Volt documentation
Run 70B models in your customer's metro
The Sovereign Inference Cloud. OpenAI-compatible, zero egress, served in-metro. Start here.
Quickstart
Install the SDK, get a key, make your first request in under five minutes.
Concepts
Zero egress, the sovereign tier, tiers and catalogs — how Volt works.
Cookbook
Streaming chat, batch embeddings, sovereign isolation, and SDK quickstarts.
API reference
The full control-plane API for Spark, Forge, and Vault.
OpenAI-compatible API
Change the base URL and key. Your existing OpenAI client streams Llama 70B from a pod in your metro.
Sovereign by default
Zero ingress, zero egress, zero inter-pod transfer. Pin a metro, enforce the sovereign tier, and verify it client-side.
Ready to run frontier models in your metro?
Get an API key, point your OpenAI client at Volt, and serve Llama 70B in-metro with zero egress.