RealRelay.ai
OpenAI

GPT Image 1 mini

A deprecated, cost-efficient OpenAI image model that turns text and image input into images.

Starting at
Input
$2.00/ 1M
Output
$8.00/ 1M
Open dashboard

Channel

Each channel is compared at its lowest input-price tier; output breaks ties. A dash means /api/pricing does not provide that rate. Selecting a channel updates the endpoints and call example below.

openai/gpt-image-1-mini
Input
$2.00 USD per 1M tokens
Output
$8.00 USD per 1M tokens
Cache read
$0.25 USD per 1M tokens
Cache write
- USD per 1M tokens

Endpoints

POST/v1/images/generationsImage generation
POST/v1/chat/completionsChat Completions

Call it

Using openai/gpt-image-1-mini

1from openai import OpenAI23client = OpenAI(4    base_url="https://www.realrelay.ai/v1",5    api_key="sk-***",6)78image = client.images.generate(9    model="openai/gpt-image-1-mini",10    prompt="A quiet reading room at golden hour",11)1213print(image.data[0].url)
1import OpenAI from "openai";23const client = new OpenAI({4  baseURL: "https://www.realrelay.ai/v1",5  apiKey: process.env.REALRELAY_API_KEY,6});78const image = await client.images.generate({9  model: "openai/gpt-image-1-mini",10  prompt: "A quiet reading room at golden hour",11});1213console.log(image.data[0].url);
1curl https://www.realrelay.ai/v1/images/generations \2  -H "Authorization: Bearer $REALRELAY_API_KEY" \3  -H "Content-Type: application/json" \4  -d '{5    "model": "openai/gpt-image-1-mini",6    "prompt": "A quiet reading room at golden hour"7  }'

Prices and availability as published on Oct 12, 2026.

Capabilities

GPT Image 1 mini generates images from text prompts and can take image input alongside the prompt as a reference.

As a natively multimodal language model, it handles written instructions and pictures in the same request, and its documented focus is lower cost per image job.

VisionText to imageImage to image
Input
TextImage
Output
Image

Overview

GPT Image 1 mini is a cost-efficient image model from OpenAI. It is a natively multimodal language model that accepts both text and image inputs and produces image outputs, with token-based pricing aimed at lighter image workloads. OpenAI lists it as deprecated.

It accepts text and image input and returns images. It was released on October 6, 2025.

Pricing

GPT Image 1 mini is priced from $2.00 per 1M input tokens and from $8.00 per 1M output tokens. Cached input reads are priced from $0.25 per 1M tokens. Pricing is token-based, and the rates shown are starting prices.

GPT Image 1 mini is available through RealRelay's OpenAI-compatible API.

Use cases

Use GPT Image 1 mini for image generation where cost matters, such as thumbnails, placeholder art, simple illustrations or many variations of a layout.

Add a reference image to guide a result, for instance a rough sketch or a photo whose composition should be kept, and rerun the prompt as often as the project needs.

Frequently asked questions

What is GPT Image 1 mini?
GPT Image 1 mini is a deprecated, cost-efficient OpenAI image model that accepts text and image inputs and produces image outputs.
How much does GPT Image 1 mini cost?
GPT Image 1 mini is priced from $2.00 per 1M input tokens and from $8.00 per 1M output tokens. The rates shown are starting prices. Cached input reads are priced from $0.25 per 1M tokens.
What inputs and outputs does GPT Image 1 mini support?
GPT Image 1 mini accepts text and image input and returns images.
What makes GPT Image 1 mini cost-efficient?
OpenAI describes GPT Image 1 mini as a cost-efficient image model. It takes text and image inputs, produces images and is billed by token.
When was GPT Image 1 mini released?
GPT Image 1 mini was released on October 6, 2025.
How do I call GPT Image 1 mini via the API?
Call GPT Image 1 mini through RealRelay's OpenAI-compatible API using the model ID openai/gpt-image-1-mini.

More from OpenAI

All 42 OpenAI models