gpt-image-1.5 deprecation: Dec 1, 2026 and Sume model ids
OpenAI removes gpt-image-1.5 and gpt-image-1-mini from its API on Dec 1, 2026. On Sume, send openai/gpt-image-2.5 and list ids with GET /v1/images/models.

OpenAI's deprecations page says gpt-image-1.5 and gpt-image-1-mini are removed from its API on December 1, 2026, with gpt-image-2.5-sunburst or gpt-image-2.5-flare as the recommended replacements. On Sume, the ChatGPT Image 2.5 ids are openai/gpt-image-2.5 (Flare) and openai/gpt-image-2.5-sunburst.
Vendor dates are from OpenAI's deprecations page; Sume ids from the Image API docs, both read 2026-09-30.
What exactly does OpenAI retire on December 1?
The page says OpenAI notified developers on June 2, 2026 about removing older GPT Image models. Three rows share the December 1, 2026 date.
| Model | Shutdown date | Recommended replacement |
|---|---|---|
| gpt-image-1-mini | Dec 1, 2026 | gpt-image-2.5-sunburst or gpt-image-2.5-flare |
| gpt-image-1.5 | Dec 1, 2026 | gpt-image-2.5-sunburst or gpt-image-2.5-flare |
| chatgpt-image-latest | Dec 1, 2026 | gpt-image-2.5-sunburst or gpt-image-2.5-flare |
Which Sume ids replace them?
The Image API page names two: openai/gpt-image-2.5 (Flare) and openai/gpt-image-2.5-sunburst. It does not list gpt-image-1.5 or gpt-image-1-mini, so there is no Sume id to keep using for them. The difference between the two 2.5 ids is covered in Flare vs Sunburst.
What happens if I send an id Sume does not know?
The generation code returns 404 with code model_not_found, the message "Unknown image model id.", and a catalog_url of /v1/images/models. Treat that as the signal to re-read the catalog rather than retrying.
How do I check my code before the shutdown?
Search your code and config for the retired ids, swap them for a catalog id, and read the catalog with GET /v1/images/models. Keep one setting for the model id so the next retirement is a one-line change.
const res = await fetch("https://api.sume.com/v1/images", {
method: "POST",
headers: {
Authorization: "Bearer " + process.env.SUME_API_KEY,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "openai/gpt-image-2.5",
prompt: "a product photo on a white table",
quality: "high",
}),
});
console.log(res.status);Does quality change when I move to 2.5?
The docs list quality: auto|low|medium|high|xhigh|max for 2.5, and an omitted quality defaults to high. Set it explicitly if your old calls relied on another default.
Sources
Related posts
More in Developers
- gpt-image-1 shuts down Oct 23, 2026: what to send on Sume
OpenAI lists gpt-image-1 as shutting down October 23, 2026. On Sume, call POST /v1/images with openai/gpt-image-2.5 or sunburst, or sume/auto. Migration steps.
- gpt-image-2-2026-04-21 on Sume: dated ids are not accepted
OpenAI's changelog names the snapshot gpt-image-2-2026-04-21. Sume documents catalog slugs and bare aliases: send openai/gpt-image-2 or check /v1/images/models.
- GPT Image 2.5 1080x1350: why the size fails and what to send
1080x1350 breaks GPT Image 2.5's multiple-of-16 size rule. 1080 is not a multiple of 16. 1088x1360 (exact 4:5) meets the listed rules. Per OpenAI and Sume docs.
- GPT Image 2.5 Batch API: not supported, so fan out jobs
OpenAI's model page lists Batch as unsupported for GPT Image 2.5. On Sume, submit many async or webhook jobs to /v1/images and collect the results.
Written by Sume