O-Series Models
One of the well-known Models by OpenAI using Chain of Thought techniques.
One of the well-known Models by OpenAI using Chain of Thought techniques.
"We are introducing OpenAI o1, a new large language model trained with reinforcement learning to perform complex reasoning. o1 thinks before it answers—it can produce a long internal chain of thought before responding to the user." [^e2e35a] 
o1
o3
2025, Feb 01. I just tried o3 mini The Prime Time, YouTube
https://youtu.be/PoeFxGzPpXE?si=en_bfy--cHZLODu-
https://youtu.be/CqpDXeMIY1Q?si=tvD2FBtNlOZNpfqI
https://youtu.be/zRPBovmV8F8?si=txOrsdT89Iv3kzbP
https://youtu.be/j0Qz2pFScsk?si=dYcVvctwpLjhy8jf
https://youtu.be/GbnglT5XkNQ?si=Lx2_VGSfDihUmi55
Footnotes
[^e2e35a]: 2024, Sep 12. [Learning to reason with LLMs](# Learning to reason with LLMs). OpenAI Blog.
Related in the catalogue
Access 250+ Apps in Just One Line of Code
composio.devComposio: Seamlessly integrate AI Agents & LLMs with 250+ tools. Build, connect, and deploy integrations for CRMs, HRMs, ticketing, productivity, and accounting systems with SOC Type II compliance. Experience powerful system tools and managed auth for secure data management. Trusted by engineers worldwide.
Agentic AI Agents for Enterprise CX and EX Automation
yellow.aiEnterprise AI agents powered by 15+ LLMs. Eliminates the trade-off between quality, cost and scale. Experience now.
Agentic Experience for your Application
adopt.aiEmpower users to take action, automate workflows, and drive outcomes on your application - all through natural language commands.
Akto
akto.ioAkto provides real-time MCP and AI agent discovery, AI agent security testing, red teaming, agentic posture management, and guardrails. Recognized by Gartner™ as a representative AI agent security platform.