Integrations / AI and LLM Providers

AI and LLM Providers

The systems VIDIZMO connects to, and what you can do with each. Where a connector is not built yet, it can be built to your requirement, or reached through an MCP server or a REST endpoint you define.

20 integrations

Anthropic Claude

Run models from Anthropic.

Available

AWS AI services

Run AI processing through AWS AI services.

Available

AWS Bedrock

Reach several model families inside your own AWS account.

Available

Azure AI Services

Run AI processing through Azure AI Services.

Available

Azure AI Video Indexer

Run AI processing through Azure AI Video Indexer.

Available

Azure OpenAI Service

Run OpenAI models inside your own Azure tenancy.

Available

Cohere

Run Cohere models for generation and retrieval.

Available

Google Gemini

Google

Run models from Google.

Available

Groq

Run open models at low latency on Groq hardware.

Available

Hugging Face

Use embedding models from Hugging Face.

Available

IBM watsonx

Run models through IBM watsonx.

Available

Infinity

Serve embedding models with Infinity.

Available

MCP (Model Context Protocol)

Reach any system that publishes a Model Context Protocol server.

Available

Microsoft Foundry

Run and manage models through Microsoft Foundry.

Available

Mistral AI

Run Mistral models, hosted in Europe or self-hosted.

Available

NVIDIA

Run models on your own GPUs through NVIDIA NIM.

Available

Ollama

Run open models on your own hardware with Ollama.

Available

OpenAI

Run models from OpenAI.

Available

Together AI

Run a broad open-model catalogue without hosting it.

Available

vLLM

Serve open models at scale with vLLM.

Available

Not on the list?

We build it

Send us your API documentation and we build, test and maintain the connector. There is no development cost to you.

Request an integration

Bring an MCP server

If the system publishes a Model Context Protocol server, AI Intelligence Hub connects to it as a client with configuration alone.

Define a REST endpoint

Describe your endpoint and it becomes a node in an agent workflow, without waiting on our roadmap.

Product names, logos and trademarks shown here are the property of their respective owners. Their use does not imply any affiliation with or endorsement by them.