, Olivier Godement
Safety
Andrea Vallone, Andrew Duberstein, Enis Sert, Eric Wallace, Grace Zhao, Irina Kofman, Jieqi Yu, Joaquin Quinonero Candela, Madelaine Boyd, Mehmet Yatbaz, Mike McClay, Mingxuan Wang, Saachi Jain, Sandhini Agarwal, Sam Toizer, Santiago Hernández, Steve Mostovoy, Young Cha, Tao Li, Yunyun Wang
External Redteaming
Lama Ahmad, Troy Peterson
Research Program Managers
Carpus Chang, Kristen Ying
Leadership
Aidan Clark, Dane Stuckey, Jerry Tworek, Jakub Pachocki, Johannes Heidecke, Kevin Weil, Liam Fedus, Mark Chen, Sam Altman, Wojciech Zaremba
Multimodal
Vision
Video
Speech