OpenAI organization verification for GPT Image 2.5 and Sume ids
OpenAI says you may need API Organization Verification before using GPT Image models. Sume lists the same two models as openai/gpt-image-2.5 and -sunburst.

Yes, possibly: OpenAI's image guide says you "may need to complete the API Organization Verification" in your developer console before using GPT Image models, including gpt-image-2.5-sunburst and gpt-image-2.5-flare. On Sume you call the same two models as openai/gpt-image-2.5-sunburst and openai/gpt-image-2.5 with a Sume API key.
The OpenAI statement is from its image generation guide, read 2026-10-01. The Sume docs read do not describe any OpenAI verification step for Sume callers, and this post does not claim one either way beyond what the docs say.
What does OpenAI say about the two models?
The guide says to choose Sunburst for workflows where editing precision matters most, and Flare for fast, high-quality everyday generation. In the Image API you set model to either id directly; in the Responses API you name it in the image generation tool's model field.
What are the ids on Sume?
The image docs say ChatGPT Image 2.5 is available as openai/gpt-image-2.5 (Flare) and openai/gpt-image-2.5-sunburst. Both support text-to-image, up to 16 image references, an optional mask_url, and background: auto|transparent|opaque. You can list what is available with GET /v1/images/models. See also Flare vs Sunburst.
| Model | OpenAI id | Sume id |
|---|---|---|
| Flare | gpt-image-2.5-flare | openai/gpt-image-2.5 |
| Sunburst | gpt-image-2.5-sunburst | openai/gpt-image-2.5-sunburst |
What error do I see if I run out of balance?
Sume's error table lists 402 insufficient_credits: "Balance is not sufficient for the requested generation." Check the ledger with GET /v1/balance before a large batch (errors and credits).
Sources
Related posts
More in Models
- Pika Camera Director vs a prompted video edit on Sume
Pika Camera Director reshoots a scene from new angles. On Sume, Omni Flash 1.1 edits a clip from a video_url and a prompt; there is no camera-angle parameter.
- Invisible models in Pika vs Sume Auto echoing sume/auto
Pika hides model names unless you ask. Sume's model sume/auto also hides the family and echoes sume/auto; pin a catalog id when you need a known model.
- Pika Soundtrack: video in, sound out. What Sume has instead
Pika Soundtrack scores a finished video. Sume's docs offer generate_audio at video creation and a Timeline soundtrack bed, but no video-to-sound endpoint.
- 30-second video with sound: Pika Video Studio vs Sume ids
Pika Video Studio makes up to 30 seconds with sound. On Sume, seedance-2.5 and wan-3.0 reach 30 seconds; every other catalog model stops at 15.
Written by Sume