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. Your OpenAI account will be charged for usage.

  • Public
  • 52.3K runs
  • Paper
  • License
Iterate in playground

Pricing

Official model
Pricing for official models works differently from other models. Instead of being billed by time, you’re billed by input and output, making pricing more predictable.

This model is priced by how many images are generated.

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

This is a bring-your-own-token model. You need to bring your own verified OpenAI key to use this model. Your OpenAI account will be charged for usage based on the following pricing.

See OpenAI’s pricing for details.

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