GPT Image 2.5 Flare and Sunburst now available on AI Gateway

OpenAI’s GPT Image 2.5 Flare and GPT Image 2.5 Sunburst models are now available on Vercel’s AI Gateway under the identifiers openai/gpt-image-2.5-flare and openai/gpt-image-2.5-sunburst. Both models generate and edit images with improved natural lighting and textures, while following complex visual instructions and handling detailed layouts and transparent backgrounds. They also support reference images for targeted edits without altering surrounding elements. The models are designed for different use cases, with Flare optimized for speed and Sunburst for precision.

Flare is optimized for faster generation and iteration, making it suitable for rapid prototyping or iterative design workflows. Sunburst, in contrast, takes longer to generate but provides tighter control over composition and detail, ideal for high-precision creative work. Users can switch between models in the AI Gateway model playground to test their outputs. The playground allows direct comparison of results before integrating the models into production workflows.

AI Gateway serves as a unified API layer that simplifies model access by handling routing, retries, failover, and performance optimizations to improve uptime beyond provider guarantees. It includes built-in custom reporting, budget controls for API keys, and routing rules to manage costs and usage efficiently. The platform reflects provider pricing without markup and does not charge a platform fee on inference, including for Bring Your Own Key requests.

Vercel’s AI Gateway now supports all image models, including the newly added GPT Image 2.5 Flare and Sunburst. The service provides a centralized interface for developers to deploy, monitor, and scale image generation workflows while maintaining cost transparency and operational control.