Models

Loading… · $0.05/1M cached · OpenAI-compatible

ModelContext Active params Input /1M Output /1M Cached /1MTTFT Throughput Uptime

Latency and throughput are medians over the last 24h. Uptime is a 30-day rolling average. Change base_url to https://api.pinstripes.io/v1 in any OpenAI SDK.