AVELIN Documentation

Welcome to AVELIN — a sovereign AI platform that gives you access to the world's best AI models through a single, governed API.

This documentation helps you get started, choose the right model, integrate with your tools, and understand the platform.

Quick Start

New to AVELIN? Start here.

AI Models

AVELIN offers 9 specialized models across 3 families, plus utility models. Each model is optimized for specific use cases.

Model Catalog

Complete model comparison with context windows, max output, capabilities, and selection guidance.

Intelligence Models (256K context)

For reasoning, analysis, and multimodal tasks.

  • avelin-ultra — Flagship reasoning for complex decisions and strategic analysis
  • avelin-pro — High-efficiency reasoning for daily workflows and production economics
  • avelin-fast — Low-latency responses for real-time chat and high-volume workloads

Coding Models (1M context)

For software engineering, debugging, and code generation.

Agentic Models (256K context)

For autonomous agents, tool calling, and multi-step workflows.

Utility Models

Specialized models for embeddings, transcription, text-to-speech, and image generation.

  • Utility Models — Embeddings (bge-m3), transcription (whisper, avelin-stt), text-to-speech (tts-1), and image generation

Model Families Overview

Deep dive into each model family's positioning, capabilities, and use cases.

Developer Resources

Build applications with the AVELIN API. Compatible with OpenAI and Anthropic SDKs.

API Documentation

  • API Reference — Complete endpoint documentation for chat completions, embeddings, audio, and images
  • Web Intelligence API — Firecrawl-compatible scrape, search, map, crawl, and extract on your AVELIN key
  • API Quickstart — Step-by-step guide to your first API call
  • SDKs & Tools — Official SDKs, CLI tools, and editor integrations

Integration Guides

Practical guides for integrating AVELIN with popular tools. We support 40+ OpenRouter-compatible apps.

Featured Integrations

  • Browser Use — Browser automation (92K GitHub stars)
  • Continue — Open-source VS Code/JetBrains assistant
  • NanoClaw — Lightweight AI code analysis tool
  • VT Code — Terminal-based AI coding assistant

Coding & IDE Tools

Chat & Desktop Clients

Automation & Productivity

Creative Tools

Frameworks & SDKs

Observability

Business Use Cases

See how organizations use AVELIN to transform workflows.

Use Cases Overview

Real-world scenarios and implementation patterns.

Platform Architecture

Understand how AVELIN works under the hood.

Core Components

Platform Modules

  • AVELIN-API — The governed API layer with automatic failover and retry logic
  • AVELIN-GPT — Conversational interface for non-technical users
  • AVELIN-MCP — Model Context Protocol for tool integrations
  • Y-RAY — Document search and RAG (retrieval-augmented generation)

MCP Integrations

Connect AVELIN to your productivity tools via MCP (Model Context Protocol).

Benefits & Value

Why organizations choose AVELIN over direct provider APIs.

Benefits Overview

Strategic, operational, and competitive advantages.

Security & Operations

Enterprise-grade security, reliability, and operational control.

Operations Overview

Deployment, administration, and governance guidance.

Reference

Glossary

Definitions of key terms and concepts used throughout the documentation.

Need Help?

Documentation Structure

docs/
├── api/              # API reference, quickstart, SDKs
├── models/           # Model catalog and family overviews
├── guides/           # Integration guides (Hermes, etc.)
├── use-cases/        # Business scenarios and workflows
├── systems/          # Platform modules and architecture
├── mcp/              # MCP integrations and actions
├── benefits/         # Value proposition and benchmarks
├── operations/       # Deployment, security, troubleshooting
└── README.md         # This file

Frequently asked questions

What is in the AVELIN docs?

Guides to the API, the nine AVELIN models, the Decision Layer, deployment and privacy, the AVELIN App, MCP connectors, Y-Ray Data and integrations with common tools, plus the price list and a glossary.

Where do I start?

With the API quickstart. It shows the two-line change: the base URL and the API key. Then pick a model in the model catalog, or let the Decision Layer pick one for each request.

Is the API OpenAI and Anthropic compatible?

Yes. The same nine models answer in the OpenAI chat format and in the Anthropic messages format, with streaming and tool calling.

Where are the prices?

On the pricing page, which lists every model and endpoint at public list prices, with cache rates. The same prices are available as JSON from the API.

Where is the Decision Layer documented?

In How AVELIN works and the platform overview. The product pages on the website describe it, and a POC proves it on your own workload.