Integration

Vercel AI Gateway integration

Vercel AI Gateway, a single endpoint that routes to models from many providers under one API key and one bill. Exposes an OpenAI-compatible chat completions, embeddings, image generation and responses surface, an Anthropic-compatible messages surface with token counting, and a Cohere-compatible rerank endpoint, plus gateway specific calls for the model catalogue with pricing, the credit balance, the cost of one past generation and a usage report. Model identifiers always take the creator/model form.

Connect Vercel AI Gateway How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Vercel AI Gateway.Built from the 13 Vercel AI Gateway tools below, on the connection you add once.

Common Vercel AI Gateway use cases

building a model picker with live pricing
producing a monthly report of model spend by team
generating illustration assets inside a content workflow
attributing the exact cost of each model call to a customer
calling several model providers through one key and one bill
embedding documents through the same key used for chat models
pinning a model to a specific provider for compliance reasons
alerting when the gateway credit balance drops below a threshold
checking a long prompt fits the context window before sending it
reordering vector search hits before building a grounding context

What you can do with Vercel AI Gateway

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Model, 3 operations

get_modelGet modelGETRetrieves a single model entry with its pricing.
list_model_endpointsList model endpointsGETLists which providers can serve a model.
list_modelsList modelsGETLists every model the gateway offers, with pricing.

Chat completion, 1 operation

create_chat_completionCreate chat completionPOSTGenerates a model reply and routes it to a provider automatically.

Credit, 1 operation

get_creditsGet creditsGETReturns the account's credit balance and total spend.

Embedding, 1 operation

create_embeddingCreate embeddingPOSTCreates embedding vectors for one or more texts.

Generation, 1 operation

get_generationGet generationGETReturns cost and usage detail for one past generation.

Image, 1 operation

generate_imageGenerate imagePOSTGenerates images from a prompt.

Message, 1 operation

create_messageCreate messagePOSTGenerates a reply using the Anthropic messages shape.

Ranking, 1 operation

rerank_documentsRerank documentsPOSTReranks candidate documents by relevance to a query.

Report, 1 operation

get_usage_reportGet usage reportGETReturns aggregated usage and spend for a period.

Response, 1 operation

create_responseCreate responsePOSTGenerates a response using the Responses API shape.

Token, 1 operation

count_message_tokensCount message tokensPOSTCounts the input tokens of an Anthropic-style request.

Use Vercel AI Gateway from Claude Code, Cursor or Codex

Connect Vercel AI Gateway in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Vercel AI Gateway operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Vercel AI Gateway

Create your workspace
Sign up free. Nothing to install.
Connect Vercel AI Gateway once
Add your Vercel AI Gateway connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

Vercel AI Gateway integration FAQ

What can you do with the Vercel AI Gateway integration?

LiveContext exposes 13 operations on Vercel AI Gateway, covering model, chat completion, credit and embedding. Common uses include building a model picker with live pricing, producing a monthly report of model spend by team and generating illustration assets inside a content workflow.