4K image creation

GPT Image 2.5 API

OpenAI's newest image model — resolutions to 4K, five quality tiers, and transparent backgrounds.

GPT Image 2.5 is an image generation model from OpenAI, available on OttoPort's OpenAI-compatible API as the model ID gpt-image-2.5 at $0.026 / image as of 2026-10-14.

Provider

OpenAI

Price

$0.026 / image

Model ID

gpt-image-2.5

Type

image generation model

Hero imagesText-rich visuals4K campaign art

Create with GPT Image 2.5

image

Prompt

ExampleSelect to edit

Pricing

GPT Image 2.5 API pricing

What OttoPort bills for GPT Image 2.5, and what that works out to per unit. Rates are read from the same catalog the gateway meters against, and were current on 2026-10-14.

Per image	$0.026	at the model's base resolution
Images per $1	38
100 images	$2.60
Up to 1024px longest side	$0.026	1× the base rate
Up to 2048px longest side	$0.0533	2.05× the base rate
Up to 4096px longest side	$0.0871	3.35× the base rate

No subscription and no minimum — OttoPort bills prepaid credits against usage. See the full rate card.

Quickstart

Call GPT Image 2.5 in three lines

Send "model": "gpt-image-2.5" to POST https://ottoport.ai/api/v1/images/generations with an OttoPort key. No OpenAI account, no waitlist, no separate SDK.

curl https://ottoport.ai/api/v1/images/generations \
  -H "Authorization: Bearer $OTTOPORT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2.5",
    "prompt": "a chrome torus on a black background, studio light",
    "size": "1024x1024",
    "n": 1
  }'

from openai import OpenAI

client = OpenAI(api_key="op-...", base_url="https://ottoport.ai/api/v1")

resp = client.images.generate(
    model="gpt-image-2.5",
    prompt="a chrome torus on a black background, studio light",
    size="1024x1024",
    n=1,
)
print(resp.data[0].url)

import OpenAI from "openai";

const client = new OpenAI({ apiKey: "op-...", baseURL: "https://ottoport.ai/api/v1" });

const resp = await client.images.generate({
  model: "gpt-image-2.5",
  prompt: "a chrome torus on a black background, studio light",
  size: "1024x1024",
  n: 1,
});
console.log(resp.data[0].url);

Before you start

1. Create a key at /api-keys.
2. Top up credits — the smallest pack is $25.
3. Paste the request. It returns on the same request.

Full reference at /docs, or drive it from an agent with the MCP server and CLI.

Reference

Request parameters

The body POST https://ottoport.ai/api/v1/images/generations accepts for GPT Image 2.5.

Field	Type	Required	Notes
model	string	Yes	Always gpt-image-2.5 for GPT Image 2.5.
prompt	string	Yes	What to generate.
size	string	No	e.g. 1024x1024. Resolutions above the base tier bill at a multiplier. This model's sizes: 1024x768, 768x1024, 1024x1536, 1536x1024, 2048x2048, 2048x1152, 1152x2048, 2560x1088, 1088x2560, 2880x2160, 2160x2880, 3840x2160, 2160x3840.
resolution	string	No	One of: 1k, 2k, 4k. Tiers above this model's base rate bill at a multiplier.
aspect_ratio	string	No	e.g. 16:9. Read only when size is absent.
quality	string	No	How much compute to spend: low, medium, high, xhigh, max. Default medium. Each tier bills at its own multiplier.
n	integer	No	How many images to return. Each one bills separately.
image_url	string	No	A source image, for editing and reference-led generation.
image_urls	array	No	Several reference images at once, up to the model's limit — see its capabilities in /v1/models. Up to 16.

Comparison

GPT Image 2.5 direct vs through OttoPort

GPT Image 2.5 is the same model either way — what changes is how many accounts, keys, and integrations you carry to reach it.

	OpenAI direct	Via OttoPort
Accounts and keys	An OpenAI account, plus one more for every other model you add	One OttoPort account and one key for the whole catalog
Request shape	OpenAI's own SDK and response format	OpenAI-compatible — point baseURL at OttoPort and change the model string
Switching models	A new integration per provider	Replace gpt-image-2.5 with any other model ID in the catalog
Billing	A separate invoice and contract per provider	Prepaid credits, no subscription, one usage ledger
Provider outages	Your call fails	Configured backup routes are tried in order on provider failure

Put the hero subject first.

Describe composition and lighting.

Specify format and visual style.

FAQ

GPT Image 2.5 API questions

Cost, keys, and model IDs for GPT Image 2.5 on OttoPort.

How much does the GPT Image 2.5 API cost?

On OttoPort, GPT Image 2.5 costs $0.026 / image as of 2026-10-14. For scale, images per $1: 38. Billing is prepaid usage with no subscription and no minimum, and the current rate is always published at ottoport.ai/pricing.

How do I get a GPT Image 2.5 API key?

You do not need an OpenAI key. Create an OttoPort account, generate a key at ottoport.ai/api-keys, and send it as "Authorization: Bearer <key>" to POST https://ottoport.ai/api/v1/images/generations with "model": "gpt-image-2.5". The same key reaches every other model in the catalog.

What is the model ID for GPT Image 2.5?

The OttoPort model ID for GPT Image 2.5 is gpt-image-2.5. Pass it as the model field on POST https://ottoport.ai/api/v1/images/generations, or list it programmatically from GET https://ottoport.ai/api/v1/models.

Can I call GPT Image 2.5 with the OpenAI SDK?

Yes. Set the OpenAI SDK's base URL to https://ottoport.ai/api/v1, use an OttoPort API key, and pass gpt-image-2.5 as the model. Image generation follows the OpenAI images shape, so existing code works after changing two lines.

Do I need an OpenAI account to use GPT Image 2.5?

No. OttoPort connects to OpenAI on your behalf, so one OttoPort account covers GPT Image 2.5 and every other model in the catalog — no per-provider contracts, keys, or invoices.

Alternatives

Other image generation models on the same API

Same endpoint, same key — swapping model is a one-string change from gpt-image-2.5.

GPT Image 2.5 Flare API

OpenAI

$0.026 / image

GPT Image 2 API

OpenAI

$0.07 / image

Nano Banana 2 API

Google

$0.088 / image

Nano Banana 2 Lite API

Google

$0.044 / image

GPT Image 1.5 API

OpenAI

$0.044 / image

Qwen Image 3.0 Pro API

Qwen

$0.044 / image

Browse the full catalog — every model with its provider and per-unit price.