Deploy and scale on
the AI cloud
Inference and compute, one platform. Pay-per-token API on every open-source model. Per-second GPU compute. Dedicated capacity when the rate card starts to hurt.
● Inference first · Compute when you need it
Trusted by teams at
Inference API
Inference Engine
200+ models across chat, code, image, video, audio, and more. One endpoint, every provider.
Chat & Reasoning
80+ models
Code Generation
25+ models
Image Generation
30+ models
Video & Motion
15+ models
Audio & Speech
20+ models
Vision & OCR
15+ models
Embeddings
12+ models
Transcription
8+ models
Infrastructure
Compute
Raw bare metal. Full root access. Pick your hardware, deploy in 60 seconds. Per-minute billing. Scale from 1 node to 128.
Available Hardware
Current fleet
Performance
Key specs
Root Access
Full control over your environment. SSH, Docker, custom images.
Auto-scaling
Scale horizontally on demand. Add nodes in seconds, release when done.
Pay Per Minute
No minimum commitments. Spin up for 5 minutes or 5 months.
Platform
Everything you needto ship faster.
01 / 05
Stop paying for idle GPUs.
You're billed by the minute. Stop an instance, stop paying. It's that simple.
Self-Serve
Deploy instantly,scale effortlessly.
Everything you need to build, monitor, and scale your AI workloads — no DevOps expertise required.
Browser IDE
VS Code Server, Jupyter notebooks, and terminal — all pre-configured in browser.
Live Monitoring
Real-time GPU metrics, spend tracking, and uptime dashboards for every workload.
Secure Access
SSH keys, encrypted connections, and role-based team permissions built in.
Pricing
vs. AWS, GCP, and Azure. No hidden fees, no egress charges.
Live GPU rates
Updated nowWhy Runcrate
One platform for everyAI compute need.
AI teams shouldn't have to choose between cheap and reliable. Between managed and flexible. Between one provider and five contracts.
We built Runcrate to be the single platform for every AI compute need. Deploy a model endpoint in seconds. Spin up bare metal for training. Reserve a 128-node cluster for production.
All from one dashboard, one API, one invoice.