How to Use the DeepInfra (Serverless LLM Inference) MCP in LangChain

Q: How do I use DeepInfra (Serverless LLM Inference) tools with a LangChain agent?

You get your Vinkius endpoint token, install the langchain-mcp-adapters library, and point the client at the server URL. The gettools() method gives you a list of tools to pass directly to your agent.

Q: Can I chain multiple DeepInfra (Serverless LLM Inference) tools together in LangChain?

Yes, that's what it's for. An agent can call generateimage and then feed the result into a prompt for createchatcompletion. The framework makes it easy to wire tool outputs to tool inputs.

Q: Does the DeepInfra (Serverless LLM Inference) server support custom models in LangChain?

It does. The runnativeinference tool is a generic endpoint for any model DeepInfra supports that might not have a standard OpenAI-style spec. It's your escape hatch for more exotic model types.

Connect your LangChain agents to DeepInfra's serverless models. Run LLMs, generate images, and create embeddings as steps in any chain.

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 LangChain

Create your Vinkius account to connect DeepInfra (Serverless LLM Inference) to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Any Model, Not Just Chat

The `create_chat_completion` tool lets your agent talk to top-tier LLMs. But the real power comes from `run_native_inference`, which handles models that don't fit a standard chat format, like speech-to-text or custom deployments. Because it's LangChain, you can chain these calls. Get a transcript with `run_native_inference`, summarize it with `create_chat_completion`, and then translate the summary. Each tool is just another link in your agent's reasoning chain, managed by this MCP server.

Generate Images Inside Your Chains

Use the `generate_image` tool to have your agent create pictures from a text prompt. This isn't a dead end. It's a composable part of your agent's workflow. Your agent can generate an image, then immediately pass that image's subject to another tool, or use `create_chat_completion` to write social media copy about it. The output of one DeepInfra tool becomes the input for the next step in the chain.

Embeddings for your LangChain MCP Server

The `create_embedding` tool turns text into vectors. This is a fundamental building block for any RAG setup you're assembling in LangChain. Your agent can feed text to `create_embedding` and pass the output vectors directly into your vector store integration. This MCP server handles the model inference; LangChain handles the rest of the pipeline.

Setup guide

Set up DeepInfra (Serverless LLM Inference) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes DeepInfra (Serverless LLM Inference) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "deepinfra-serverless-llm-inference-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent DeepInfra (Serverless LLM Inference) transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

You get your Vinkius endpoint token, install the `langchain-mcp-adapters` library, and point the client at the server URL. The `get_tools()` method gives you a list of tools to pass directly to your agent.

Yes, that's what it's for. An agent can call `generate_image` and then feed the result into a prompt for `create_chat_completion`. The framework makes it easy to wire tool outputs to tool inputs.

It does. The `run_native_inference` tool is a generic endpoint for any model DeepInfra supports that might not have a standard OpenAI-style spec. It's your escape hatch for more exotic model types.

Vinkius handles the auth and provides a stable, unified interface through the MCP standard. You just give your agent the tools; you don't write custom API client code or manage credentials.

Vinkius only sees the text prompts, messages, and model names you send to the DeepInfra tools. It's all ephemeral and processed in a zero-trust sandbox. Nothing is stored after the request is complete.

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