Controlling Reasoning Effort in LLMs: From OpenAI o1 to GPT-5.6

Controlling Reasoning Effort in LLMs

Reasoning models like OpenAI o1 and DeepSeek-R1 are now standard, using reinforcement learning with verifiable rewards to generate step-by-step traces. I explain how to build models with adjustable reasoning effort settings, similar to the new GPT-5.6 family. We explore training scaling versus inference scaling, debunking myths about special tokens, and show how to balance performance with compute costs.

"In the context of AI and LLM research, reasoning model means a model that outputs an intermediate reasoning trace, which is like an intermediate response that works through a question or task step by step."