Runcrate vs Sesterce

Token-billed API calls and GPU hours draw on one credit balance with a single invoice, auto-recharge, and credits that do not expire

Chat, image, video, text-to-speech, speech-to-text and embedding models served behind OpenAI-compatible REST endpoints, so existing clients switch by changing the base URL

Bare-metal instances with SSH, Docker and custom images, provisioned in about 60 seconds

An unauthenticated endpoint publishes the live GPU rate card, refreshed every few minutes

Reserved bare-metal from 16 to 128+ nodes with NVLink fabric and managed Slurm job submission

Python and TypeScript SDKs, a Vercel AI SDK provider, a CLI for instance and volume management, and an MCP server for controlling the platform from AI assistants

Each site is operated as a single system, owning the hand-off between energy, facility, silicon, network fabric, and orchestration

French sites offering data residency, controlled energy origin, and supply-chain control, drawing on 2 GW of hydro, nuclear, and solar capacity secured under long-term PPAs

A joint venture with SoftBank Group to develop a 1 GW AI data center campus at Bosquel in Hauts-de-France

Single console and API to provision clusters, orchestrate training, serve inference, and meter usage across every Sesterce site, Slurm and Kubernetes native

Purpose-built Tier III+ facilities with direct-to-chip liquid cooling at up to 150 kW per rack, rated at PUE 1.12 under full AI load

Non-blocking NVIDIA Quantum InfiniBand at 800 Gb/s with rail-optimized topology and native RDMA