neon-ai-gateway - Route LLM requests through the Neon AI Gateway
Enable branch-scoped access to multiple LLM providers through one Neon credential and a unified gateway endpoint.
Tags
Updated: 2026-10-07Capabilities
Typical Inputs
What this skill does
- Enable the AI Gateway
- Configure branch gateway settings
- Send LLM inference requests
- Route requests across models
- Use compatible SDKs
- Stream server-sent events
- Inspect available models
- Pull gateway credentials
Inputs
- Neon project
- Neon branch
- Neon configuration file
- Model identifier
- Prompts or messages
- Gateway credentials
- SDK configuration
Outputs
- LLM inference responses
- Streaming response events
- Available model listings
- Gateway credentials in environment files
- Updated branch gateway configuration
Requirements
- Neon project in us-east-2
- Paid Neon plan
- Neon AI Gateway beta access
- Neon CLI
- Configured Neon credentials
