Netlify Adds OpenAI GPT Image 2 to AI Gateway With Zero-Config Integration.

Netlify announced on LinkedIn that OpenAI's GPT Image 2 is now available through Netlify AI Gateway. The integration removes the need for developers to configure API keys or maintain a separate OpenAI setup.

The image generation model can be called directly from any Netlify Function. AI Gateway handles authentication and connection management automatically, allowing developers to use the OpenAI SDK without additional configuration.

GPT Image 2 works alongside Netlify's existing infrastructure capabilities. The model runs with access to caching and rate limiting controls, giving teams the ability to manage request behavior at the platform level rather than implementing these controls in application code.

This approach mirrors Netlify's recent addition of GPT-5.5 Instant, which also became available through AI Gateway with zero configuration required. Both integrations reflect Netlify's positioning around removing infrastructure overhead for AI-powered features.

Developers import the OpenAI SDK in a Netlify Function and call the image generation endpoint. No API key management or authentication flow is required. The AI Gateway intercepts the request, handles credentials, and returns the generated image.

The model is available across all Netlify Function types. Teams can apply the same caching rules and rate limits they use for other API calls, centralizing request management for both traditional APIs and AI model endpoints.

Netlify launched AI Gateway as part of a broader infrastructure push around agent-friendly deployment. The service provides a unified interface for multiple AI providers, handling authentication and request routing without requiring developers to manage individual provider accounts or keys.

The GPT Image 2 addition expands the range of AI capabilities accessible through a single integration point. Combined with Netlify's existing support for text models and the recent positioning of Agent Experience as a production bridge, the platform is building toward a deployment model where AI features require minimal configuration overhead.

Full implementation details are available in the AI Gateway documentation.