Answer: Bulk scans use `gpt-5.6-sol` with `xhigh` reasoning effort by default; to choose another model and effort for a CSV campaign, use a model your credentials can access, and use an `--effort` value supported by your model, provider, and Codex version. For example, you can pass `--model gpt-6.1-sol --effort medium`. Status: Confirmed Entry: tool/codex/models/choose-model-reasoning-effort Revision: 2 Digest: sha256:e0a02be6143265dc (changes whenever the content changes) Timeline: Created: 2026-11-13T03:52:59Z Last changed: 2026-11-19T13:31:47Z (Effort constraint: — → --effort) Last verified: 2026-11-20T13:41:31Z Next check: 2026-11-21T13:41:31Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of Default model | gpt-5.6-sol | [1] | 2026-11-20 Default reasoning effort | xhigh | [1] | 2026-11-20 Example model | gpt-6.1-sol | [1] | 2026-11-20 Example effort | medium | [1] | 2026-11-20 Effort constraint | --effort | [1] | 2026-11-20 Sources: [1] OpenAI. "Run bulk security scans". https://learn.chatgpt.com/docs/security/cli/bulk-scans.md Role: primary. Accessed: 2026-11-20T13:41:31Z Quote: "Bulk scans use `gpt-5.6-sol` with `xhigh` reasoning effort by default." (Supports: Default model, Default reasoning effort) Quote: "--model gpt-6.1-sol \" (Supports: Example model) Quote: "--effort medium" (Supports: Example effort) Quote: "Use an `--effort` value supported by your model, provider, and Codex version." (Supports: Effort constraint) Snapshot SHA-256: 70a62735c3bba216c96f7e1dc571de575dc489904d55f86100f004f5227f0dc9 (captured 2026-11-19T13:31:45Z) 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 2026-11-19T13:31:47Z, so the values verified then were kept. Cross-check: not-available at 2026-11-20T13:41:31Z. No independent second source is configured for this entry Last successful check: 2026-11-20T13:41:31Z Last attempt: 2026-11-20T13:41:31Z Notes and limitations: Extracted automatically from a single official source (section "Choose a model and reasoning effort"). Related: https://latestn.com/tool/codex/models/custom-model-providers How do I set up a custom model provider like Amazon Bedrock or Google Cloud Vertex AI in Codex? https://latestn.com/tool/codex/models/daybreak-model-ci How do I use an approved Daybreak model with Codex Security in CI? https://latestn.com/tool/codex/models/fast-mode-supported-models Which models support Fast mode in Codex? https://latestn.com/tool/codex/models/choose-model-and-reasoning-effort How do I choose a model and adjust reasoning effort in Codex or ChatGPT Work? 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/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-19T13:31:47Z | changed | Effort constraint: — → --effort | [1] 2026-11-19T13:31:47Z | changed | Example effort: — → medium | [1] 2026-11-19T13:31:47Z | changed | Example model: — → gpt-6.1-sol | [1] 2026-11-19T13:31:47Z | changed | Default reasoning effort: — → xhigh | [1] 2026-11-19T13:31:47Z | changed | Default model: — → gpt-5.6-sol | [1] 2026-11-19T13:31:47Z | changed | effort guidance: Use an `--effort` value supported by your model, provider, and Codex version. → — | [1] 2026-11-19T13:31:47Z | changed | example effort: medium → — | [1] 2026-11-19T13:31:47Z | changed | example model: gpt-6.1-sol → — | [1] 2026-11-19T13:31:47Z | changed | default reasoning effort: xhigh → — | [1] 2026-11-19T13:31:47Z | changed | default model: gpt-5.6-sol → — | [1] 2026-11-13T03:52:59Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/codex/models/choose-model-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-reasoning-effort POST: https://latestn.com/dispute/tool/codex/models/choose-model-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-reasoning-effort?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). How do I choose a model and reasoning effort for a Codex Security bulk scan? Revision 2, last verified 2026-11-20T13:41:31Z. https://latestn.com/tool/codex/models/choose-model-reasoning-effort (accessed 2026-11-21T10:00:50Z). @misc{LatestN_tool_codex_models_choose_model_reasoning_effort_r2, title = {How do I choose a model and reasoning effort for a Codex Security bulk scan?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/codex/models/choose-model-reasoning-effort}}, note = {Revision 2; digest sha256:e0a02be6143265dc; last verified 2026-11-20T13:41:31Z; accessed 2026-11-21T10:00:50Z} } 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-reasoning-effort