Which image ids shut down on December 1, 2026?
The dataset lists chatgpt-image-latest, gpt-image-1-mini, gpt-image-1.5, gpt-image-1.5-2025-12-16 with shutdown date 2026-12-01. gpt-image-1 is not in that list. Its shutdown date is 2026-10-23.
The dataset has 4 OpenAI image ids with shutdown date 2026-12-01: chatgpt-image-latest, gpt-image-1-mini, gpt-image-1.5, gpt-image-1.5-2025-12-16. OpenAI's deprecations page lists those ids for removal on December 1, 2026, and names gpt-image-2.6-sunburst or gpt-image-2.6-flare. It does not prefer one. The same page says: "At the time of the shut down, the model or endpoint will no longer be accessible." gpt-image-1 is not in this table. That id shut down on 2026-10-23.
Last reviewed . Publisher: SunsetDiff.
These rows are every OpenAI model in the dataset with shutdown date 2026-12-01. The model id links to its SunsetDiff model page. Deprecation date, shutdown date, and replacement are the fields stored on that row. Not published means the field is empty.
OpenAI's deprecations page says: "On June 2, 2026, we notified developers using older GPT Image models of their deprecation and removal from the API on December 1, 2026." The December 1 table on that page lists gpt-image-1-mini, then gpt-image-1.5 with snapshot gpt-image-1.5-2025-12-16, then chatgpt-image-latest. Each replacement cell says gpt-image-2.6-sunburst or gpt-image-2.6-flare. The word or means either id. The page does not prefer one.
gpt-image-1 is on the October 23, 2026 row of the same page. That row names gpt-image-2.5-sunburst or gpt-image-2.5-flare. Its stored shutdown date is 2026-10-23. It is not in the table below.
OpenRouter is also expiring image slugs. The OpenRouter models API sets expiration_date, and SunsetDiff stores that day as not_before. openai/gpt-5-image-mini (not before December 1, 2026) and openai/gpt-image-1-mini (not before December 1, 2026). The stored replacement list on those rows is empty, so this page does not name one. Those slugs are OpenRouter ids, not the OpenAI ids in the table above. See /shutdowns/openrouter-2026-12-01/. See the OpenRouter model expirations in November and December 2026.
| Model id | Deprecation date | Shutdown date | Recommended replacement |
|---|---|---|---|
| chatgpt-image-latest | Not published | 2026-12-01 | gpt-image-2.6-sunburst, gpt-image-2.6-flare |
| gpt-image-1-mini | Not published | 2026-12-01 | gpt-image-2.6-sunburst, gpt-image-2.6-flare |
| gpt-image-1.5 | Not published | 2026-12-01 | gpt-image-2.6-sunburst, gpt-image-2.6-flare |
| gpt-image-1.5-2025-12-16 | Not published | 2026-12-01 | gpt-image-2.6-sunburst, gpt-image-2.6-flare |
Sources: OpenAI deprecations , OpenRouter models API , checked November 12, 2026.
On December 1, 2026 these ids reach the shutdown date stored in the dataset. OpenAI's deprecations page says: "At the time of the shut down, the model or endpoint will no longer be accessible." The same page uses sunset and shut down for that moment. It does not print an HTTP status for it.
A 400 from a field the replacement rejects is a different failure. Those sentences are on the request errors pages. This guide does not invent an error body.
Source: OpenAI deprecations , checked November 12, 2026.
Search the repository for the ids in the table. A short id and its dated snapshot can sit in different files. gpt-image-1 is a different string and a different date. How to find every model ID in your codebase covers SDK argument names. The scan page builds a search from dataset ids that have a shutdown date.
OpenAI's deprecations page says to call the List models endpoint, GET /v1/models, and read each model's optional shutdown_date field. When present, the field is a YYYY-MM-DD string, or null if no shutdown date has been announced. The same field is on the Retrieve a model endpoint.
You can also read one id from the free SunsetDiff lookup file. gpt-image-1.5 is one of these rows. The API page lists the other files. No key and no signup. The alerts page is the free email form. That page says what the form stores and the one welcome email it can send.
rg -n -w -e 'chatgpt-image-latest' -e 'gpt-image-1-mini' -e 'gpt-image-1.5' -e 'gpt-image-1.5-2025-12-16'
Source: OpenAI deprecations , checked November 12, 2026.
The image generation page says: "Choose Sunburst for workflows where editing precision matters most, and Flare for fast, high-quality everyday image generation." And: "With the Image API, set model to gpt-image-2.5-sunburst or gpt-image-2.5-flare directly. With the Responses API, select a supported mainline model at the top level and specify gpt-image-2.5-sunburst or gpt-image-2.5-flare in the image generation tool's model field."
The gpt-image-2.6-sunburst model page lists v1/images/generations and v1/images/edits as supported, and lists v1/responses as not supported. Put gpt-image-2.6-sunburst or gpt-image-2.6-flare in the image tool's model field. Do not set the top-level Responses model to either image id.
The image generation page says: "gpt-image-2.5-sunburst and gpt-image-2.5-flare add xhigh and max quality settings. Both default to auto. Earlier GPT Image models support quality settings up to high." The same page says: "For GPT Image 2.6 and 2.5 Sunburst and Flare, the quality options are low, medium, high, xhigh, and max." A request that already sends high can keep high. xhigh and max are the settings the earlier models do not have.
The image generation page says: "Both models also support custom dimensions as WIDTHxHEIGHT strings, such as 1536x864. Width and height must be multiples of 16, the aspect ratio must be between 1:3 and 3:1, and neither edge may exceed 3840 pixels. The total pixel count must be between 655,360 and 8,294,400 (4K). Resolutions above 2560x1440 are experimental." Those size rules are in the section for gpt-image-2.5-sunburst and gpt-image-2.5-flare.
The same page says: "The Images API user parameter is deprecated. Send the same identifier as safety_identifier instead. Existing requests using user remain supported."
The image generation page's Python sample calls client.images.generate with model gpt-image-2.5-sunburst. The page also names gpt-image-2.5-flare for that same field. The deprecations page names gpt-image-2.6-sunburst or gpt-image-2.6-flare for the ids in the table. Send one prompt you use now, to the id you will keep, before the shutdown date.
result = client.images.generate(model="gpt-image-2.5-sunburst", prompt=prompt)
Sources: OpenAI image generation , gpt-image-2.6-sunburst , OpenAI deprecations , checked November 12, 2026.
OpenAI's deprecations page says the notice period is time to evaluate the recommended replacement, test application behavior, and finish the migration before the model is no longer available. Call gpt-image-2.6-sunburst or gpt-image-2.6-flare with a prompt you send today. Do that before December 1, 2026.
The pre-migration test checklist is the longer list: evals, rejected fields, token limits, tools, price, and latency.
Sources: OpenAI deprecations , OpenAI image generation , checked November 12, 2026.
The dataset lists chatgpt-image-latest, gpt-image-1-mini, gpt-image-1.5, gpt-image-1.5-2025-12-16 with shutdown date 2026-12-01. gpt-image-1 is not in that list. Its shutdown date is 2026-10-23.
OpenAI's deprecations page names gpt-image-2.6-sunburst or gpt-image-2.6-flare for each of these ids. It does not prefer one. The image generation page says: "Choose Sunburst for workflows where editing precision matters most, and Flare for fast, high-quality everyday image generation." The recommended replacement is the official replacement stored on each row. chatgpt-image-latest: gpt-image-2.6-sunburst, gpt-image-2.6-flare. gpt-image-1-mini: gpt-image-2.6-sunburst, gpt-image-2.6-flare. gpt-image-1.5: gpt-image-2.6-sunburst, gpt-image-2.6-flare. gpt-image-1.5-2025-12-16: gpt-image-2.6-sunburst, gpt-image-2.6-flare.
OpenAI's deprecations page says: "At the time of the shut down, the model or endpoint will no longer be accessible." That page does not print an HTTP status for that moment.
The image generation page says: "With the Image API, set model to gpt-image-2.5-sunburst or gpt-image-2.5-flare directly. With the Responses API, select a supported mainline model at the top level and specify gpt-image-2.5-sunburst or gpt-image-2.5-flare in the image generation tool's model field." The gpt-image-2.6-sunburst model page lists v1/images/generations and v1/images/edits as supported, and v1/responses as not supported. The deprecations page names gpt-image-2.6-sunburst or gpt-image-2.6-flare for these ids. Keep a mainline model at the top of a Responses request and put the image id in the tool.
The image generation page says: "gpt-image-2.5-sunburst and gpt-image-2.5-flare add xhigh and max quality settings. Both default to auto. Earlier GPT Image models support quality settings up to high." The same page says: "Both models also support custom dimensions as WIDTHxHEIGHT strings, such as 1536x864. Width and height must be multiples of 16, the aspect ratio must be between 1:3 and 3:1, and neither edge may exceed 3840 pixels. The total pixel count must be between 655,360 and 8,294,400 (4K). Resolutions above 2560x1440 are experimental."
OpenRouter is also expiring image slugs. The OpenRouter models API sets expiration_date, and SunsetDiff stores that day as not_before. openai/gpt-5-image-mini (not before December 1, 2026) and openai/gpt-image-1-mini (not before December 1, 2026). The stored replacement list on those rows is empty, so this page does not name one. Those slugs are OpenRouter ids, not the OpenAI ids in the table above. See /shutdowns/openrouter-2026-12-01/. See the OpenRouter model expirations in November and December 2026.