GPT-Image-1

Bot Information

Creator: @openai

Description: OpenAI's model that powers image generation in ChatGPT, offering exceptional prompt adherence, level of detail, and quality. It supports editing, restyling, and combining images attached to the latest user query. For a conversational editing experience, use https://poe.com/GPT-4o (all users) or https://poe.com/Assistant (subscribers) instead.

Optional parameters: * --aspect (options: 1:1, 3:2, 2:3): Aspect ratio of the output image * --quality (options: high, medium, low): Image resolution * --use_mask: Indicates that the last attached image is a mask for inpainting (editing specific regions). The mask must match the dimensions of the base image, with transparent (zero-alpha) areas showing which parts to edit.

Extra: Powered by a server managed by @openai. Learn more

Architecture

Input Modalities: text

Output Modalities: image

Modality: text->image

Pricing

| Type | Cost |

|------|------|

| Input Text | 151 points/1k tokens |

| Initial Points Cost | Variable points |

| Input (Images) | 301 points/1k tokens |

| High Fidelity Editing | 2000 points |

| Output (Image) | Based on output image quality and resolution (see table below) |

Last Checked: 2025-08-05 23:23:34.836895

Technical Details

Model ID: GPT-Image-1

Object Type: model

Created: 1743434309185

Owned By: poe

Root: GPT-Image-1