# Image generation

AgentSky uses OpenAI gpt-image-2 to generate one image at high quality. Specify the subject, composition and exact wording, then choose a square, portrait or landscape size.

## Image generation

- ### Actual model

OpenAI gpt-image-2; high quality, one image per request, non-streaming.

- ### Available sizes

1024×1024 square (default), 1024×1536 portrait, or 1536×1024 landscape.

- ### Input and output

Provide a text prompt and size to receive a downloadable image. This tool creates new images; it does not accept an existing image or mask for editing.

# Pricing

## Tool usage

Tool charges use the same configured cost basis and 2× multiplier as billing. Model and runtime charges are separate.

Prices use the current configured reference cost.

- ### gptimage.generate

$0.422 per asset.

# Example tasks

## Put it to work

Choose an example and adapt its input and intended result to your task.

- ### Illustrate an article

Create a quiet editorial illustration about human–AI collaboration. Use a light background, a clear focal point, and no text.

- ### Create a portrait

Create a 1024×1536 portrait-format editorial illustration of a quiet reading room. Use natural lighting, strong perspective and no text.

# Common questions

### Which model actually creates the image?

### Can I choose size, quality and image count?

### Can I edit an uploaded reference image with this tool?

### What makes a useful image prompt?

### How should I check the generated result?

### Which image size should I choose for a portrait or banner?

### Can I request several alternatives in one call?

### Can I switch to a cheaper quality setting?

### How much does image generation cost?