gpt-image-1, o1, gpt-4.1-nano: what to change by 2026-10-23
As of 2026-10-07, the 2026-04-22 section of OpenAI's deprecation page still gives October 23, 2026 as the shutdown date for the 9 rows on this page. The substitute for gpt-image-1 has changed 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. For gpt-4.1-nano OpenAI names gpt-5.6-luna. As of 2026-10-08, QCode does not support gpt-6-luna or gpt-5.6-luna for now (both removed from /models); please use another GPT model, such as gpt-6.1-sol, gpt-6-sol or gpt-5.6-terra. Chat rows: /openai-gpt-4-turbo-sunset.
Updated 2026-10-08
Hit your subscription limit or keep getting 429s? Switch to an API billed per token and keep working with one key.
- Billed per token — live rates on /models
- Pay by card (Visa / Mastercard / AMEX), 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 the 9 rows here all read October 23, 2026. Another section defines it: at the shut down, the model or endpoint is no longer accessible.
rows this page lists
The 2026-10-23 wave is 12 snapshot rows plus 5 fine-tuning rows, 17 in total. We list 9: 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; and gpt-4o-2024-05-13. The remaining 8 rows are chat and base models.
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 2026-10-07 the job is still small: before 2026-10-23, swap the retired model ids for the ones the table names. Every row on OpenAI's page carries a shutdown date, a model snapshot and a substitute; the 9 rows here lead 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. Compared with the 2026-09-20 capture, only one of the 17 rows in this section changed its substitute: gpt-image-1, which used to point to gpt-image-2. Note that as of 2026-10-08, QCode does not support gpt-6-luna or gpt-5.6-luna for now (both removed from /models); please use another GPT model, such as gpt-6.1-sol, gpt-6-sol or gpt-5.6-terra.
What happened
The section headed 2026-04-22: Legacy GPT model snapshots states “we are deprecating a set of older OpenAI models. Access to these models will be shut down on the dates below”, and all 17 rows in it carry October 23, 2026 - still the case in the copy fetched on 2026-10-07. 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 the 9 rows of this page are among them.
2026-10-07 re-fetch of the deprecation page: the 9 rows here still read October 23, 2026; the gpt-image-1 substitute changed from gpt-image-2 (2026-09-20 capture) to gpt-image-2.5-sunburst or gpt-image-2.5-flare.
2026-10-23, the shutdown day: the image row, the 5 reasoning rows, gpt-4.1-nano with its fine-tuning entry and gpt-4o-2024-05-13 stop together, each snapshot alongside its alias.
Confirmed vs caution
Officially confirmed
Only what the copy fetched on 2026-10-07 states word for word: the section title 2026-04-22: Legacy GPT model snapshots; the header Shutdown date / Model snapshot / Substitute model; October 23, 2026 on all 17 rows; the substitutes for the 9 rows above, including gpt-image-2.5-sunburst or gpt-image-2.5-flare on the gpt-image-1 row and reasoning.mode: pro in parentheses on the o1-pro row; 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 2026-10-07 copy holds no postponement wording. In the 2026-10-07 copy this section sits under the page's Past deprecations heading, but its text still says will be shut down and the date is still October 23, 2026; OpenAI gives no reason for the placement, so this page reads it neither as a shutdown that has happened nor as a postponement. Reading the section title 2026-04-22 as the announcement date is our inference. No QCode status is claimed for o1, o3-mini, o4-mini or the old gpt-image ids. gpt-4-1106-preview plus the remaining 4 fine-tuning rows are named, not expanded.
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 9 ids, snapshots and aliases together - the o1 cell holds o1-2024-12-17 and o1 side by side, one date for both. 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. The official substitute for gpt-4.1-nano is gpt-5.6-luna, but as of 2026-10-08 QCode does not support gpt-6-luna or gpt-5.6-luna for now (both removed from /models); 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 2026-10-07, 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 2026-10-08, QCode does not support gpt-6-luna or gpt-5.6-luna for now (both removed from /models); please use another GPT model, such as gpt-6.1-sol, gpt-6-sol or gpt-5.6-terra. This page states no QCode status for the image substitutes or the retired ids - check /models.
FAQ
My config just says o1, no snapshot - does it stop that day too?
Yes. That row carries the snapshot o1-2024-12-17 and the alias o1 in the same cell, with one date and one substitute. Same for o1-pro, o3-mini and o4-mini: pinning a snapshot buys you nothing.
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 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. Note that as of 2026-10-08 QCode does not support gpt-6-luna or gpt-5.6-luna for now (both removed from /models); on QCode, please use another GPT model instead, such as gpt-5.6-terra, gpt-6-sol or gpt-6.1-sol (our suggestion). gpt-4-turbo, gpt-3.5-turbo-0125 and gpt-4-0613 are written up on the other page.
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?
This page does not predict; /models is the reference. As of 2026-10-07 the reasoning substitutes gpt-5.6-sol and gpt-5.6-terra are callable on QCode. As of 2026-10-08, QCode does not support gpt-6-luna or gpt-5.6-luna for now (both removed from /models); please use another GPT model, such as gpt-6.1-sol, gpt-6-sol or gpt-5.6-terra. No promise is made that a retired id stays callable after its shutdown date.
Sources
OpenAI deprecations page https://developers.openai.com/api/docs/deprecations (and its .md version), fetched directly on 2026-10-07; 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 2026-10-07). 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 9 old ids out of config first
As of 2026-10-07, gpt-5.6-sol and gpt-5.6-terra are callable on QCode, billed per token, unit prices on /models. As of 2026-10-08, QCode does not support gpt-6-luna or gpt-5.6-luna for now (both removed from /models); please use another GPT model. A retired id staying callable is not promised here.
Related
gpt-4-turbo shutdown 2026-10-23
Where the chat rows of the same day are written up: gpt-4-turbo, gpt-3.5-turbo, gpt-4-0613.
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.
Not affiliated with OpenAI. Dates, model ids and substitutions are transcribed from the public deprecation page as fetched on 2026-10-07; 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.