GPT Image 2.5 via the Tokenator API

What the model is for

GPT Image 2.5 is an image generation and editing model from OpenAI, positioned as the precision-oriented tier of the GPT Image 2.5 series. It is suited to detailed creative work where editing accuracy matters more than generation speed, via the dedicated Images API.

Specification

Full nameGPT Image 2.5
API IDgpt-image-2.5
Model vendorOpenAI
TypeImage generation
Context window—
Max output—
Image inputyes
Tokenator usage multiplier1×
Input modalitiestext, image
Supported API formats/v1/images/generations /v1/images/edits
Upstream providers1
Current statusavailable
Data updated2026-09-09

Upstream providers

ProviderMultiplier
AiPartners Ltd1×

A request goes to the first available provider by priority; if it fails, Tokenator switches to the next one.

Example request

curl
curl https://api.tokenator.top/v1/images/generations \
  -H "Authorization: Bearer sk-your-tokenator-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2.5",
    "prompt": "an isometric illustration of a server rack",
    "n": 1
  }'

FAQ about GPT Image 2.5

What is the API ID of GPT Image 2.5?

gpt-image-2.5 — put this into the model field of your request.

What does a generation request look like?

POST to /v1/images/generations, /v1/images/edits with model, prompt and optionally n and size. The format matches the OpenAI Images API — only the base URL and the key change.

How do I set the image size?

With the size field, for example 1024x1024. The available set depends on the model; 2048x2048 is not supported everywhere, and even there the result sometimes comes back smaller — check the actual image.

What does one image cost?

Generations are taken from the key's image quota: one picture — 1×, and with n images per request it is n × the multiplier. See the documentation for details.

Can I edit an existing image?

Yes. Send the source image to /v1/images/edits together with a prompt describing the change, and the response carries a link to the edited picture. Both multipart uploads and base64 JSON are accepted.

What comes back in the response?

A data array where each item holds a link to the finished image in the url field. Download the picture and store it on your side — the link is not meant for permanent hosting.