FAQ
Minutes: sign up (welcome credits, no card), create a key in Console → API Keys, point any OpenAI client at https://api.runaii.cloud/v1. See /docs and /cookbook.
New accounts get $5 in welcome credits — granted once your email is verified, and capped per network per day. Modal offers $30/mo compute and Koyeb offers startup credits — ours is smaller but instant, no sales call.
Any OpenAI-compatible client (Python, TypeScript, cURL) plus Anthropic-compatible clients at POST /api/messages. Plus our zero-dep runaii-cli.mjs — see /cli.
Billed per 1M tokens from the model card rate. Cached prompt prefixes bill at the cached rate automatically (up to 90% off). Batch API is in beta with no separate discount.
API calls return 402 with a top-up link. Set a hard spend limit in Settings and low-credit alerts via email + webhook.
Dodo Payments (cards) when configured; invoices and custom DPAs on Enterprise. Every charge lands in your ledger — see /console/billing.
Serverless scales to zero and bursts on demand; P50 cold start <800ms on H100. Dedicated deployments stay warm with autoscaling.
60 req/min per API key on welcome credits; 180 req/min after your first payment or card verification. 429s carry Retry-After and an X-Runaii-Rate-Limit header. Higher limits on Enterprise.
Pin GLOBAL / US / EU / APAC per workspace in Settings. EU/APAC carry a 15% premium. VPC/self-hosted on Enterprise.
Yes — dedicated deployments run your checkpoints with per-second billing, or train on runaii (SFT/DPO/RL) and deploy in seconds.