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