Observed arrival · 2026-09-22
Runaii Cloud Wants You to Own Your Inference
A public-beta cloud platform for serverless LLM inference, dedicated Blackwell GPUs, and managed training through an OpenAI- and Anthropic-compatible API.
- For
- Developers building applications on open LLMs
- Worth noticing
- The homepage lists 15 models with token prices, context windows, cached-input rates, and claimed output speeds.
Field notes
The homepage organizes the service around three layers: serverless model calls, dedicated GPU capacity, and managed training. Its catalog includes language models alongside embeddings, rerankers, Whisper, and FLUX, while code examples show a conventional chat-completions request authenticated with a RUNAII_API_KEY. Pricing is unusually exposed for an AI infrastructure landing page, including separate cached-input figures and a no-card signup credit.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
One card from the complete issue