Models & architecture
Reasoning model
Definition
A reasoning model is trained to generate extended internal deliberation before answering. It trades latency and cost for substantially better performance on maths, logic, coding and multi-step problems.
Reasoning models internalise what chain-of-thought prompting does externally. Rather than being told to think step by step, they are trained to produce long reasoning traces — often hidden from the user — before committing to an answer.
The gains on verifiable tasks are large: competition maths, algorithmic coding, scientific problems. The costs are also real. Responses take longer, consume many more tokens (you pay for reasoning tokens even when they are not shown), and the extra deliberation adds nothing on simple tasks.
Practical routing: use reasoning models for hard analytical problems, standard models for writing, summarisation, extraction and conversation.
Related terms
Chain-of-thought prompting
Chain-of-thought prompting asks a model to work through its reasoning step by step before answering. It measurably improves accuracy on maths, logic, and multi-step problems by forcing intermediate steps instead of an immediate guess.
Inference cost
Inference cost is what you pay to run a model on a request, almost always billed per million input and output tokens. Output tokens typically cost three to five times more than input tokens.
Large language model (LLM)
A large language model is a neural network trained on vast amounts of text to predict the next token in a sequence. That single objective, at sufficient scale, produces the ability to write, summarise, translate, reason and code.
Transformer
The transformer is the neural network architecture behind virtually all modern language models. Its key innovation is self-attention, which lets every token directly consider every other token in the input.
Attention
Attention is the mechanism that lets a model weigh how much each token should influence the interpretation of every other token. It is how a model resolves what a pronoun refers to, or which clause modifies which noun.
Parameters
Parameters are the learned numerical weights inside a model, adjusted during training. Parameter count — 7B, 70B, 405B — is a rough proxy for capacity, but not a reliable predictor of quality.
Put this into practice
Understanding the term is step one. Our free courses and tools let you actually use it.