Can My Agent Uselookup · compare · cite

Aug 28, 2026 · Catalog foundation is up

Product feature · models-context

Reasoning effort controlsCommon product term

Choose a documented reasoning depth, effort, or budget for a run.

Terminology basis: Common product term. OpenAI — Models in ChatGPT Work and Codex

Reasoning effort controls: 6 supported, 0 partial, 0 unsupported, 25 unreviewed across 31 cataloged products.

Markdown · JSON

Explore this familyMore in Models and context11 capabilities

Current evidence by product

Can my agent use Reasoning effort controls?

Read across for the answer. 6 of 31 current product columns have reviewed evidence; unreviewed does not mean unsupported.

Known issues (0)Report an issue
  • Supported6
  • Partial0
  • Unsupported0
  • Unknown25
  • Not applicable0

Web

9 products

Desktop

13 products

CLI

9 products

Unknown means no public evidence has been reviewed for that product and capability. It does not mean unsupported.

How statuses are assigned

Definition and scope

What this capability means

This row covers an operator-visible control over reasoning effort, depth, or budget. It does not assert that hidden reasoning is exposed, and it does not treat ordinary model selection as an equivalent control.

Evidence should name the available levels, defaults, model and plan restrictions, whether the setting changes output-token or tool-use budgets, and the scope at which it persists. Qualify controls that are only advisory or available through configuration rather than the primary interface.

Traceable compatibility

Assertion ledger

Documentation evidence only. No runtime conformance test is implied.

ChatGPTweb · current
Supported
Target
2026-08-28 ChatGPT Work web documentation observation · hosted-observation
Environment
hosted-default
Observed
2026-08-28
  • planavailable reasoning levels depend on the selected model and account eligibility
Evidence
ChatGPTdesktop · current
Supported
Target
current ChatGPT desktop documentation · dated-documentation
Environment
local-default
Observed
2026-08-28
  • planavailable reasoning levels depend on the selected model and account eligibility; Max may require enabling it in settings
Evidence
Codex CLIcli · current
Supported
Target
current Codex CLI documentation · dated-documentation
Environment
local-default
Observed
2026-08-28
  • runtimedocumented selector includes Low, Medium, High, Extra high, Max, and Ultra when the selected model supports them
Evidence
Claudeweb · current
Supported
Target
2026-08-28 Claude web documentation observation · hosted-observation
Environment
hosted-default
Observed
2026-08-28
  • runtimeeffort and extended thinking are distinct controls and depend on model availability
Evidence
Claudedesktop · current
Supported
Target
current Claude Desktop documentation · dated-documentation
Environment
local-default
Observed
2026-08-28
  • runtimeeffort and extended thinking are distinct controls and depend on model availability
Evidence
Claude CLIcli · current
Supported
Target
current Claude Code documentation · dated-documentation
Environment
local-default
Observed
2026-08-28
  • runtimelow, medium, high, xhigh, and max are documented where supported; ultrathink requests deeper reasoning for one turn
Evidence
  1. 1. Evidence checked 2026-08-28: ChatGPT Work on the web and ChatGPT desktop expose a reasoning control beneath the composer; Codex CLI exposes reasoning effort through /model, with documented Low through Ultra levels when supported.
  2. 2. Evidence checked 2026-08-28: Claude web and desktop expose effort and extended-thinking controls; Claude Code documents per-session and configured effort levels, subject to model support.