gpt-image-1, o1, gpt-4.1-nano: what to change by 2026-10-23
As of 2026-10-26, the 2026-04-22 section of OpenAI's deprecation page is in the past tense: “Access to these models was shut down on October 23, 2026.” All 17 rows listed here shut down on that date. gpt-image-1 goes to gpt-image-2.5-sunburst or gpt-image-2.5-flare; o1, o1-pro and o3-mini go to gpt-5.6-sol (o1-pro with reasoning.mode: pro), o4-mini and ft-o4-mini-2025-04-16 to gpt-5.6-terra, gpt-4o-2024-05-13 to gpt-5.6-sol; OpenAI names gpt-5.6-luna for gpt-4.1-nano and its fine-tuning entry. The 8 added rows: gpt-5.6-sol for gpt-4-0613, gpt-4-1106-preview, gpt-4-turbo and ft-gpt-4, and gpt-5.6-terra for gpt-3.5-turbo-0125, ft-gpt-3.5-turbo, ft-babbage-002 and ft-davinci-002.
Updated 2026-10-26
One key for Claude, GPT and leading Chinese models, billed per token, up and running in minutes.
- Billed per token — live rates on /models
- Pay by card (Visa / Mastercard), Apple Pay, Google Pay or crypto
- Self-service: top up and activate instantly
Four key points
the shutdown date in the table
The section dated 2026-04-22 has three columns - Shutdown date, Model snapshot, Substitute model - and all 17 rows read October 23, 2026; the 2026-10-26 copy says was shut down.
rows this page lists
The 2026-10-23 wave is 12 snapshot rows plus 5 fine-tuning rows, 17 in total, and since 2026-10-14 this page lists all of them: gpt-image-1; o1, o1-pro, o3-mini, o4-mini and ft-o4-mini-2025-04-16; gpt-4.1-nano together with its fine-tuning entry; gpt-4o-2024-05-13; plus the 8 rows added now - gpt-3.5-turbo-0125, gpt-4-0613, gpt-4-1106-preview, gpt-4-turbo, ft-gpt-3.5-turbo, ft-gpt-4, ft-babbage-002 and ft-davinci-002.
the minimum notice the vendor states
Same page, policy section: generally available models get at least 6 months, specialised variants of them at least 3 months, and preview models can be retired on much shorter notice - the example given is 2 weeks. From 2026-04-22 to 2026-10-23 is roughly that span, and calling it exactly 6 months is our own arithmetic.
the second image wave
A section dated 2026-06-02 sets 2026-12-01 as the shutdown date for gpt-image-1-mini, gpt-image-1.5 and chatgpt-image-latest; as of 2026-10-07 all three point to gpt-image-2.5-sunburst or gpt-image-2.5-flare. Reasoning continues on 2026-12-11, where o3-2025-04-16 goes to gpt-5.6-sol.
What this is
As of 2026-10-26 all 17 rows of the official 2026-04-22 section shut down on October 23, 2026: 12 snapshots plus 5 fine-tuning entries, each listed here. The substitutes lead only to gpt-image-2.5-sunburst or gpt-image-2.5-flare, gpt-5.6-sol, gpt-5.6-terra and gpt-5.6-luna, and the o1-pro row adds reasoning.mode: pro. Among the 8 added rows, OpenAI writes gpt-5.6-sol for gpt-4-0613, gpt-4-1106-preview, gpt-4-turbo and ft-gpt-4, and gpt-5.6-terra for gpt-3.5-turbo-0125, ft-gpt-3.5-turbo, ft-babbage-002 and ft-davinci-002.
What happened
The section dated 2026-04-22 now says “Access to these models was shut down on October 23, 2026”, and all 17 rows in it carry October 23, 2026. In the 2026-10-26 copy the section sits under Past deprecations. Next on the schedule: on 2026-12-11 older GPT-5 and o3 snapshots shut down, for example o3-2025-04-16 onto gpt-5.6-sol. After that, a section dated 2026-10-01 sets 2027-04-01 as the shutdown date for gpt-5.3-codex, gpt-5.1 and gpt-5.4-nano, with substitutes gpt-6-sol, gpt-6-sol and gpt-6-luna respectively.
Timeline
The section dated 2026-04-22: Legacy GPT model snapshots lists 17 rows all dated October 23, 2026, and this page has carried all 17 since 2026-10-14.
Re-fetched 2026-10-26: all 17 rows still carry October 23, 2026, the text now says was shut down, and the substitutes are unchanged; the section sits under Past deprecations.
2026-10-23, the shutdown day, has passed: all 17 rows stopped together - the image row, the 5 reasoning rows, gpt-4.1-nano with its fine-tuning entry, gpt-4o-2024-05-13, and the 8 added rows (gpt-3.5-turbo-0125, gpt-4-0613, gpt-4-1106-preview, gpt-4-turbo, ft-gpt-3.5-turbo, ft-gpt-4, ft-babbage-002, ft-davinci-002), each snapshot alongside its alias.
Confirmed vs caution
Officially confirmed
Only what the copy fetched on 2026-10-26 states word for word: the section dated 2026-04-22; the header Shutdown date / Model snapshot / Substitute model; October 23, 2026 on all 17 rows; the sentence “Access to these models was shut down on October 23, 2026”; the substitute named in each of those 17 rows, including gpt-image-2.5-sunburst or gpt-image-2.5-flare on the gpt-image-1 row, reasoning.mode: pro in parentheses on the o1-pro row, and the five fine-tuning rows ft-gpt-3.5-turbo, ft-gpt-4, ft-gpt-4.1-nano-2025-04-14, ft-babbage-002 and ft-davinci-002; the definition that at the shut down the model or endpoint is no longer accessible; at least 6 months for generally available models, 3 for specialised variants, less for preview; and the dedicated-capacity sentence.
⚠️ Caution
Not to be written as fact: that QCode redirects an old id automatically or cuts it over the same day as OpenAI - unchecked; that a substitute behaves or prices the same, since the table maps ids only; that 2026-10-23 will slip, as the 2026-10-26 copy has no postponement wording and the text already says was shut down. Reading the section title 2026-04-22 as the announcement date is our inference. The QCode status of o1, o3-mini, o4-mini and the old gpt-image ids follows /models. The 8 rows added on 2026-10-14, including gpt-4-1106-preview and the ft- fine-tuning rows, are listed row by row with their substitutes, not merely named.
Two families, two mappings
Images: 1 row, 1 target
gpt-image-1 → gpt-image-2.5-sunburst or gpt-image-2.5-flare, shutdown 2026-10-23; the 2026-09-20 capture still had gpt-image-2 in that cell. Three more image ids (gpt-image-1-mini, gpt-image-1.5, chatgpt-image-latest) are not on that day: OpenAI lists them under 2026-12-01, onto the same two ids. gpt-image-2 itself has its own page.
Reasoning: 5 rows, 2 targets
o1-2024-12-17 | o1, o1-pro-2025-03-19 | o1-pro and o3-mini-2025-01-31 | o3-mini go to gpt-5.6-sol, the o1-pro row with reasoning.mode: pro; o4-mini-2025-04-16 | o4-mini and ft-o4-mini-2025-04-16 go to gpt-5.6-terra. None of the 5 rows keeps an o-series id.
What to do
Four steps. First, search: grep your code, environment variables, SDK defaults and eval scripts for the 17 ids, snapshots and aliases together - the o1 cell holds o1-2024-12-17 and o1 side by side, and the gpt-3.5-turbo-0125 cell also carries gpt-3.5-turbo and gpt-3.5-turbo-completions, one date for all of them. Second, change the model field to the substitute the table names: gpt-image-1 → gpt-image-2.5-sunburst or gpt-image-2.5-flare, the reasoning rows onto gpt-5.6-sol or gpt-5.6-terra, gpt-4o-2024-05-13 → gpt-5.6-sol, and for the 8 rows added now, as the table has it: gpt-4-0613 → gpt-5.6-sol, gpt-4-1106-preview → gpt-5.6-sol, gpt-4-turbo → gpt-5.6-sol, ft-gpt-4 → gpt-5.6-sol, gpt-3.5-turbo-0125 → gpt-5.6-terra, ft-gpt-3.5-turbo → gpt-5.6-terra, ft-babbage-002 → gpt-5.6-terra, ft-davinci-002 → gpt-5.6-terra. The official substitute for gpt-4.1-nano and its fine-tuning entry ft-gpt-4.1-nano-2025-04-14 is gpt-5.6-luna (not supported on QCode); on QCode, please use another GPT model instead, such as gpt-5.6-terra, gpt-6-sol or gpt-6.1-sol (our suggestion, not an OpenAI mapping). Third, add: o1-pro also needs reasoning.mode: pro, and swapping only the id drops the pro behaviour. Fourth, verify against the endpoint you actually call: run real requests, confirm that the model reported back and in your billing log is the new id, and keep a same-prompt comparison between old and new. The last step is our operational advice - OpenAI only says the model is no longer accessible after shutdown, not that the substitute behaves the same.
On QCode
As of 2026-10-26 the two reasoning substitutes on this page, gpt-5.6-sol and gpt-5.6-terra, are callable on QCode, billed per token, with unit prices for each model on /models. GPT models use the OpenAI endpoints, not the Anthropic one: the OpenAI SDK base_url is https://api.qcode.cc/openai/v1 (requests go to /openai/v1/chat/completions), Codex CLI uses https://api.qcode.cc/openai (requests go to /openai/v1/responses). As of 2026-10-26, QCode does not currently support gpt-6-luna / gpt-5.6-luna; please use another GPT model, such as gpt-6.1-sol, gpt-6-sol or gpt-5.6-terra. For the image substitutes and the retired ids, the QCode status follows /models. To try the replacement for a few days first: Not ready for a monthly plan? Pay-as-you-go Packs start at $4 for a one-time quota you use within 7 days; if you already have a Personal Plan, add a booster pack when you need more quota.
FAQ
Have o1 and gpt-image-1 shut down?
Yes. As of 2026-10-26 the deprecation page states in the past tense that these models were shut down on 2026-10-23; o1-2024-12-17 and the alias o1 share one cell, and the same goes for o1-pro, o3-mini and o4-mini. The section now sits under Past deprecations.
Is gpt-image-1.5 also on 2026-10-23?
No. On 2026-10-23 the image family has only the gpt-image-1 row. gpt-image-1.5, gpt-image-1-mini and chatgpt-image-latest sit in the section dated 2026-06-02 and shut down on 2026-12-01; as of 2026-10-07 their substitute is gpt-image-2.5-sunburst or gpt-image-2.5-flare.
How much does an o1-pro caller have to change?
Two places: model becomes gpt-5.6-sol and the request carries reasoning.mode: pro, the condition in parentheses on that row. The same pattern is on o3-pro-2025-06-10 and gpt-5-pro-2025-10-06 in the 2026-12-11 section. Swap only the id and you lose the pro tier.
gpt-4.1-nano and gpt-4o-2024-05-13 are chat models - why here?
OpenAI put them in the same section and the same 2026-10-23 table, with substitutes gpt-5.6-luna (not supported on QCode) and gpt-5.6-sol; gpt-4.1-nano also has a fine-tuning entry, ft-gpt-4.1-nano-2025-04-14, with the same date and target. On QCode, please use another GPT model instead, such as gpt-5.6-terra, gpt-6-sol or gpt-6.1-sol (our suggestion). On that same day OpenAI writes gpt-5.6-sol for gpt-4-turbo, gpt-4-0613, gpt-4-1106-preview and ft-gpt-4, and gpt-5.6-terra for gpt-3.5-turbo-0125, ft-gpt-3.5-turbo, ft-babbage-002 and ft-davinci-002; those 8 rows have been listed here row by row since 2026-10-14.
What counts as verified after the change?
Whatever the endpoint you really call shows: run real requests, confirm the model in the response and in the billing log is the new id, then send one old-id request and watch it get refused. The vendor guarantees only inaccessibility, not equivalence.
After OpenAI shuts it down, does QCode follow?
As of 2026-10-26 the reasoning substitutes on this page, gpt-5.6-sol and gpt-5.6-terra, are callable on QCode; in the official table the substitute for o1, o1-pro and o3-mini is gpt-5.6-sol and for o4-mini gpt-5.6-terra. For the status of an old id on QCode, /models is the reference, and no promise is made that it stays callable after the shutdown date.
Sources
OpenAI deprecations page https://developers.openai.com/api/docs/deprecations (and its .md version), fetched directly on 2026-10-26; the quotes come from the sections dated 2026-04-22, 2026-06-02, 2026-06-11 and 2026-10-01 plus the notice-period policy. The earlier gpt-image-1 substitute comes from the Wayback snapshot https://web.archive.org/web/20260920011745/https://developers.openai.com/api/docs/deprecations (2026-09-20 01:17 UTC). QCode setup values come from the docs.qcode.cc page on endpoints and API paths (fetched 2026-10-26). OpenAI writes dates as October 23, 2026 or Dec 1, 2026; this page renders them as ISO. If the table changes again, this page needs re-verification.
Clean the 17 old ids out of config first
As of 2026-10-26, gpt-5.6-sol and gpt-5.6-terra are callable on QCode, billed per token, unit prices on /models. Whether a retired id stays callable follows /models.
Related
GPT-4 series deprecation and removal
Noticed 2026-10-14, removed 2027-01-14: four GPT-4 models, the snapshot IDs, the official replacement gpt-6-luna, plus shutdown_date and the migration steps.
GPT Image 2 guide
How gpt-image-2 works is on its own page; as of 2026-10-07 the official substitute for gpt-image-1 is the gpt-image-2.5 line.
GPT-5.6 Sol vs Terra vs Luna
How the three GPT-5.6 tiers differ; gpt-5.6-luna has since been removed from QCode /models and is not recommended for new integrations.
Crypto payment guide
Nine coins, 56 networks, zero platform fee for AI coding API credits.
Not affiliated with OpenAI. Dates, model ids and substitutions come from the public deprecation page fetched on 2026-10-26; the official page prevails, and model availability follows /models. This is not an OpenAI migration guide and no promise that a retired id stays callable.