OpenAI o1 Mini
OpenAI launches o1-mini, a cost-efficient reasoning model excelling in math and coding, now available to API users with enhanced performance
By OpenAI

OpenAI o1 Mini overview

What is OpenAI o1 Mini?

On September 12, 2024, OpenAI announced the release of o1-mini, a cost-efficient reasoning model that excels in STEM fields, particularly math and coding. This new model nearly matches the performance of OpenAI o1 on evaluation benchmarks such as AIME and Codeforces.

Key Features and Performance

  • o1-mini is now available to tier 5 API users at a cost 80% cheaper than OpenAI o1-preview.
  • ChatGPT Plus, Team, Enterprise, and Edu users can use o1-mini as an alternative to o1-preview, with higher rate limits and lower latency.
  • In mathematics, o1-mini achieves a 70.0% score on the AIME competition, competitive with o1 (74.4%) and outperforming o1-preview (44.6%).
  • For coding, o1-mini reaches a 1650 Elo rating on Codeforces, comparable to o1 (1673) and superior to o1-preview (1258).
  • The model performs well on STEM-related academic benchmarks, sometimes outperforming GPT-4o on science and math tests.

Specialized Training and Efficiency

Unlike larger language models pre-trained on vast text datasets, o1-mini is a smaller model optimized specifically for STEM reasoning during pretraining. This specialization allows it to achieve comparable performance on many useful reasoning tasks while being significantly more cost-efficient.

Safety and Alignment

o1-mini is trained using the same alignment and safety techniques as o1-preview. It demonstrates improved jailbreak robustness compared to GPT-4o and has undergone rigorous safety evaluations before deployment.

Limitations

Due to its STEM specialization, o1-mini’s factual knowledge on non-STEM topics is comparable to smaller language models. OpenAI plans to address these limitations in future versions and explore extending the model to other modalities and specialties outside of STEM.

This release represents a significant step forward in creating more efficient and specialized AI models, potentially opening up new applications in fields requiring advanced reasoning capabilities at a lower cost.

See OpenAI o1 pricing

Other popular AI Models (LLMs)

Best OpenAI model for advanced coding and research capabilities
10X your coding tasks and
Better coding, reasoning, and automation

You can now access three new models through the API: GPT-4.1, …

ERNIE 4.5 is Baidu’s latest generation native multimodal foundation model, representing …

TitleModalitiesModel FeaturesTagline
GPT-510Best OpenAI model for advanced coding and research capabilities
Claude Opus 4Text Input and Output, Image Input OnlyStreaming10X your coding tasks and
Claude Sonnet 4Text Input and Output, Image Input Only, Audio Input OnlyStreamingBetter coding, reasoning, and automation
GPT 4.1text,image-input,novideo,noaudiostreaming,function-calling,distillation
Ernie 4.5Text Input and Output, Image Input Only, Video Input Only, Audio Input OnlyStreaming, Function Caling, Fine Tuning, Predicted Outputs, Web Search
GPT 4.5text,image-input,novideo,noaudiostreaming,function-calling,distillation
Kimi k1.5
Claude 3.7 Sonnet
DeepSeek R1
OpenAI o1 Mini