Your local Llama API

Replace Groq with your own Ollama server. Use the chat UI or call the OpenAI-compatible API from your other projects.

Ollama Online 2 model(s) available

Open Chat View API Models

Installed models

llama3.2:3b
llama3.1:8b

API for your other projects

OpenAI-compatible endpoint. Change only base_url and api_key.

POST http://YOUR-SERVER:5080/v1/chat/completions
Authorization: Bearer llama-local-dev-key-change-me
Content-Type: application/json

{
  "model": "llama3.1:8b",
  "messages": [
    { "role": "user", "content": "Hello!" }
  ]
}

C# example

var client = new OpenAIClient(
    new ApiKeyCredential("llama-local-dev-key-change-me"),
    new OpenAIClientOptions { Endpoint = new Uri("http://YOUR-SERVER:5080/v1") });

var chat = client.GetChatClient("llama3.1:8b");
var response = await chat.CompleteChatAsync("Hello!");
Console.WriteLine(response.Value.Content[0].Text);

Change the API key in appsettings.json under Api:Keys.