Riven documentation

Riven is a sovereign AI platform: 75 live models behind one OpenAI-compatible API, served on-prem first with cloud fallback, plus the surfaces and services built on top of it.

curl

curl https://api.rivenai.io/v1/chat/completions \
  -H "Authorization: Bearer $RIVEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "riven-best", "messages": [{"role": "user", "content": "Hello"}]}'

Start here

Getting started

Create a key and make your first call in about two minutes.

Copy-paste examples in curl, Python, and JavaScript — including streaming.

Authentication & keys

Issue, rotate, and revoke rvn_ keys. Guest keys and rate limits.

Tier aliases, token multipliers, and how to read your quota.

Every endpoint, parameter, response header, and status code.

Per-model reference generated from the live gateway catalog.

The platform

Core Platform12 pages

The surfaces you sign in to: Console, Chat, Computer, Studio, Docs, and the rest of the shell.

Infrastructure14 pages

The services under the surfaces — routing, telemetry, scheduling, grounding, and identity plumbing.

Commerce & Business5 pages

Running a company on Riven: Commerce, the Business Suite, ERP, Mail, and Comms.

AI & Models6 pages

The API gateway, authentication, secrets, tools, and the model fleet behind them.

On-Prem Fleet2 pages

The sovereign inference fleet and the cloud models it falls back to.

Support

Accounts, billing, privacy, and troubleshooting.

What shipped, when.