gpt-image-2 or openai/gpt-image-2? Model ids on Sume's Image API
Sume accepts bare Image Router ids such as gpt-image-2 and nano-banana-2 as aliases for openai/gpt-image-2 style ids. The catalog lists org/slug ids.

Sume accepts the bare Image Router ids (gpt-image-2, nano-banana-2) as aliases for their org/slug equivalents, such as openai/gpt-image-2. The catalog at GET /v1/images/models lists the org/slug ids.
From Sume's Image API docs, read 2026-09-30.
What does the response echo?
The response model echoes the id you requested, and sume/auto stays sume/auto. Sume does not disclose which family Auto ran, and Auto is not listed in GET /v1/images/models.
| Form | Example | Status |
|---|---|---|
| Catalog id | openai/gpt-image-2 | Catalog form |
| Bare legacy id | gpt-image-2 | Accepted alias |
| Auto | sume/auto | Sume-only value, not in the catalog list |
Which ids exist for GPT Image?
ChatGPT Image 2.5 is openai/gpt-image-2.5 (Flare) and openai/gpt-image-2.5-sunburst; ChatGPT Image 2 remains selectable. Pull the live list rather than hardcoding.
curl "https://api.sume.com/v1/images/models" \
-H "Authorization: Bearer $SUME_API_KEY"Why prefer org/slug?
The catalog id is the one that appears in model records and endpoint URLs, for example /v1/images/models/bytedance-seed/seedream-4.5/endpoints. This post is a suggestion to use it; the docs do not say the aliases will be removed.
What if the id is wrong?
Check the id spelling against the catalog list. Provider slugs other than sume return 400 provider_not_available.
How do I check this myself?
A one-line change in your config, from a bare id to the org/slug form, is enough. Keep the id in one constant so a future model swap touches a single place. The linked docs pages and the catalog endpoint show the current values, and this post reflects them as of 2026-09-30.
Sources
Related posts
More in Models
- Kling 2.1 API sunset: 410 Gone, and the kling-3 id on Sume
Krea retired Kling 1.0 through 2.1: endpoints return 410 Gone after Sep 15, 2026. Sume lists kling-3 in its video catalog; here is what to change.
- Kling 4.0 30 seconds: Sume lists kling-3 at 4 to 15
Kling 4.0 announces 3 to 30 second generation. Sume lists kling-3 at 4 to 15 seconds; seedance-2.5 and wan-3.0 are the ids that reach 30 seconds.
- Kling 4.0 prompt length: 8,000 tokens vs Omni's 20,000 characters
Kling 4.0 allows prompts up to 8,000 tokens. Sume documents a 20,000-character prompt cap for gemini-omni-flash-1.1; tokens and characters differ.
- Kling 4.0 video editing: five video inputs, Sume edits one
Kling 4.0 editing takes up to five video inputs. Sume's Omni edit route takes one video_url and cannot combine it with references.
Written by Sume