Configure model providers

Connect kagent to a LLM provider by creating a ModelConfig resource.

About model providers

Understand how a ModelConfig connects kagent to an LLM provider, and which configurations a Harness …

OpenAI

Configure kagent to use OpenAI models by creating a ModelConfig for the OpenAI provider.

agentgateway

Route kagent model requests through an agentgateway deployment for traffic management, …

Amazon Bedrock

Configure kagent to use models served through AWS Bedrock, with either the native Bedrock provider …

Anthropic

Configure kagent to use Anthropic Claude models by creating a ModelConfig for the Anthropic …

Azure AI Foundry

Configure kagent to use models served through an Azure AI Foundry deployment.

Azure OpenAI

Configure kagent to use OpenAI models hosted on Azure by creating a ModelConfig for the AzureOpenAI …

Gemini

Configure kagent to use Google Gemini models through the Google AI Studio API.

Google Vertex AI

Understand why Vertex AI models do not run on kagent 1.0, and which providers serve the same models …

Mistral

Configure kagent to use Mistral models by creating a ModelConfig for the Mistral provider.

Ollama

Configure kagent to use models that you run yourself with Ollama, in the cluster or on your own …

SAP AI Core

Understand why SAP AI Core models do not run on kagent 1.0, and what to use instead.

xAI

Configure kagent to use xAI Grok models through xAI’s OpenAI-compatible API.

BYO OpenAI-compatible endpoint

Configure kagent to use any provider that serves the OpenAI API, including a self-hosted gateway in …