GPT: gpt-image-2

gpt-image-2

GPT Image 2 is an OpenAI model for high-fidelity image generation and editing through the dedicated Images API. It supports text-to-image generation and image-to-image editing.

text → image → image

Modalities

In / Out Price

40% off

$3/ 1M

$5 Official price

$0/ 1M

$0 Official price

400K

Context

Jun 23, 2026

Released

Providers

This model is hosted by one provider. Requests are forwarded to it directly, with no routing decisions to make.

Provider	Input /M	Output /M	Context	Latency	Throughput	Uptime
OpenAI	$340% off $5 Official price	$0 $0 Official price	400K	—	—	—

Call this model in three steps.

Get your API key

Create a key and set your API key and base URL as environment variables.

Create API Key

Environment

export UNIROUTER_API_KEY="<YOUR_API_KEY>"
export UNIROUTER_BASE_URL="https://api.tokatlas.com/v1"

Choose a request format

Choose the format supported by your selected route.

Make your first request

Model ID: gpt-image-2

from openai import OpenAI

client = OpenAI(
    base_url="https://api.tokatlas.com/v1",
    api_key="<YOUR_API_KEY>",
)
response = client.images.generate(**{
    "model": "gpt-image-2",
    "prompt": "A serene koi pond at sunset.",
    "size": "1024x1024",
    "n": 1
})

print(response)

Endpoint

Creates a model response for the given chat conversation.

POST: https://api.tokatlas.com/v1/images/generations
Authorization: Bearer $UNIROUTER_API_KEY
Content-Type: application/json