RealRelay.ai
OpenAI

GPT Image 1.5

A deprecated OpenAI image model with better instruction following and prompt adherence.

Starting at
Input
$5.00/ 1M
Output
$10.00/ 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-1.5
Input
$5.00 USD per 1M tokens
Output
$10.00 USD per 1M tokens
Cache read
$2.00 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-1.5

1from openai import OpenAI23client = OpenAI(4    base_url="https://www.realrelay.ai/v1",5    api_key="sk-***",6)78response = client.chat.completions.create(9    model="openai/gpt-image-1.5",10    messages=[{"role": "user", "content": "Hello"}],11)1213print(response.choices[0].message.content)
1import OpenAI from "openai";23const client = new OpenAI({4  baseURL: "https://www.realrelay.ai/v1",5  apiKey: process.env.REALRELAY_API_KEY,6});78const response = await client.chat.completions.create({9  model: "openai/gpt-image-1.5",10  messages: [{ role: "user", content: "Hello" }],11});1213console.log(response.choices[0].message.content);
1curl https://www.realrelay.ai/v1/chat/completions \2  -H "Authorization: Bearer $REALRELAY_API_KEY" \3  -H "Content-Type: application/json" \4  -d '{5    "model": "openai/gpt-image-1.5",6    "messages": [{ "role": "user", "content": "Hello" }]7  }'

Prices and availability as published on Oct 12, 2026.

Capabilities

GPT Image 1.5 creates images from text prompts and works with image input as a reference or an edit target. It supports inpainting for changes to part of a picture.

Its documented strength is following instructions closely, so detailed prompts with several requirements are more likely to be reflected in the result.

VisionText to imageImage to image
Input
TextImage
Output
TextImage

Overview

GPT Image 1.5 is an image generation model from OpenAI that OpenAI documents with better instruction following and closer adherence to prompts. It accepts text and image input, produces images, supports inpainting for edits to part of a picture and is billed by token. OpenAI lists it as deprecated.

It accepts text and image input and returns images and text. It was released on December 16, 2025.

Pricing

GPT Image 1.5 is priced from $5.00 per 1M input tokens and from $10.00 per 1M output tokens. Cached input reads are priced from $2.00 per 1M tokens. Pricing is token-based, and the rates shown are starting prices.

GPT Image 1.5 is available through RealRelay's OpenAI-compatible API.

Use cases

Use GPT Image 1.5 for prompt-driven image work where the brief has many specific requirements, such as a poster with a stated layout, colors and subjects, and check the result against each requirement.

With image input it can also edit an existing picture through inpainting, which suits touch-ups to product photos and design drafts.

Frequently asked questions

What is GPT Image 1.5?
GPT Image 1.5 is a deprecated OpenAI image model that accepts text and image input and is documented for better instruction following and prompt adherence.
How much does GPT Image 1.5 cost?
GPT Image 1.5 is priced from $5.00 per 1M input tokens and from $10.00 per 1M output tokens. The rates shown are starting prices. Cached input reads are priced from $2.00 per 1M tokens.
What inputs and outputs does GPT Image 1.5 support?
GPT Image 1.5 accepts text and image input and returns images and text.
Does GPT Image 1.5 support image editing?
Yes. GPT Image 1.5 accepts image input and supports inpainting, so it can edit part of an existing image.
When was GPT Image 1.5 released?
GPT Image 1.5 was released on December 16, 2025.
How do I call GPT Image 1.5 via the API?
Call GPT Image 1.5 through RealRelay's OpenAI-compatible API using the model ID openai/gpt-image-1.5.

More from OpenAI

All 42 OpenAI models