reasoning effort
A request setting that tells a reasoning model how much thinking to do before answering, trading cost and latency for accuracy.
In more detail
OpenAI exposes it as an effort level; Anthropic uses an effort setting and, for extended thinking, a token budget. The reasoning tokens count as output and are billed, so measure whether higher effort actually improves your eval scores.
Related terms
- reasoning model — A model trained to work through a problem in hidden or summarised reasoning tokens before it writes its answer.
- usage block — The part of a model reply that reports how many tokens the call read and wrote, split by type, which is what you are billed for.
Taught in
- Tokens And The Context Window — AI Engineering: LLM Apps, RAG & Agents
- Reasoning Techniques — AI Engineering: LLM Apps, RAG & Agents
- Vector Indexes And Databases — AI Engineering: LLM Apps, RAG & Agents