Status: [LIVE] Endpoints found: https://api.ai.seedofcode.dev/api/chat https://api.ai.seedofcode.dev/api/chat/stream Source: https://github.com/Explore13/seedofcode-llm-backend # SeedOfCode LLM API - Integration Guide ![alt text](image.png) ## Introduction Welcome to the SeedOfCode LLM Platform! This guide provides everything you need to integrate our managed, scalable LLM inference API into your own applications. Our platform handles model routing, queueing, and credit management behind the scenes, providing a seamless developer experience. ## Prerequisites & Getting Started Before you can make API requests, you will need an active account and a valid API key. 1. **Register**: Navigate to [ai.seedofcode.dev](https://ai.seedofcode.dev) (Note: The frontend UI is currently in development). 2. **Verify**: Complete the email verification process to activate your account. 3. **Generate API Key**: Create a new API Key in your dashboard. Keep this key secure; you will only be able to view the full secret key once. API keys begin with `soc_live_` (for production) or `soc_test_` (for testing). 4. **Credits**: New accounts receive a signup bonus of credits. Inference costs are calculated dynamically based on input/output token counts. --- ## Authentication The API uses standard API Key authentication. All inference endpoints require your secret API key. You can pass the key in one of two ways: **Option 1: Using the `x-api-key` header** ```http x-api-key: soc_live_YOUR_API_KEY ``` **Option 2: Using the `Authorization` header** ```http Authorization: Bearer soc_live_YOUR_API_KEY ``` *(You may also use `Authorization: api_key soc_live_YOUR_API_KEY`)* --- ## Base URL All API requests should be prefixed with the following base URL: ```text https://api.ai.seedofcode.dev/api ``` *(For local testing, use `http://localhost:8080/api`)* --- ## Core Endpoints ### 1. Chat Completion **`POST /chat`** Generates a response for a given chat conversation. The request blocks until the full response is generated. **Request Body:** ```json { "model": "llama3.1:8b", "messages": [ { "role": "system", "content": "You are a helpful AI assistant." },