Riven documentation
Riven is a sovereign AI platform: 162 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 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
Create a key and make your first call in about two minutes.
QuickstartCopy-paste examples in curl, Python, and JavaScript — including streaming.
Authentication & keysIssue, rotate, and revoke rvn_ keys. Guest keys and rate limits.
Models & usageTier aliases, token multipliers, and how to read your quota.
API referenceEvery endpoint, parameter, response header, and status code.
Model fleetPer-model reference generated from the live gateway catalog.
The platform
The surfaces you sign in to: Console, Chat, Computer, Studio, Docs, and the rest of the shell.
The services under the surfaces — routing, telemetry, scheduling, grounding, and identity plumbing.
Running a company on Riven: Commerce, the Business Suite, ERP, Mail, and Comms.
The API gateway, authentication, secrets, tools, and the model fleet behind them.
The sovereign inference fleet and the cloud models it falls back to.