GPT-Image-1
OpenAI · GPT Image
Deprecated earlier GPT Image route retained for compatibility with older OpenAI image integrations.
Overview
Freshness note: Model capabilities, limits, and pricing can change quickly. This profile is a point-in-time snapshot last verified on June 8, 2026.
GPT-Image-1 is now a deprecated earlier image-generation route in OpenAI’s GPT Image family. It remains useful for understanding older integrations, but new image workflows should start with GPT Image 2 or the lower-cost gpt-image-1-mini tier depending on quality and budget.
Capabilities
The model supports text-to-image style generation and iterative image refinement patterns. Its practical value today is compatibility: teams with older prompts or applications can use this page to compare behavior and cost against newer GPT Image routes.
Technical Details
Token-centric context/output fields are not directly meaningful for this image model. In this repository, contextWindow and maxOutput are set to 0 intentionally and should be interpreted as N/A for token displays.
Pricing & Access
GPT-Image-1 is exposed through OpenAI API model surfaces for existing users, but OpenAI’s current docs mark it deprecated. OpenAI’s current pricing page lists text-prompt input at 10.00 per 1M tokens, and image output at $40.00 per 1M tokens. OpenAI also frames practical image costs by model, size, and quality, so teams should model real generation settings before comparing routes.
Best Use Cases
Use GPT-Image-1 only for older image ideation services, creative tooling prototypes, marketing workflows, or product experiences that already depend on this route. Do not choose it as the default for a fresh build.
Comparisons
Compared with GPT Image 2, GPT-Image-1 is a deprecated compatibility route. Compared with gpt-image-1-mini, it is usually harder to justify for high-volume work. Compared with Imagen 4, provider ecosystem and output style still matter, but fresh OpenAI image work should not start here.