--- title: "Reasoning effort controls" canonical: "https://canmyagentuse.com/features/reasoning-effort-controls" contentKind: "feature" locale: "en" description: "Choose a documented reasoning depth, effort, or budget for a run." llmSummary: "Reasoning effort controls let an operator choose a documented reasoning mode or budget; model selection alone does not prove this capability." publishedAt: "2026-08-28T00:00:00.000Z" updatedAt: "2026-08-28T00:00:00.000Z" verifiedAt: "2026-08-28" tags: ["models","reasoning","latency","cost"] --- # Reasoning effort controls Reasoning effort controls let an operator choose a documented reasoning mode or budget; model selection alone does not prove this capability. - HTML: https://canmyagentuse.com/features/reasoning-effort-controls - JSON: https://canmyagentuse.com/api/v1/features/reasoning-effort-controls.json - Markdown: https://canmyagentuse.com/features/reasoning-effort-controls.md Terminology basis: **Common product term** — https://learn.chatgpt.com/docs/models. ## Current support at a glance Reasoning effort controls: 6 supported, 0 partial, 0 unsupported, 25 unreviewed across 31 cataloged products. - Reviewed current products: 6 of 31 - Supported: 6 - Partial: 0 - Unsupported: 0 - Unreviewed: 25 - Not applicable: 0 Unknown or unreviewed means insufficient published evidence; it does not mean unsupported. 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. ## Catalog context - Category: [models-context](/categories/models-context.md) - Terminology basis: Common product term - Aliases: thinking budget, reasoning mode, thinking level - Family: [Models and context](/features/models-and-context.md) - Siblings: [Automatic context compaction](/features/automatic-context-compaction.md), [Context compaction controls](/features/context-compaction-controls.md), [Context usage](/features/context-usage-visibility.md), [Context window](/features/context-window.md), [Local models](/features/local-models.md), [Model fallback](/features/model-fallback.md), [Model selection](/features/model-selection.md), [Output token limit](/features/output-token-limit.md), [Prompt cache controls](/features/prompt-cache-controls.md), [Prompt cache telemetry](/features/prompt-cache-telemetry.md), [Prompt caching](/features/prompt-cache-reuse.md) ## Compatibility assertions Unknown means insufficient published evidence; it does not mean unsupported. ### ChatGPT (web) - Harness: [ChatGPT](/harnesses/chatgpt-web.md) - current: **Supported** - Target: hosted-observation — 2026-08-28 ChatGPT Work web documentation observation; observed 2026-08-28 - Environment: hosted-default - Constraint (plan): available reasoning levels depend on the selected model and account eligibility - Evidence: [OpenAI — Models in ChatGPT Work and Codex](https://learn.chatgpt.com/docs/models) — documented; observed 2026-08-28 - Qualification note 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. - preview: **Unknown** ### Claude (web) - Harness: [Claude](/harnesses/claude-web.md) - current: **Supported** - Target: hosted-observation — 2026-08-28 Claude web documentation observation; observed 2026-08-28 - Environment: hosted-default - Constraint (runtime): effort and extended thinking are distinct controls and depend on model availability - Evidence: [Anthropic — Change model, effort, and thinking settings](https://support.claude.com/en/articles/8664678-change-the-model-effort-and-thinking-settings) — documented; observed 2026-08-28 - Qualification note 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. - preview: **Unknown** ### Gemini (web) - Harness: [Gemini](/harnesses/gemini-web.md) - current: **Unknown** - preview: **Unknown** ### Copilot (web) - Harness: [Copilot](/harnesses/copilot-web.md) - current: **Unknown** - preview: **Unknown** ### Grok (web) - Harness: [Grok](/harnesses/grok-web.md) - current: **Unknown** - preview: **Unknown** ### Grok Bot (desktop) - Harness: [Grok Bot](/harnesses/grok-bot-desktop.md) - current: **Unknown** ### Perplexity (web) - Harness: [Perplexity](/harnesses/perplexity-web.md) - current: **Unknown** - preview: **Unknown** ### Le Chat (web) - Harness: [Le Chat](/harnesses/le-chat.md) - current: **Unknown** - preview: **Unknown** ### Devin (web) - Harness: [Devin](/harnesses/devin-web.md) - current: **Unknown** - preview: **Unknown** ### Replit Agent (web) - Harness: [Replit Agent](/harnesses/replit-agent.md) - current: **Unknown** - preview: **Unknown** ### ChatGPT (desktop) - Harness: [ChatGPT](/harnesses/chatgpt-desktop.md) - current: **Supported** - Target: dated-documentation — current ChatGPT desktop documentation; observed 2026-08-28 - Environment: local-default - Constraint (plan): available reasoning levels depend on the selected model and account eligibility; Max may require enabling it in settings - Evidence: [OpenAI — Models in ChatGPT Work and Codex](https://learn.chatgpt.com/docs/models) — documented; observed 2026-08-28 - Qualification note 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. - preview: **Unknown** ### Claude (desktop) - Harness: [Claude](/harnesses/claude-desktop.md) - current: **Supported** - Target: dated-documentation — current Claude Desktop documentation; observed 2026-08-28 - Environment: local-default - Constraint (runtime): effort and extended thinking are distinct controls and depend on model availability - Evidence: [Anthropic — Change model, effort, and thinking settings](https://support.claude.com/en/articles/8664678-change-the-model-effort-and-thinking-settings) — documented; observed 2026-08-28 - Qualification note 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. - preview: **Unknown** ### Cursor (desktop) - Harness: [Cursor](/harnesses/cursor.md) - current: **Unknown** - preview: **Unknown** ### OpenWork Desktop (desktop) - Harness: [OpenWork Desktop](/harnesses/openwork-desktop.md) - current: **Unknown** ### Copilot Chat (desktop) - Harness: [Copilot Chat](/harnesses/vscode-copilot.md) - current: **Unknown** - preview: **Unknown** ### Chrome WebMCP origin trial (desktop) - Harness: [Chrome WebMCP origin trial](/harnesses/chrome-webmcp-preview.md) - current: **Unknown** ### Windsurf (desktop) - Harness: [Windsurf](/harnesses/windsurf.md) - current: **Unknown** - preview: **Unknown** ### Zed Agent (desktop) - Harness: [Zed Agent](/harnesses/zed-agent.md) - current: **Unknown** - preview: **Unknown** ### Continue (desktop) - Harness: [Continue](/harnesses/continue.md) - current: **Unknown** - preview: **Unknown** ### Cline (desktop) - Harness: [Cline](/harnesses/cline.md) - current: **Unknown** - preview: **Unknown** ### JetBrains AI (desktop) - Harness: [JetBrains AI](/harnesses/jetbrains-ai.md) - current: **Unknown** - preview: **Unknown** ### Warp (desktop) - Harness: [Warp](/harnesses/warp.md) - current: **Unknown** - preview: **Unknown** ### Claude CLI (cli) - Harness: [Claude CLI](/harnesses/claude-cli.md) - current: **Supported** - Target: dated-documentation — current Claude Code documentation; observed 2026-08-28 - Environment: local-default - Constraint (runtime): low, medium, high, xhigh, and max are documented where supported; ultrathink requests deeper reasoning for one turn - Evidence: [Anthropic — Claude Code model configuration](https://code.claude.com/docs/en/model-config) — documented; observed 2026-08-28 - Qualification note 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. - preview: **Unknown** ### ChatGPT CLI (cli) - Harness: [ChatGPT CLI](/harnesses/chatgpt-cli.md) - current: **Unknown** - preview: **Unknown** ### Codex CLI (cli) - Harness: [Codex CLI](/harnesses/codex-cli.md) - current: **Supported** - Target: dated-documentation — current Codex CLI documentation; observed 2026-08-28 - Environment: local-default - Constraint (runtime): documented selector includes Low, Medium, High, Extra high, Max, and Ultra when the selected model supports them - Evidence: [OpenAI — Models in ChatGPT Work and Codex](https://learn.chatgpt.com/docs/models) — documented; observed 2026-08-28 - Qualification note 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. - preview: **Unknown** ### OpenCode (cli) - Harness: [OpenCode](/harnesses/opencode.md) - current: **Unknown** - preview: **Unknown** ### Gemini CLI (cli) - Harness: [Gemini CLI](/harnesses/gemini-cli.md) - current: **Unknown** - preview: **Unknown** ### Aider (cli) - Harness: [Aider](/harnesses/aider.md) - current: **Unknown** - preview: **Unknown** ### Goose (cli) - Harness: [Goose](/harnesses/goose.md) - current: **Unknown** - preview: **Unknown** ### Copilot CLI (cli) - Harness: [Copilot CLI](/harnesses/copilot-cli.md) - current: **Unknown** - preview: **Unknown** ### Amp (cli) - Harness: [Amp](/harnesses/amp-cli.md) - current: **Unknown** - preview: **Unknown**