Runcrate
On-demand GPUs and inference for AI teams, and for the agents they run
Runcrate rents GPUs by the second on most models, from $0.36 per GPU-hour, and sells 125 models behind one OpenAI-compatible API, with one prepaid balance paying for both. Instances come with SSH, Jupyter and VS Code in the browser, and booting is never billed. Multi-node clusters can be reserved for a month or longer. Instances and models may run on infrastructure operated by partners. Operated by Aeonmind, LLC, a Delaware company.
Pricing: Pay-as-you-go
Choosing a GPU cloud right now?
One click, anonymous. Helps us know our visitors.
Thanks, that helps.
Choosing a GPU cloud right now?
One click, anonymous. Helps us know our visitors.
Thanks, that helps.
Runcrate prices by model
Per 1M tokens, read off Runcrate's own pricing page on the date shown.
| Model | Input / 1M | Cached / 1M | Output / 1M | Checked | Notes |
|---|---|---|---|---|---|
| Kimi K3 | $2.99 | $0.299 | $14.96 | 3 Nov 2026 |
Runcrate Alternatives
Explore 157 products in the Inference APIs category. View all Runcrate alternatives.
CoreWeave
GPU cloud infrastructure built for large-scale AI training and inference workloads
Hetzner GPU Servers
Dedicated single-GPU servers with NVIDIA RTX PRO Blackwell cards, billed hourly, in Finland and Germany
inference shell
One API key for any AI model, with skills, agents and a CLI
Work on Runcrate? Feature it at the top of Inference APIs.
Is your product missing?