Providers

Vercel AI gateway

The Vercel AI Gateway provides a unified API to access hundreds of models through a single endpoint.

Property	Value
Provider	`vercel-ai-gateway`
Package	`@openclaw/vercel-ai-gateway-provider`
Auth	`AI_GATEWAY_API_KEY`
API	Anthropic Messages compatible
Base URL	`https://ai-gateway.vercel.sh`
Model catalog	Auto-discovered via `/v1/models`

Getting started

Install the plugin

bash

openclaw plugins install @openclaw/vercel-ai-gateway-provider

Installation applies to a running Gateway automatically; otherwise it takes effect on the next startup. See Apply changes and inspect.

Set the API key

bash

openclaw onboard --auth-choice ai-gateway-api-key

Check the default model

Onboarding sets the default to the first recommended model that your key can use. To choose another, set any model from the list below:

json5

{  agents: {    defaults: {      model: { primary: "vercel-ai-gateway/<model-id>" },    },  },}

Verify the model is available

bash

openclaw models list --provider vercel-ai-gateway

Non-interactive example

bash

openclaw onboard --non-interactive --accept-risk --skip-health \  --mode local \  --auth-choice ai-gateway-api-key \  --ai-gateway-api-key "$AI_GATEWAY_API_KEY"

Token Pass

Vercel Token Pass uses a Token Pass API key in place of a regular AI Gateway API key. Set it up with the same auth choice. Vercel lists only Token Pass models for that key, so openclaw models list --provider vercel-ai-gateway shows exactly the models the key can use. Onboarding picks the default from those models.

Model ID shorthand

OpenClaw normalizes Claude shorthand model refs at runtime:

Shorthand input	Normalized model ref
`vercel-ai-gateway/claude-opus-4.6`	`vercel-ai-gateway/anthropic/claude-opus-4.6`
`vercel-ai-gateway/opus-4.6`	`vercel-ai-gateway/anthropic/claude-opus-4-6`

Advanced configuration

Environment variable for daemon processes

If the OpenClaw Gateway runs as a daemon (launchd/systemd), make sure AI_GATEWAY_API_KEY is available to that process.

Provider routing

Vercel AI Gateway routes each request to the upstream provider named in the model ref prefix. For example, vercel-ai-gateway/anthropic/claude-opus-4.6 routes through Anthropic, vercel-ai-gateway/openai/gpt-5.5 routes through OpenAI, and vercel-ai-gateway/moonshotai/kimi-k2.6 routes through MoonshotAI. One AI_GATEWAY_API_KEY authenticates all upstream providers.

Thinking levels

/think options follow the upstream model prefix when OpenClaw recognizes it. vercel-ai-gateway/anthropic/... uses the Claude thinking profile, including the adaptive default for Claude 4.6 models. Trusted vercel-ai-gateway/openai/... refs (gpt-5.2 and newer, plus Codex variants down to gpt-5.1-codex) expose /think xhigh. Other namespaced refs keep the standard reasoning levels unless their catalog metadata declares more.

App attribution

Requests to ai-gateway.vercel.sh carry Vercel's documented app-attribution headers, HTTP-Referer: https://openclaw.ai and X-Title: OpenClaw. This also applies to custom provider ids whose baseUrl points at AI Gateway. A custom proxy baseUrl gets no attribution headers.

Model selection

Choosing providers, model refs, and failover behavior.

Troubleshooting

General troubleshooting and FAQ.

Was this useful?