# GPT Image 1

> A deprecated OpenAI natively multimodal model that turns text and image input into images.

## Key facts

- Model author: OpenAI
- Input: $5.00 per 1M tokens (starting tier)
- Output: $40.00 per 1M tokens (starting tier)
- Cached input: $2.50 per 1M tokens
- Input modalities: image, text
- Output modalities: image
- Capabilities: vision
- Released: 2026-02-09
- Model IDs: `openai/gpt-image-1`
- Model page: https://www.realrelay.ai/model/openai/gpt-image-1

## Overview

GPT Image 1 is a natively multimodal language model from OpenAI. It accepts both text and image inputs and produces image outputs, so one model handles prompts, reference pictures and the images it returns. OpenAI lists it as deprecated, and it is billed by token.

It accepts text and image input and returns images.

## Capabilities

GPT Image 1 generates images from text prompts and can take image input alongside the prompt, so a reference picture can shape the result.

Because it is a natively multimodal language model, the same request can mix written instructions and pictures.

## Pricing

GPT Image 1 is priced from $5.00 per 1M input tokens and from $40.00 per 1M output tokens. Cached input reads are priced from $2.50 per 1M tokens. Pricing is token-based, and the rates shown are starting prices.

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

## Use cases

Use GPT Image 1 to turn a written description into a finished picture, such as an illustration, a product visual or a social media graphic.

Add a reference image to the request to guide style or content, for example a sketch to be rendered or a photo whose look should be echoed.

## FAQ

### What is GPT Image 1?

GPT Image 1 is a deprecated OpenAI natively multimodal model that accepts text and image inputs and produces image outputs.

### How much does GPT Image 1 cost?

GPT Image 1 is priced from $5.00 per 1M input tokens and from $40.00 per 1M output tokens. The rates shown are starting prices. Cached input reads are priced from $2.50 per 1M tokens.

### What inputs and outputs does GPT Image 1 support?

GPT Image 1 accepts text and image input and returns images.

### Does GPT Image 1 accept image input?

Yes. GPT Image 1 accepts both text and image inputs and produces image outputs.

### How do I call GPT Image 1 via the API?

Call GPT Image 1 through RealRelay's OpenAI-compatible API using the model ID openai/gpt-image-1.