Netlify Adds Gemini 3.7 Flash to AI Gateway and Agent Runners.

Netlify is adding Google’s Gemini 3.7 Flash to its AI Gateway and Agent Runners, giving developers another model option for building coding tools and autonomous workflows without managing model credentials directly.

The company announced the integration on LinkedIn, describing Gemini 3.7 Flash as a workhorse model suited to coding and agent tasks. It is available across every Netlify Function type as well as Agent Runners.

Developers can call Gemini 3.7 Flash through the Google GenAI SDK inside a Netlify Function. Netlify’s AI Gateway sits between the application and the model provider, taking responsibility for API keys and authentication.

That arrangement addresses several pieces of infrastructure that small teams would otherwise need to build or configure themselves. The integration includes:

• Managed API keys and authentication, reducing the need to expose or distribute provider credentials
• Caching, which can avoid repeated model calls for identical requests
• Rate limiting, giving teams a way to control request volume
• Support across Netlify Function types, rather than requiring a dedicated runtime
• Compatibility with Agent Runners, for workflows that need an AI agent to perform longer or multi-step tasks

Netlify points developers to its changelog for an implementation sample. The important technical detail is that the application can continue using Google’s own SDK while Netlify manages access at the platform layer. That should make the integration more approachable for teams already deploying serverless functions on Netlify.

The release also extends a broader model-access strategy. Netlify has been expanding the AI Gateway beyond a limited set of proprietary providers, including open model support through OpenRouter and, more recently, production access to hundreds of open models.

A conventional Function responds to an invocation and executes application logic. Agent Runners are intended for AI-led work that may involve planning, coding or making a sequence of changes. Adding a fast, general-purpose Gemini model gives developers another option for those workloads without changing the surrounding deployment platform.

For a small business or independent builder, that could support practical tools such as code assistants, internal content processors, support triage systems or agents that modify a web project. The model call can live beside the rest of the application code, while Netlify handles deployment and the gateway controls around it.

The integration lands as Netlify continues to develop Agent Runners as a more interactive development layer. The company has also added the ability for Agent Runners to ask clarifying questions before building apps, addressing a common problem in which an agent starts implementing an underspecified request.

Netlify has not provided separate pricing details for Gemini 3.7 Flash in the supplied announcement. Developers evaluating it should therefore check current AI Gateway, Agent Runner and model usage terms before moving a high-volume workload into production.

What is Gemini 3.7 Flash on Netlify?

Gemini 3.7 Flash is a Google AI model that developers can call through Netlify AI Gateway from Netlify Functions or Agent Runners. Netlify positions the integration for coding and agent-based workflows, with the gateway managing authentication and operational controls.

What does Netlify AI Gateway manage for Gemini 3.7 Flash?

The AI Gateway manages API keys and authentication. Netlify says caching and rate limiting are also included, reducing the amount of supporting infrastructure developers need to configure themselves.

Where is Gemini 3.7 Flash available on Netlify?

According to Netlify’s announcement, the model works across all Netlify Function types and Agent Runners. Developers can access it using the Google GenAI SDK inside a Netlify Function.