GPT Image 2.5 request returned 202: how to get the image from the job
When GPT Image 2.5 takes longer than 30 seconds on Sume, POST /v1/images returns 202 with a job. Poll the status URL, then read the result, or use a webhook.

If a GPT Image 2.5 request on Sume returns 202 instead of 200, the image is still being made: the body is a job envelope with status_url and result_url, not the picture. Poll the status URL until the job is terminal, then fetch the result URL. Sume blocks for up to 30 seconds, and 4K, high quality and large n are the settings most likely to run past that.
OpenAI's guide says complex prompts may take up to 2 minutes, so a 202 is normal. Sume behavior from the Image API docs and Jobs and results, read 2026-09-29.
How do I tell the two responses apart?
Check the status code, not the body shape.
| Status | Body | Next step |
|---|---|---|
200 | Images in data[].url, with usage.cost | Use the URLs |
202 | Job envelope with status_url and result_url | Poll, then fetch the result |
How do I poll the job?
The result uses the standard job result shape, not the 200 image body.
curl "https://api.sume.com/v1/jobs/$JOB_ID/status" \
-H "Authorization: Bearer $SUME_API_KEY"
curl "https://api.sume.com/v1/jobs/$JOB_ID/result" \
-H "Authorization: Bearer $SUME_API_KEY"Can I skip the wait entirely?
Yes. Send mode: "async" to get the job envelope at once, or mode: "webhook" with a public HTTPS webhook_url to receive the terminal event. mode: "subscribe" is not a progress stream; it is an alias of sync. wait_timeout_seconds takes 0 to 30.
Sources
Related posts
More in Developers
- GPT Image mask edit API: how to use mask_url on GPT Image 2.5
GPT Image 2.5 on Sume takes an optional mask_url for edits. OpenAI says the mask needs an alpha channel and only guides the edit. The request and the limits.
- GPT Image 2.5 multi-round edits: chain edits on one image via API
To make several edits to one picture with GPT Image 2.5, feed each result back as a reference. What fal says Sunburst preserves, and what to check each round.
- GPT Image 2.5: how many images can I generate per request?
On Sume, GPT Image 2.5 takes n from 1 to 4 images per request, billed per image. How to ask for several versions and what a 202 means for a larger n.
- GPT Image 2.5 API: OpenAI's two endpoints versus Sume's one route
OpenAI serves GPT Image 2.5 on images/generations and images/edits. On Sume both become POST /v1/images. How the fields map and what returns instead of base64.
Written by Sume