Answer: GPT-6.2 Astra and GPT-6.2 Sol are recommended for ChatGPT Work and Codex. Astra is best for demanding work across code, apps, or research, while Sol is best for everyday coding, writing, and work across several sources. Status: Confirmed Entry: tool/codex/models/recommended-models Revision: 2 Digest: sha256:a22e5dddd361ed40 (changes whenever the content changes) Timeline: Created: 2026-11-13T03:52:03Z Last changed: 2026-11-18T13:34:16Z (Luna best at: — → focused, repeatable tasks) Last verified: 2026-11-20T13:40:29Z Next check: 2026-11-21T13:40:29Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of Recommended model for demanding work | GPT-6.2 Astra | [1] | 2026-11-20 Recommended model for everyday work | GPT-6.2 Sol | [1] | 2026-11-20 Astra best at | demanding projects, such as diagnosing a bug across services or turning research into a presentation that follows your template | [1] | 2026-11-20 Sol best at | everyday tasks like editing code, drafting a report, or turning project notes into a plan | [1] | 2026-11-20 Terra best at | writing, visual understanding, and computer use | [1] | 2026-11-20 Luna best at | focused, repeatable tasks | [1] | 2026-11-20 Sources: [1] OpenAI. "Models". https://learn.chatgpt.com/docs/models.md Role: primary. Accessed: 2026-11-20T13:40:29Z Quote: "For demanding work across code, apps, or research, choose GPT-6.2 Astra." (Supports: Recommended model for demanding work) Quote: "Choose GPT-6.2 Sol for everyday coding, writing, and work across several sources." (Supports: Recommended model for everyday work) Quote: "Choose GPT-6.2 Astra for demanding projects, such as diagnosing a bug across services or turning research into a presentation that follows your template." (Supports: Astra best at) Quote: "Use GPT-6.2 Sol for everyday tasks like editing code, drafting a report, or turning project notes into a plan." (Supports: Sol best at) Quote: "GPT-6.1 Terra is a fast, efficient choice for writing, visual understanding, and computer use." (Supports: Terra best at) Quote: "Luna suits focused, repeatable tasks." (Supports: Luna best at) 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 2026-11-20T13:40:29Z. No independent second source is configured for this entry Last successful check: 2026-11-20T13:40:29Z Last attempt: 2026-11-20T13:40:29Z Notes and limitations: Extracted automatically from a single official source (section "Recommended models"). Related: https://latestn.com/tool/codex/models/subagent-model-reasoning-effort How do I choose the model and reasoning effort for Codex subagents? https://latestn.com/tool/codex/permissions-and-security/act-on-security-findings What should I do with the findings from a Codex security change review? https://latestn.com/tool/codex/permissions-and-security/add-deployment-context-threat-model How do I add deployment context to a Codex threat model for validation? https://latestn.com/tool/codex/models/fast-mode-supported-models Which models support Fast mode in Codex? https://latestn.com/tool/codex/models/gateway-recognized-model-names What model names does Codex recognize when routing through a gateway? https://latestn.com/tool/codex/models/max-vs-ultra-mode What is Ultra mode in Codex and when should I use Max or Ultra? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-18T13:34:16Z | changed | Luna best at: — → focused, repeatable tasks | [1] 2026-11-18T13:34:16Z | changed | Terra best at: — → writing, visual understanding, and computer use | [1] 2026-11-18T13:34:16Z | changed | Sol best at: — → everyday tasks like editing code, drafting a report, or turning project notes into a plan | [1] 2026-11-18T13:34:16Z | changed | Astra best at: — → demanding projects, such as diagnosing a bug across services or turning research into a presentation that follows your template | [1] 2026-11-18T13:34:16Z | changed | Recommended model for everyday work: — → GPT-6.2 Sol | [1] 2026-11-18T13:34:16Z | changed | Recommended model for demanding work: — → GPT-6.2 Astra | [1] 2026-11-18T13:34:16Z | changed | Scope: These recommendations apply to ChatGPT Work and Codex → — | [1] 2026-11-18T13:34:16Z | changed | Luna: Luna suits focused, repeatable tasks → — | [1] 2026-11-18T13:34:16Z | changed | GPT-6.1 Sol: GPT-6.1 Sol offers near-Astra performance at a lower cost than Astra → — | [1] 2026-11-13T03:52:03Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/codex/models/recommended-models/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/recommended-models POST: https://latestn.com/dispute/tool/codex/models/recommended-models with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/codex/models/recommended-models?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). Which models are recommended for Codex and ChatGPT Work, and what is each model best at? Revision 2, last verified 2026-11-20T13:40:29Z. https://latestn.com/tool/codex/models/recommended-models (accessed 2026-11-21T09:52:37Z). @misc{LatestN_tool_codex_models_recommended_models_r2, title = {Which models are recommended for Codex and ChatGPT Work, and what is each model best at?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/codex/models/recommended-models}}, note = {Revision 2; digest sha256:a22e5dddd361ed40; last verified 2026-11-20T13:40:29Z; accessed 2026-11-21T09:52:37Z} } 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/recommended-models