GPT Image 2.5 reference images: how many you can send and how to use
GPT Image 2.5 on Sume accepts up to 16 reference images per request, six more than GPT Image 2. How to label each image's job in the prompt and what to check.

GPT Image 2.5 on Sume accepts up to 16 reference images per request, in input_references; ChatGPT Image 2 accepts up to 10. Every URL must be public HTTPS. OpenAI's guide states no maximum for its own edit endpoint and shows examples with several images, so 16 is Sume's catalog limit.
Limits from Sume's Image API docs, read 2026-09-29.
How do I say what each image is for?
Refer to images by order and role: "image 1 is the model, image 2 is the jacket, image 3 is the background". Without roles, the model has to guess which image supplies the subject and which supplies the style.
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": "Image 1 is the person, image 2 is the jacket. Dress the person in the jacket. Keep the pose and background of image 1.",
"input_references": [
{ "type": "image_url", "image_url": { "url": "https://example.com/person.jpg" } },
{ "type": "image_url", "image_url": { "url": "https://example.com/jacket.jpg" } }
],
"aspect_ratio": "auto"
}'Do more references cost more?
Yes: the input image tokens are estimated per reference and added to the output cost, at $8 per million image input tokens per OpenAI's model page. Send only the images the result needs.
What are the limits?
| Item | Limit |
|---|---|
| References, 2.5 ids | 0 to 16 |
| References, ChatGPT Image 2 | 0 to 10 |
| URL rule | Public HTTPS; localhost, private-network and non-HTTPS URLs are rejected |
| Aspect ratio on edits | Prefer auto |
Sources
Related posts
More in Developers
- GPT Image 2.5 transparent background: how to request a cutout by API
GPT Image 2.5 on Sume accepts background transparent. OpenAI says transparency needs png or webp output. The request, the catch, and when to use another route.
- GPT Image 2.5 400 unsupported_parameter: fields each model accepts
A 400 unsupported_parameter from Sume's image API means the model does not list that field. Which GPT Image ids accept quality, mask_url and background.
- Grok 4.7 remote MCP tool: connect Sume to the xAI Responses API
xAI's remote MCP tool works with grok-4.7 on the Responses API. Point server_url at Sume's hosted MCP, restrict allowed_tools, and cap spend on the Sume side.
- HeyGen API avatar ID and voice ID: where to find them
In HeyGen's v3 API, avatar_id is a look id from GET /v3/avatars/looks, and voice_id comes from GET /v3/voices or the look's default voice.
Written by Sume