# openrout.ing

> Open source AI inference platform. Zero logging. Completely private. 22,250+ models, 904 AI agents, 347 API endpoints.

## What is openrout.ing?

openrout.ing is an open source AI inference platform that provides two APIs:

1. **Raw Inference API** (raw.openrout.ing) - OpenAI-compatible API with 22,250+ models via Featherless AI. Features zero 429 rate limiting (unlimited Redis-backed queue), model coalition fallback (41 model mappings), per-client concurrency slots, streaming (SSE), and embeddings. Direct passthrough to Featherless AI infrastructure.

2. **Intelligence API** (api.openrout.ing) - Enriched LLM inference with 904 pre-built specialized AI agents across medical, financial, security, architecture, creative, and executive domains. Features context enrichment pipeline, tiered memory (core/recall/archival), knowledge graphs, workflow orchestration, multi-agent collaboration, guardrails, event sourcing, and 49 advanced features.

## Key Facts

- 22,250+ open source models (Qwen3, DeepSeek V4, Llama, Mistral, Phi, etc.)
- 904 pre-built AI agents
- 347 API endpoints across v1, v2, v4, v5
- Zero logging, zero telemetry, zero data retention
- GDPR compliant by default
- Streaming (SSE) and non-streaming inference
- Model coalition fallback (41 mappings, 3 retries per model)
- Per-client concurrency (tier-based: 4 to unlimited)
- Token usage tracking per client per day per model
- Embeddings (Qwen3-Embedding-0.6B, 1024 dimensions)
- Fixed monthly pricing from 79/mo (no usage-based billing)
- Upstream: https://api.featherless.ai/v1
- Backend: FastAPI on port 9000
- Raw proxy: a0_proxy_v5.py on port 9101 (Redis-backed)
- Intelligence: brain_server_v4.py on port 9102 (Docker)

## API Endpoints

- Raw Inference: https://raw.openrout.ing/v1/chat/completions, https://raw.openrout.ing/v1/models, https://raw.openrout.ing/v1/embeddings
- Intelligence: https://api.openrout.ing/v1/chat/completions, https://api.openrout.ing/v1/agents, https://api.openrout.ing/v1/agents/{agent_id}/chat
- Backend: https://openrout.ing/v1/auth/login, https://openrout.ing/v1/billing/checkout, https://openrout.ing/v1/models
- OpenAPI spec: https://openrout.ing/openapi.json (245 paths)
- Postman collection: https://openrout.ing/openrouting.postman_collection.json

## Documentation

- Full API docs: https://openrout.ing/docs
- Features: https://openrout.ing/features
- Pricing: https://openrout.ing/pricing
- Models: https://openrout.ing/models

## Authentication

All APIs use Bearer token authentication:
Authorization: Bearer YOUR_API_KEY

## Quick Start

curl https://raw.openrout.ing/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"Qwen/Qwen3-8B","messages":[{"role":"user","content":"Hello!"}],"max_tokens":100}'