🔄 Shimmy API Playground

Interactive testing environment for the Shimmy LLM inference API

Quick Examples

Click any example to load it into the playground:

API Request

Full URL: http://localhost:11434/api/generate

API Response

Ready to send your first request! 🚀 Try the examples above or customize your own request. Shimmy supports: • Text generation (/api/generate) • Chat completions (/api/chat) • Model listing (/api/tags) • Health checks (/health) • Streaming responses • Native SafeTensors models

API Documentation

Text Generation

POST /api/generate

Generate text with any loaded model. Supports streaming and custom parameters.

Chat Completion

POST /api/chat

Chat-style completions with conversation history and system prompts.

List Models

GET /api/tags

Get all available models and their metadata.

Health Check

GET /health

Check if the Shimmy server is running and healthy.