Answer: Yes. Deep research is powered by the latest model by default, and you can continue using legacy models for deep research if you prefer. Status: Check failed Entry: tool/chatgpt/models/choose-model-deep-research Revision: 2 Digest: sha256:8819d4c332dfd213 (changes whenever the content changes) Timeline: Created: 2026-11-13T03:09:02Z Last changed: 2026-11-19T11:45:01Z Last verified: 2026-11-19T11:45:01Z Last attempt: 2026-11-20T11:45:34Z (failed) Next check: 2026-11-20T12:45:34Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of Can choose different model | Yes | [1] | 2026-11-19 Default model | latest model | [1] | 2026-11-19 Legacy models option | legacy models | [1] | 2026-11-19 Sources: [1] OpenAI. "Deep research in ChatGPT". https://help.openai.com/en/articles/10500283-deep-research-in-chatgpt Role: primary. Accessed: 2026-11-19T11:45:02Z Retrieved via: DeepSeek Fetch API (Markdown conversion; the original server response was not captured) Quote: "Yes. Deep research is powered by the latest model by default" (Supports: Can choose different model) Quote: "Deep research is powered by the latest model by default" (Supports: Default model) Quote: "you can continue using legacy models for deep research if you prefer" (Supports: Legacy models option) Snapshot SHA-256: 10f19d25f10694987cea1d27dd629ba3e4f045681aa8abeab2810ee8e578a065 (captured 2026-11-19T11:45:02Z) 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]. [1] was retrieved through the DeepSeek Fetch API because a direct request did not return usable content. Cross-check: not-available at 2026-11-19T11:45:01Z. No independent second source is configured for this entry Last successful check: 2026-11-19T11:45:01Z Last attempt: 2026-11-20T11:45:34Z (failed) Notes and limitations: Extracted automatically from a single official source (section "Can I choose a different model for deep research?"). Related: https://latestn.com/tool/chatgpt/models/choose-thinking-level How do I choose a thinking level for GPT-6 in ChatGPT? https://latestn.com/tool/chatgpt/models/compare-models-and-reasoning-effort How do I compare ChatGPT models and reasoning effort settings? https://latestn.com/tool/chatgpt/models/dalle-image-generation Can I still generate images with DALL·E on ChatGPT? https://latestn.com/tool/chatgpt/models/choose-daybreak-model Which Codex and ChatGPT model should I use for authorized defensive cybersecurity work? https://latestn.com/tool/chatgpt/models/choose-gpt-6-1-sol-use-cases When should I use GPT-6.1 Sol in ChatGPT instead of other models? https://latestn.com/tool/chatgpt/models/choose-gpt-6-1-terra-use-cases Which ChatGPT model should I use for concise writing, computer-use tasks, or scoped code fixes? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-20T11:45:34Z | check-failed | Could not fetch the primary source: http 403; fallback: deepseek-fetch http 404: failed to fetch URL (request_id: fc03d840-6f20-4fdb-bd05-eb25c05aad31) | — 2026-11-19T11:45:01Z | recovered | Check succeeded again | — 2026-11-19T11:45:01Z | changed | Legacy models option: — → legacy models | [1] 2026-11-19T11:45:01Z | changed | Default model: — → latest model | [1] 2026-11-19T11:45:01Z | changed | Can choose different model: — → Yes | [1] 2026-11-19T11:45:01Z | changed | legacy models option: legacy models → — | [1] 2026-11-19T11:45:01Z | changed | default model: latest model → — | [1] 2026-11-14T11:45:44Z | check-failed | Could not fetch the primary source: http 403; fallback: deepseek-fetch http 404: failed to fetch URL (request_id: 74e8d4f2-9d20-4e3e-bffd-dae516dc7314) | — 2026-11-13T03:09:02Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/chatgpt/models/choose-model-deep-research/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/chatgpt/models/choose-model-deep-research POST: https://latestn.com/dispute/tool/chatgpt/models/choose-model-deep-research with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/chatgpt/models/choose-model-deep-research?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). Can I choose a different model for deep research in ChatGPT? Revision 2, last verified 2026-11-19T11:45:01Z. https://latestn.com/tool/chatgpt/models/choose-model-deep-research (accessed 2026-11-21T10:02:01Z). @misc{LatestN_tool_chatgpt_models_choose_model_deep_research_r2, title = {Can I choose a different model for deep research in ChatGPT?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/chatgpt/models/choose-model-deep-research}}, note = {Revision 2; digest sha256:8819d4c332dfd213; last verified 2026-11-19T11:45:01Z; accessed 2026-11-21T10:02:01Z} } 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/chatgpt/models/choose-model-deep-research