GPT Image 2 API
OpenAI image generation and editing model.
GPT Image 2 is an image generation model from OpenAI, available on OttoPort's OpenAI-compatible API as the model ID gpt-image-2 at $0.07 / image as of 2026-10-14.
Provider
OpenAI
Price
$0.07 / image
Model ID
gpt-image-2
Type
image generation model
Create with GPT Image 2
image
GPT Image 2 API pricing
What OttoPort bills for GPT Image 2, 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 | $0.07 | at the model's base resolution |
|---|---|---|
| Images per $1 | 14 | |
| 100 images | $7.00 | |
| Up to 1024px longest side | $0.07 | 1× the base rate |
| Up to 2048px longest side | $0.1435 | 2.05× the base rate |
| Up to 4096px longest side | $0.2345 | 3.35× the base rate |
No subscription and no minimum — OttoPort bills prepaid credits against usage. See the full rate card.
Call GPT Image 2 in three lines
Send "model": "gpt-image-2" 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",
"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",
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",
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.
Request parameters
The body POST https://ottoport.ai/api/v1/images/generations accepts for GPT Image 2.
| Field | Type | Required | Notes |
|---|---|---|---|
| model | string | Yes | Always gpt-image-2 for GPT Image 2. |
| 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: 1024x1024, 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. 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. |
GPT Image 2 direct vs through OttoPort
GPT Image 2 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 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.
GPT Image 2 API questions
Cost, keys, and model IDs for GPT Image 2 on OttoPort.
How much does the GPT Image 2 API cost?
On OttoPort, GPT Image 2 costs $0.07 / image as of 2026-10-14. For scale, images per $1: 14. 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 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". The same key reaches every other model in the catalog.
What is the model ID for GPT Image 2?
The OttoPort model ID for GPT Image 2 is gpt-image-2. 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 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 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?
No. OttoPort connects to OpenAI on your behalf, so one OttoPort account covers GPT Image 2 and every other model in the catalog — no per-provider contracts, keys, or invoices.
Other image generation models on the same API
Same endpoint, same key — swapping model is a one-string change from gpt-image-2.
GPT Image 2.5 Flare API
OpenAI
$0.026 / image
GPT Image 2.5 API
OpenAI
$0.026 / image
Nano Banana 2 API
$0.088 / image
Nano Banana 2 Lite API
$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.