Skip to main content
Pastures works with any AI provider that implements the OpenAI chat completions API. This includes OpenAI, Anthropic, Ollama, Azure OpenAI, and any custom endpoint.

​
Supported providers

ProviderAPI Base URLModel exampleAuth
OpenAIhttps://api.openai.com/v1gpt-4oAPI key
Anthropichttps://api.anthropic.comclaude-sonnet-4-20250514API key
Ollamahttp://localhost:11434/v1llama3.2None
Azure OpenAIhttps://{resource}.openai.azure.comYour deployment nameAPI key
CustomAny OpenAI-compatible endpointProvider-specificProvider-specific

​
Configure in Pastures

Navigate to Pastures → Settings and enter:
FieldValue
AI ProviderYour provider (OpenAI, Anthropic, Ollama, etc.)
API Base URLThe provider’s API endpoint
API KeyYour provider’s API key (leave blank for Ollama)
ModelThe model identifier

​
Ollama local setup

Ollama lets you run models locally with no API key and no data leaving your network.
1

Install Ollama

brew install ollama
Or download from ollama.com.
2

Pull a model

ollama pull llama3.2
This downloads the model weights (~4 GB for llama3.2).
3

Start Ollama

ollama serve
Ollama serves an OpenAI-compatible API at http://localhost:11434/v1.
4

Configure in Pastures

In Pastures → Settings:
FieldValue
AI ProviderOllama
API Base URLhttp://localhost:11434/v1
API Key(leave blank)
Modelllama3.2
For Rancher running in a VM or container, replace localhost with the host machine’s IP address.

​
Limitations of BYO mode

BYO mode uses your model’s general knowledge for diagnostics. The following features are only available with Rancher Oracle:
  • Source citations — GitHub issue links in diagnostic responses
  • Fleet correlation — Cross-cluster pattern matching
  • Fix verification — Post-fix monitoring
See Oracle Setup to enable these features.