Skip to main content
The Vercel AI Gateway provides a unified API to access hundreds of models through a single endpoint.
FluffBuzz auto-discovers the Gateway /v1/models catalog, so /models vercel-ai-gateway includes current model refs such as vercel-ai-gateway/openai/gpt-5.5 and vercel-ai-gateway/moonshotai/kimi-k2.6.

​
Getting started

1

Set the API key

Run onboarding and choose the AI Gateway auth option:
2

Set a default model

Add the model to your FluffBuzz config:
3

Verify the model is available

​
Non-interactive example

For scripted or CI setups, pass all values on the command line:

​
Model ID shorthand

FluffBuzz accepts Vercel Claude shorthand model refs and normalizes them at runtime:
You can use either the shorthand or the fully qualified model ref in your configuration. FluffBuzz resolves the canonical form automatically.

​
Advanced configuration

If the FluffBuzz Gateway runs as a daemon (launchd/systemd), make sure AI_GATEWAY_API_KEY is available to that process.
A key set only in ~/.profile will not be visible to a launchd/systemd daemon unless that environment is explicitly imported. Set the key in ~/.fluffbuzz/.env or via env.shellEnv to ensure the gateway process can read it.
Vercel AI Gateway routes requests to the upstream provider based on the model ref prefix. For example, vercel-ai-gateway/anthropic/claude-opus-4.6 routes through Anthropic, while vercel-ai-gateway/openai/gpt-5.5 routes through OpenAI and vercel-ai-gateway/moonshotai/kimi-k2.6 routes through MoonshotAI. Your single AI_GATEWAY_API_KEY handles authentication for all upstream providers.

Model selection

Choosing providers, model refs, and failover behavior.

Troubleshooting

General troubleshooting and FAQ.