OpenRouter Pricing: Input and Output Token Rates
OpenRouter charges official API prices plus a markup fee that varies by model, typically between 5-20% over the base rate. For GPT-4o, that.
OpenRouter charges official API prices plus a markup fee that varies by model, typically between 5-20% over the base rate. For GPT-4o, that.
293ms median latency across 311 models is the fastest measured response time of any multi-model gateway I've tested from a Beijing Unicom node..
OpenRouter lists 311 models as of May 2026; the standout additions from the current lineup are GPT-5.5 and Claude Opus 4.7 . Model Coverage &.