Reasoning models such as OpenAI's o1 and o3 series use an extended thinking process before generating a response. AI Chat supports these models and surfaces their reasoning output so you can follow the model's chain of thought.
What Are Reasoning Models?
Standard chat models generate responses token by token in a single pass. Reasoning models add a thinking phase before the final response. During this phase, the model works through the problem step by step, considering different approaches and verifying its logic before producing an answer.
This thinking process is especially beneficial for:
Complex math and logic problems
Multi-step analysis and planning
Code debugging and architectural decisions
Tasks that require careful evaluation of tradeoffs
How Reasoning Models Differ
When you use a reasoning model in AI Chat, the experience differs from standard models in several ways:
Longer response times — The thinking phase adds processing time before the response begins streaming. This is normal and expected.
Reasoning content — The model's internal reasoning may be displayed alongside the final response, allowing you to follow how it arrived at its answer.
Reasoning tokens — Reasoning models consume additional tokens for the thinking phase. These reasoning tokens count toward the model's context window and usage.
Reasoning Effort
Some reasoning models support a reasoning effort parameter that controls how much time the model spends thinking before responding. AI Chat supports three effort levels:
Low — Minimal reasoning. The model spends less time thinking, resulting in faster responses. Best for straightforward questions where deep analysis is not needed.
Medium — Balanced reasoning. A good default for most tasks.
High — Maximum reasoning. The model takes more time to think through the problem thoroughly. Best for complex problems where accuracy is critical.
Model Support
Reasoning effort is only available for models that support it. If the selected model does not support reasoning effort, the setting has no effect.
When to Use Reasoning Models
Use reasoning models when:
The task involves complex logic, math, or multi-step problem-solving.
You need the model to carefully evaluate multiple options before answering.
Accuracy matters more than response speed.
You are debugging intricate code or analyzing system architectures.
Use standard models when:
You need quick, conversational responses.
The task is straightforward (summarization, simple Q&A, text generation).
Low latency is important.
You want to minimize token usage.
Working with Reasoning Output
When a reasoning model is used, AI Chat may display the model's reasoning process alongside the final response. This reasoning content shows the steps the model took to arrive at its answer. Reviewing this output can help you:
Verify the model's logic and catch errors in its reasoning.
Understand why the model chose a particular approach.
Refine your prompt based on how the model interpreted your request.
