MCP For Claude Marketplace
DeepInfra (Serverless LLM Inference)

DeepInfra (Serverless LLM Inference) MCP Connector for Claude

A+

Run top-tier LLMs, image generation, and embeddings via DeepInfra's serverless infrastructure directly from your AI agent.

4 tools Official Updated Jun 28, 2026 Official Vinkius Partner
More Details Connect to Claude

Connect to DeepInfra to access a massive library of open-source models including DeepSeek, Llama 3, and FLUX. This MCP server provides high-performance, serverless inference for text, images, and specialized tasks.

What you can do

  • Chat Completions — Generate text using state-of-the-art models like DeepSeek-V3 or Llama-3.3-70B with full control over temperature and tokens.
  • Image Generation — Create stunning visuals using models like FLUX-1 or Stable Diffusion by simply providing a text prompt.
  • Text Embeddings — Convert text into high-dimensional vectors for RAG (Retrieval-Augmented Generation) or semantic search.
  • Native Inference — Access specialized models for speech-to-text (Whisper), OCR, or custom deployments that don't follow standard OpenAI specs.

How it works

  1. Subscribe to this server
  2. Enter your DeepInfra API Token
  3. Start querying world-class AI models from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • Developers — integrate powerful LLMs into your coding workflow without managing GPU infrastructure.
  • Content Creators — generate high-quality images and text variations directly within your workspace.
  • Data Engineers — build semantic search pipelines using serverless embedding endpoints.
llm-inferenceserverless-aitext-to-imageembeddingsai-models

4 tools expose this connector's capabilities to your AI agent.

create_embedding

Create embeddings for text via DeepInfra

generate_image

Generate an image from a text prompt via DeepInfra

create_chat_completion

Provide model name (e.g., deepseek-ai/DeepSeek-V3) and messages array. Create a chat completion using an LLM via DeepInfra

run_native_inference

Useful for models not covered by OpenAI spec (e.g., speech-to-text, OCR, video generation, or private deployments). Run native inference for a specific model on DeepInfra

See how to talk to your AI agent using DeepInfra (Serverless LLM Inference).

Generate a chat completion using deepseek-ai/DeepSeek-V3 to explain quantum entanglement.

I'll use the `create_chat_completion` tool with the DeepSeek-V3 model to generate a detailed explanation of quantum entanglement for you.

Create an image of a cyberpunk city at night using black-forest-labs/FLUX-1-schnell.

I'm calling the `generate_image` tool with the FLUX-1-schnell model and your cyberpunk prompt. One moment while the image is generated.

Generate embeddings for the text 'Artificial Intelligence is transforming the world' using BAAI/bge-large-en-v1.5.

I'll process that text through the `create_embedding` tool using the BGE model to get the vector representation.

You can use any model hosted on DeepInfra, such as `deepseek-ai/DeepSeek-V3` or `meta-llama/Llama-3.3-70B-Instruct`, by passing the model name to the `create_chat_completion` tool.

Related Connectors

GE

Geoapify MCP

17 tools Official

Access powerful location intelligence — geocoding, routing, place search, and IP tracking directly from your AI agent.

D View details →
GP

Gainsight PX MCP

12 tools Official

Manage product experience, track user behavior, and oversee engagements via AI agents with Gainsight PX.

A+ View details →
CL

Commerce Layer MCP

9 tools

Enable your AI agent to manage orders, SKUs, customers, and shipments via the Commerce Layer API.

A+ View details →
7S

7shifts MCP

12 tools Official

Schedule restaurant staff, manage shifts, track labor costs, and coordinate your team with intelligent workforce planning.

A+ View details →