| Hard budgets (team / key / user) (scored) | yes Budgets & spend controls (Standard and up); each API key can carry its own credit cap; workspaces per environment Source: openrouter.ai/pricing |
|---|---|
| Rate & spend limits (scored) | partial No plan-based limits on paid models (provider limits pass through); per-key credit caps act as spend limits Source: openrouter.ai/pricing |
| Cost attribution / chargeback tags (scored) | partial Per-key and per-workspace activity, logs and export Source: openrouter.ai/pricing |
| FOCUS export (scored) | no Activity logs & export; no FOCUS format documented Source: openrouter.ai/pricing |
| EU data residency option (scored) | yes EU in-region routing via eu.openrouter.ai on Business and Enterprise Source: openrouter.ai/pricing |
| Public pricing (scored) | yes Source: openrouter.ai/pricing |
| Open source | no Hosted service Source: openrouter.ai/pricing |
| Hosting | SaaS Source: openrouter.ai/pricing |
| Supported providers / models | 80+ providers (500+ models) Source: openrouter.ai/pricing |
| Caching | partial Provider prompt caching (Standard and up); no gateway response cache listed Source: openrouter.ai/pricing |
| Pricing model | Fee on credit purchases Source: openrouter.ai/pricing |
| Public price points | Standard 5.5% fee on credits; Business 8%; Enterprise discounts; inference at provider list price; BYOK: first $25k/mo list-price inference free, then 5% Source: openrouter.ai/pricing |
"unknown" means we could not confirm it in public sources. Vendors can send evidence to update a cell; see get verified. Verification never changes the scoring rules.