Answer: In Work or Codex in the ChatGPT desktop app, use the model and reasoning control beneath the composer to choose an available model and adjust its reasoning effort; if you see the Power slider, open Advanced to choose a specific model such as GPT-6.2 Astra. Status: Confirmed Entry: tool/codex/models/choose-model-and-reasoning-effort Revision: 2 Digest: sha256:883c911b3c1ac473 (changes whenever the content changes) Timeline: Created: 2026-11-13T03:52:03Z Last changed: 2026-11-18T13:34:16Z (Example model: — → GPT-6.2 Astra) Last verified: 2026-11-20T13:40:28Z Next check: 2026-11-21T13:40:28Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of Control location | beneath the composer | [1] | 2026-11-20 Power slider action | Advanced | [1] | 2026-11-20 Example model | GPT-6.2 Astra | [1] | 2026-11-20 Reasoning effort guidance | Start with the default effort and increase it when the task needs deeper planning or analysis. | [1] | 2026-11-20 Sources: [1] OpenAI. "Models". https://learn.chatgpt.com/docs/models.md Role: primary. Accessed: 2026-11-20T13:40:28Z Quote: "use the model and reasoning control beneath the composer to choose an available model and adjust its reasoning effort" (Supports: Control location) Quote: "If you see the Power slider, open **Advanced** to choose a specific model" (Supports: Power slider action) Quote: "such as GPT-6.2 Astra" (Supports: Example model) Quote: "Start with the default effort and increase it when the task needs deeper planning or analysis." (Supports: Reasoning effort guidance) Snapshot SHA-256: 2ca411d02af5e803e25d60eedcac752c7a6153c2c6dffafdbd854aff61f4277c (captured 2026-11-18T13:34:16Z) Verification: Method: Automated extraction from [1] with deepseek-flash (JSON output, thinking disabled). Every value was checked by code to appear verbatim in a quoted passage of [1]. On this check the text of [1] was unchanged since 2026-11-18T13:34:16Z, so the values verified then were kept. Cross-check: not-available at 2026-11-20T13:40:28Z. No independent second source is configured for this entry Last successful check: 2026-11-20T13:40:28Z Last attempt: 2026-11-20T13:40:28Z Notes and limitations: Extracted automatically from a single official source (section "Choose a model"). Related: https://latestn.com/tool/codex/models/choose-model-for-complex-work Which GPT model should I use in Codex for complex, long-running work? https://latestn.com/tool/codex/models/choose-model-names-routes How do I choose model names and routes for a Codex gateway? https://latestn.com/tool/codex/models/choose-model-reasoning-effort How do I choose a model and reasoning effort for a Codex Security bulk scan? https://latestn.com/tool/codex/models/astra-ultrafast-model What is GPT-6 Astra Ultrafast and when should I use it? https://latestn.com/tool/codex/models/bedrock-supported-models Which OpenAI models are supported when using Codex with Amazon Bedrock? https://latestn.com/tool/codex/models/choose-astra-or-sol-in-codex How do I choose between GPT-6.2 Astra and GPT-6.2 Sol in Codex? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-18T13:34:16Z | changed | Example model: — → GPT-6.2 Astra | [1] 2026-11-18T13:34:16Z | changed | Power slider action: — → Advanced | [1] 2026-11-18T13:34:16Z | changed | Ultra mode: Ultra → — | [1] 2026-11-18T13:34:16Z | changed | Higher effort tradeoff: it takes longer and uses more tokens → — | [1] 2026-11-13T03:52:03Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/codex/models/choose-model-and-reasoning-effort/latest Challenge this entry: Open challenges: None How: If a value here is wrong or out of date, send what is wrong and a link to evidence. Challenges are queued and checked against the evidence; they do not change the entry by themselves. If the entry changes as a result, the change log says so. Form: https://latestn.com/dispute/tool/codex/models/choose-model-and-reasoning-effort POST: https://latestn.com/dispute/tool/codex/models/choose-model-and-reasoning-effort with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/codex/models/choose-model-and-reasoning-effort?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). How do I choose a model and adjust reasoning effort in Codex or ChatGPT Work? Revision 2, last verified 2026-11-20T13:40:28Z. https://latestn.com/tool/codex/models/choose-model-and-reasoning-effort (accessed 2026-11-21T09:59:02Z). @misc{LatestN_tool_codex_models_choose_model_and_reasoning_effort_r2, title = {How do I choose a model and adjust reasoning effort in Codex or ChatGPT Work?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/codex/models/choose-model-and-reasoning-effort}}, note = {Revision 2; digest sha256:883c911b3c1ac473; last verified 2026-11-20T13:40:28Z; accessed 2026-11-21T09:59:02Z} } Reuse: License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/) Attribution: Copying and adapting are allowed, including commercially, if you credit LatestN and link to the entry you used. Each entry ends with a ready-made citation. URL: https://latestn.com/tool/codex/models/choose-model-and-reasoning-effort