Seedream 5.5 is live on Atlas Cloud — native transparent PNG & 80+ round editing
Início
Explorar
OpenAI
GPT Image 2.5
openai/gpt-image-2.5-sunburst-developer/edit
GPT Image 2.5 Sunburst Developer Edit
Imagem para Imagem
DEV

GPT Image 2.5 Sunburst Developer Edit API by OpenAI

openai/gpt-image-2.5-sunburst-developer/edit
Edit

GPT Image 2.5 Sunburst Developer Edit applies natural-language instructions to reference images at a flat per-image price by 1K / 2K / 4K resolution tier, with no token accounting to reason about. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Comparar modelos

GPT Image 2.5 Sunburst Developer Edit foi desenvolvido pela OpenAI. A Atlas Cloud (operada pela Atlas Cloud AI LLC) fornece acesso ao modelo, mas não é sua proprietária. Todas as marcas registradas pertencem aos seus respectivos titulares.

GPT Image 2.5 Sunburst Developer Edit

GPT Image 2.5 Sunburst Developer is the developer edition of GPT Image 2.5 Sunburst, OpenAI's upgraded GPT Image generation model, reached through the OpenAI Images API. It exposes the same parameters, limits and output quality as the standard edition under its own model id. Generation is asynchronous: submit the request, then poll for the final image URL.

Highlights

  • Up to 16 reference images in a single request.
  • Arbitrary resolutions up to 3840x2160, and fully supported transparent backgrounds.
  • Long prompts: up to 32000 characters.

Parameters

ParameterRequiredDescription
modelYesopenai/gpt-image-2.5-sunburst-developer/edit
imagesYesUp to 16 source images. Each entry is a URL, Base64 data, or an asset reference (asset://<ASSET_ID>).
promptYesInstruction describing the desired edit. Up to 32000 characters.
sizeNoOutput size as WIDTHxHEIGHT (for example 1536x864) or auto. Defaults to 1024x1024. The only control over output dimensions.
backgroundNoauto, opaque, or transparent. transparent forces a png or webp output format.
output_formatNopng, jpeg, or webp. Defaults to png.
nNoNumber of images to generate, 1 to 10. Defaults to 1. Each image is billed separately.

How To Use

curl -X POST "https://api.atlascloud.ai/api/v1/model/generateImage" \ -H "Authorization: Bearer $AIP_API_KEY" \ -H "Content-Type: application/json" \ --data-raw '{ "model": "openai/gpt-image-2.5-sunburst-developer/edit", "images": [ "https://static.atlascloud.ai/media/images/example-a.png", "https://static.atlascloud.ai/media/images/example-b.png" ], "prompt": "Arrange these products into a lovely gift basket on a marble counter.", "size": "1536x1024" }'

Size

size is the only control over output dimensions. gpt-image-2.5 accepts arbitrary resolutions, subject to:

  • both edges at least 256 px, floored to a multiple of 16
  • each edge at most 3840 px, and at most 3840x2160 in total
  • aspect ratio between 1:3 and 3:1

Resolutions above 2560x1440 are experimental upstream. auto lets the model choose, and is billed at the auto ceiling then settled down against the image actually produced.

Notes

  • Generation is asynchronous. Submit the request, then poll /api/v1/model/prediction/{request_id} for the final image URL.
  • Pricing is per token, at OpenAI's list rates: image tokens 8.00/1Minand8.00/1M in and 30.00/1M out, text input 5.00/1M(cachedinput5.00/1M (cached input 2.00/1M and $1.25/1M respectively). The request is charged from the token usage the model actually reports, so the amount held at submit is an upper bound and the difference is refunded.
  • This is the Developer edition. The request format, parameter set and limits are identical to openai/gpt-image-2.5-sunburst/edit; only the model id differs.
  • Streaming (stream, partial_images) and response_format are not supported — the API always returns finished images re-hosted on AtlasCloud storage.
  • Source images are fetched and uploaded to the upstream API as multipart files, so URLs, Base64 payloads and asset:// references are all accepted.

Explorar Modelos Semelhantes

Uma API para toda a IA de mídia.

Explorar Todos os Modelos