Independent reviews. IonBin has no partnerships with the tools on this page and was not paid for these listings. Our evaluations are our own, based on public documentation and our research. Product names are trademarks of their owners and are used for identification only. How disclosure works.
Reasoning models
Reasoning models spend extra computation thinking through a problem before answering. They are stronger at multi-step math, planning, code and analysis, but slower and more expensive per answer. Use them for hard problems and use faster models for routine drafting.
What it is
OpenAI says its reasoning models use internal reasoning tokens before producing a response. This helps them plan, use tools, consider alternatives and solve harder multi-step tasks. Anthropic’s current Claude models use “adaptive thinking”, where the model decides whether to think and how much.
How it works
- You send a task as usual.
- The model works through the problem in reasoning tokens before it answers.
- You steer the effort:
- OpenAI offers a reasoning-effort setting with model-dependent levels from none to max.
- Anthropic offers an effort parameter as soft guidance.
- Billing (checked 2026-10-17). Anthropic bills thinking tokens as output tokens, whether or not the thinking is shown. OpenAI counts reasoning tokens toward the output token limit you set with max_output_tokens.
Benefits
- Better results on complex, multi-step tasks.
- Fewer prompt tricks needed to get careful work.
- Good for planning steps an agent will carry out.
Limits and risks
- Higher latency and cost per request. Lower the effort setting for routine work.
- Overkill for simple tasks such as rewriting or tagging (see model tiers).
- More thinking isn’t verification. Reasoning models still make mistakes.
Agent compatibility
Not tool-specific. See Agent-ready for connector support by tool.
Levels come from each tool's recorded, sourced compatibility. How the levels work.
Related entries
Sources
- Reasoning models · OpenAIofficial accessed Oct 17, 2026
- Models overview · Anthropicofficial accessed Oct 17, 2026
- Steering thinking (adaptive thinking) · Anthropicofficial accessed Oct 17, 2026
Practitioner views are restated in our words and labeled as views, not measured results. Product facts come from official sources dated above.
Suggest an edit
IonBin's wiki isn't user-edited. Corrections go to our Directory Curator, who checks them against primary sources before anything changes. Spot something wrong or out of date on “Reasoning models”? Email us with a link to a primary source.
Suggest an edit by email or write to [email protected]