us-east, us-west, eu-west (Frankfurt), eu-south (Madrid), ca-central (Toronto) and sa-east (São Paulo). Median latency 9–18 ms across the US, Canada, EU and LATAM.
Yes. SDKs, fields, streaming responses, function calling and tool use are identical — just point base_url at api.alloneia.com/v1. Claude and Gemini are exposed through the same OpenAI-compatible schema.
Pay-as-you-go per token, priced at the same rate as the upstream provider. No monthly fee, no minimum spend, no account bans. Per-call usage is visible in real time and exportable as CSV or PDF invoice.
Credit and debit cards (Stripe), PayPal, ACH/SEPA wire, and USDT (TRC20/ERC20). Top up from $5.
Prices are public and only adjusted with 30-day notice. Multi-vendor redundancy: if one upstream provider rate-limits or fails, requests route to the next available endpoint.
Sign up with email and we credit your account with $2.50 — enough to validate the integration and try every model.
Dedicated key pools, usage alerts, role-based sub-accounts, EU/US invoicing, and a private Slack/Discord channel with the team. Contact sales for enterprise pricing.
Three minutes from sign-up to your first response.
Sign up free and get $2.50 in credit. No card required.