Vercel AI Gateway for AI agents
Vercel AI Gateway routes requests to different AI models through one endpoint, used by developers who want model flexibility and usage tracking without juggling separate API keys. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Vercel AI Gateway.
Create a chat completion
Send a prompt through the gateway to a chosen model and get back a response.
Check the spend report
Read usage and spend across models as a read-only report.
List the model catalog
Pull the available models before deciding which one to route a request to.
22 Vercel AI Gateway actions, graded by risk.
Every Vercel AI Gateway action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
9Look things up. Allowed by default.
- vercel_ai_gateway.get_modelGet Model
- vercel_ai_gateway.search_modelsSearch Models
- vercel_ai_gateway.get_generationGet Generation
- vercel_ai_gateway.get_spend_reportGet Spend Report
- vercel_ai_gateway.get_credit_balanceGet Credit Balance
- vercel_ai_gateway.list_model_catalogList Model Catalog
- vercel_ai_gateway.get_model_endpointsGet Model Endpoints
- vercel_ai_gateway.list_typesafe_modelsList TypeSafe Models
- vercel_ai_gateway.count_message_tokensCount Message Tokens
write
13Create and change things. Allow, or ask the user first.
- vercel_ai_gateway.create_embeddingsCreate Embeddings
- vercel_ai_gateway.create_chat_completionCreate Chat Completion
- vercel_ai_gateway.create_anthropic_messageCreate Anthropic Message
- vercel_ai_gateway.edit_imagesEdit Images
- vercel_ai_gateway.evaluate_stateEvaluate State
- vercel_ai_gateway.generate_imagesGenerate Images
- vercel_ai_gateway.generate_speechGenerate Speech
- vercel_ai_gateway.compact_responseCompact Response
- vercel_ai_gateway.transcribe_audioTranscribe Audio
- vercel_ai_gateway.generate_responseGenerate Response
- vercel_ai_gateway.typesafe_evaluateEvaluate with TypeSafe API
- vercel_ai_gateway.rerank_text_documentsRerank Text Documents
- vercel_ai_gateway.rerank_object_documentsRerank Object Documents
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Vercel AI Gateway in three steps.
- 01Your users connect Vercel AI GatewayThey add their Vercel AI Gateway api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “create Embeddings” can wait for the user to approve.
- 03Any agent can actYour agent calls Vercel AI Gateway through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('vercel_ai_gateway', { read: 'allow', write: 'ask', // create_embeddings destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Vercel AI Gateway connects.
Users add their Vercel AI Gateway api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Vercel AI Gateway connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Vercel AI Gateway from any agent.
Vercel AI Gateway and Arc0, answered.
Can I use Vercel AI Gateway with Claude, ChatGPT or Cursor?
Yes. Connect Vercel AI Gateway to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Vercel AI Gateway actions you allow.
How do users connect Vercel AI Gateway?
Users add their Vercel AI Gateway api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Vercel AI Gateway actions can my agent take?
22 in total: 9 read, 13 write and 0 destructive, such as “create Embeddings”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Vercel AI Gateway?
Yes. Allow read actions and deny writes in the Vercel AI Gateway policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Vercel AI Gateway too?
Yes. The same Vercel AI Gateway connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Vercel AI Gateway into your agent.
Your users connect Vercel AI Gateway once, under your brand. Your agent gets 22 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan