ChatGPT Images 2.5 vs GPT-Image-2.5: which name is the API?
ChatGPT Images 2.5 is OpenAI's product; GPT-Image-2.5 Flare and Sunburst are the API models. How the names map to Sume ids and which features stay in ChatGPT.

They are two names for one model generation. On OpenAI's launch page, ChatGPT Images 2.5 is the product inside ChatGPT, and GPT-Image-2.5 Flare and GPT-Image-2.5 Sunburst are the two API models. If you are writing code against Sume, you call openai/gpt-image-2.5 (Flare) or openai/gpt-image-2.5-sunburst.
Sources: OpenAI's launch page and Sume's Image API docs, both read 2026-09-29.
How do the names map?
The Sume docs call the family "ChatGPT Image 2.5" and list the two ids below. They also say ChatGPT Image 2 remains selectable.
| Where you see it | Name | What it is |
|---|---|---|
| OpenAI launch page | ChatGPT Images 2.5 | The image feature in ChatGPT, ChatGPT Work and Codex |
| OpenAI launch page | GPT-Image-2.5 Flare | API model, described as the default choice for most applications |
| OpenAI launch page | GPT-Image-2.5 Sunburst | API model, described as built for premium visual workflows with longer generation times |
| Sume API | openai/gpt-image-2.5 | Flare |
| Sume API | openai/gpt-image-2.5-sunburst | Sunburst |
Which ChatGPT features are not in the API?
OpenAI lists Sketch, Templates, comments on images and shared prompts as product features introduced "in ChatGPT". They are described as things you do in the ChatGPT app, and Sume's Image API docs do not list any of them as request fields. What the API takes instead is a prompt, up to 16 reference images, an optional mask_url and a background value.
For the two API models and how to choose, see GPT Image 2.5 Flare vs Sunburst.
What does a call with the API name look like?
Use the Sume id as the model. Everything else is the normal image request.
curl -X POST "https://api.sume.com/v1/images" \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-image-2.5",
"prompt": "a matte black coffee grinder on a marble counter, soft window light"
}'Is the ChatGPT Images name searchable in the Sume catalog?
Read GET /v1/images/models for the live list of ids and their supported parameters. The ids are the source of truth, not the product names, so match on openai/gpt-image-2.5 and openai/gpt-image-2.5-sunburst rather than on any marketing label.
What does OpenAI say about safety on these models?
The launch page says Images 2.5 builds on existing safeguards, with checks on prompts and images, and that OpenAI continues to use C2PA metadata and invisible watermarking to help identify images made with its tools. Sume's docs are silent on that, so treat it as OpenAI's statement about its own tools.
Does the product name change my request?
No. The product name never appears in a request. The model field takes a Sume catalog id. If a teammate says "use ChatGPT Images 2.5", ask which of the two API models they mean: Flare is the one OpenAI calls the default choice for most applications, and OpenAI describes Sunburst as built for premium visual workflows that benefit from tighter control across edits.
Pricing and quality settings depend on the id and on quality, not on the name used in conversation. Prices are on the API pricing page rather than in this post.
Sources
Related posts
More in Models
- Does ChatGPT Images 2.5 add a watermark? C2PA explained
OpenAI says ChatGPT Images 2.5 uses C2PA metadata and invisible watermarking to identify its images. What that means for files you get through an API.
- Claude Sonnet 5.5 or Opus 5.5 for an agent that calls a video tool?
Sonnet 5.5 and Opus 5.5 differ in price and release date on Anthropic's pages. Which facts matter when the tool is Sume's video generation, and what stays same?
- How to colorize a black and white video with AI
Colorize a black and white video with an AI video-to-video edit: send the clip and a prompt naming the colors. The model invents them.
- ElevenLabs Eleven v4 API: what it is and how to reach it
Eleven v4 and v4 Turbo launched September 28, 2026 on ElevenLabs' own API. What ElevenLabs says they do, and which TTS ids Sume's router lists.
Written by Sume