openai/gpt-image-1 – Run with an API on Replicate

Official

openai / gpt-image-1

A multimodal image generation model that creates high-quality images. You need to bring your own verified OpenAI key to use this model.

Warm

Public
1.2K runs
$0.001 per image
Commercial use
Paper
License

Playground Examples README

Input

openai_api_key

*secret

Your OpenAI API key

prompt

*string

Shift + Return to add a new line

A text description of the desired image

aspect_ratio

string

The aspect ratio of the generated image

Default: "1:1"

input_images

file[]

Add multiple files

A list of images to use as input for the generation

number_of_images

integer

(minimum: 1, maximum: 10)

Number of images to generate (1-10)

Default: 1

quality

string

The quality of the generated image

Default: "auto"

background

string

Set whether the background is transparent or opaque or choose automatically

Default: "auto"

output_compression

integer

(minimum: 0, maximum: 100)

Compression level (0-100%)

Default: 90

output_format

string

Output format

Default: "webp"

moderation

string

Content moderation level

Default: "auto"

user_id

string

Shift + Return to add a new line

An optional unique identifier representing your end-user. This helps OpenAI monitor and detect abuse.

Run this model in Node.js with one line of code:

npx create-replicate --model=openai/gpt-image-1

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run openai/gpt-image-1 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const input = {
  prompt: "A beautiful landscape",
  quality: "auto",
  background: "auto",
  moderation: "auto",
  aspect_ratio: "3:2",
  output_format: "webp",
  number_of_images: 1,
  output_compression: 90
};

const output = await replicate.run("openai/gpt-image-1", { input });

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run openai/gpt-image-1 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "openai/gpt-image-1",
    input={
        "prompt": "A beautiful landscape",
        "quality": "auto",
        "background": "auto",
        "moderation": "auto",
        "aspect_ratio": "3:2",
        "output_format": "webp",
        "number_of_images": 1,
        "output_compression": 90
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run openai/gpt-image-1 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "input": {
      "prompt": "A beautiful landscape",
      "quality": "auto",
      "background": "auto",
      "moderation": "auto",
      "aspect_ratio": "3:2",
      "output_format": "webp",
      "number_of_images": 1,
      "output_compression": 90
    }
  }' \
  https://api.replicate.com/v1/models/openai/gpt-image-1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

Generated in

46.6 seconds

Input tokens

Output tokens

6.2K

Tokens per second

133.10 tokens / second

Tweak it ShareReport

Pricing

This model is priced by how many images are generated.

Type	Per unit	Per $1
Output	$0.001 / image or 1000 images / $1

For example, generating 100 images should cost around $0.10.

Check out our docs for more information about how per-image pricing works on Replicate.

Readme

GPT Image 1 is a new state-of-the-art image generation model. It is a natively multimodal language model that accepts both text and image inputs, and produces image outputs.

Capabilities

Creates images across diverse styles
Follows custom guidelines
Leverages world knowledge
Renders text accurately

Pricing

Usage is priced per token, with different rates for:

Text input tokens (prompt text): $5 per 1M tokens
Image input tokens (input images): $10 per 1M tokens
Image output tokens (generated images): $40 per 1M tokens

Safety Features

Same safety guardrails as image generation in ChatGPT
Safeguards against generating harmful images
C2PA metadata included in generated images
Moderation sensitivity control with the moderation parameter:
auto (default): standard filtering
low: less restrictive filtering

Data Usage

By default, OpenAI does not train on customer API data
All image inputs and outputs remain subject to API usage policies