Netlify AI Gateway Adds Google Gemini 3.5 Flash With Zero-Config Integration.

Netlify has added Google's Gemini 3.5 Flash model to its AI Gateway, allowing developers to use the Google GenAI SDK directly inside Netlify Functions without managing API keys or configuring authentication.

The integration, announced on LinkedIn and detailed in the platform's official changelog, handles caching, rate limiting, and authentication automatically. The feature is available across all Netlify Function types, requiring no additional setup from developers.

Netlify AI Gateway sits between developer code and AI model providers, managing the operational complexity of production AI integrations. When developers call Google's GenAI SDK from within a Netlify Function, the gateway intercepts requests and applies platform-level handling for common infrastructure concerns.

This means no environment variables to configure, no credential rotation workflows, and no rate limit logic in application code. The gateway provisions access automatically when developers deploy functions that reference supported models.

The addition follows Netlify's broader push into AI infrastructure, including Netlify Database's AI-native branching model and Agent Runners for deploying AI agents. By absorbing authentication and performance tuning at the platform layer, Netlify removes friction from the AI development loop.

Gemini 3.5 Flash is Google's speed-optimized model in the Gemini family, designed for applications requiring fast inference with moderate context windows. It sits between lighter models like Gemini 1.5 Flash and the full Gemini 3.5 Pro, balancing response time with reasoning capability.

For developers building customer-facing features, chatbots, or real-time workflows where latency matters, the Flash variant often provides the best cost-to-performance ratio. Combined with Netlify's edge network and automatic caching, requests that hit cached responses avoid provider round trips entirely.

The model joins other providers already available through AI Gateway, though Netlify has not published a complete list of supported models. Previous changelog entries confirm support for models used in Agent Runners, Netlify's framework for deploying autonomous AI agents that can execute multi-step workflows.

Netlify's AI Gateway is part of a coordinated infrastructure play. The platform now offers integrated Postgres through Netlify Database, which automatically provisions branch databases for every deploy preview and isolates AI agent runs into independent database branches for parallel testing.

By handling model access, data persistence, and deployment orchestration in a single platform, Netlify reduces the number of services developers must coordinate when building AI features. The approach mirrors how platforms like Vercel and Supabase have bundled adjacent infrastructure to reduce integration overhead.

Developers interested in using Gemini 3.5 Flash through Netlify AI Gateway can reference the Agent Runners documentation for implementation details. The feature is available immediately for all Netlify accounts with no changes required to existing function configurations.