neon-ai-gateway - Route LLM calls through Neon AI Gateway
Routes LLM inference through a branch-scoped Neon gateway using one credential and supports multiple model providers, SDKs, and streaming.
Tags
Updated: 2026-09-29Capabilities
Typical Inputs
Typical Outputs
What this skill does
- Enable the Neon AI Gateway
- Send LLM inference requests
- Route across model providers
- Build AI SDK agents
- Stream responses with SSE
- Switch SDK dialect endpoints
Inputs
- Neon project and branch
- Model identifier
- Prompt or messages
- Gateway credentials
- SDK or API client configuration
Outputs
- LLM inference responses
- Streamed response events
- Configured AI agent code
- Gateway credentials in environment files
Requirements
- Neon project
- us-east-2 deployment region
- Neon CLI and neon.ts configuration
- Supported LLM SDK or API client