How to Use the DeepInfra (Serverless LLM Inference) MCP in Vercel AI SDK

Q: How do I configure DeepInfra (Serverless LLM Inference) with Vercel AI SDK?

Install @ai-sdk/mcp and instantiate the client using the Vinkius HTTP URL. Pass the tools array directly into streamText to let your agent call DeepInfra models.

Q: Do I need to close the connection after running an inference tool?

Yes, always call mcpClient.close() when your execution completes. This prevents socket leaks in your serverless functions and keeps your Next.js API routes fast.

Feed DeepInfra's serverless LLM responses and generated images directly into your Vercel AI SDK frontend without loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DeepInfra (Serverless LLM Inference) MCP to Vercel AI SDK

Create your Vinkius account to connect DeepInfra (Serverless LLM Inference) to Vercel AI SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup DeepInfra (Serverless LLM Inference) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pipe serverless LLM power into Vercel AI SDK via MCP

Users hate waiting for slow AI outputs. When you call `create_chat_completion` inside your Next.js edge route, this MCP Server lets you stream the token-by-token response of DeepSeek-V3 straight to the browser. The Vercel AI SDK handles the stream chunking natively. Because Vinkius hosts the endpoint, you bypass cold starts and pipe raw text directly to the UI components.

Render generated images live in your React UI

To show images immediately, trigger `generate_image` via the SDK's tool calling mechanism. The server spits out the image data, which your frontend displays instantly instead of leaving users staring at a blank card. For search features, you can also trigger `create_embedding` to index user inputs on the fly. It runs entirely inside your edge runtime setup without bloating your bundle.

Run speech and OCR models in Next.js Edge Functions

When standard LLMs aren't enough, use `run_native_inference` to run specialized OCR or audio transcription models on DeepInfra. This bypasses the typical API limitations of default web runtimes. The Vercel AI SDK coordinates these complex non-text outputs from the MCP Server. You get the raw JSON back, ready to be formatted into your application's state.

Setup guide

Set up DeepInfra (Serverless LLM Inference) MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all DeepInfra (Serverless LLM Inference) tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent DeepInfra (Serverless LLM Inference) transactions",
});

console.log(text);
await mcpClient.close();

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by DeepInfra. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect DeepInfra (Serverless LLM Inference) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about DeepInfra (Serverless LLM Inference) MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and instantiate the client using the Vinkius HTTP URL. Pass the tools array directly into `streamText` to let your agent call DeepInfra models.

Yes, the serverless endpoint is fully compatible with Vercel edge runtimes. You can trigger `create_chat_completion` directly from edge routes without timeout issues.

While image generation itself doesn't stream token-by-token, the SDK can stream the progress state and render the output URL returned by `generate_image` immediately. This keeps your UI responsive.

Yes, always call `mcpClient.close()` when your execution completes. This prevents socket leaks in your serverless functions and keeps your Next.js API routes fast.

All text prompts, image descriptions, and raw inputs processed by `create_embedding` are routed through an isolated V8 sandbox on Vinkius. Your sensitive data never persists on our disks and goes straight to DeepInfra over TLS.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript