Local Runtime Integrations

Ollama API

Local API surface for connecting open-weight models to apps, scripts, chat UIs, automations, and developer tools.

Best for

Developers who want a simple local model endpoint behind apps and workflows.

Integration profile

Workflow: Local Runtime IntegrationsLocal support: trueSetup: BeginnerOpen source

Model support

Supports models available through Ollama's model library and compatible local builds.

How to use this integration

Local chat
Automation calls
Coding assistants
Private prototypes

Where it fits

Ollama API fits in the local runtime integrations layer of an AI stack. Use it when you need model outputs connected to real workflows, and evaluate it against your privacy needs, deployment model, team habits, and operational complexity.

Related models

Phi-4 Mini
Mistral Small 3.1
Llama 3 70B

Source and docs

Ollama API docs