{"provider":"Prism","legalName":"Prism Technologies Inc","currency":"USD","billing":"prepaid","unit":"token","pricingPage":"https://prisminference.com/pricing","tiers":[{"id":"serverless","name":"Serverless endpoints","rateLabel":"Pay as you go","summary":"Per-token access to frontier open source models. Call an endpoint and go: zero setup.","features":["Frontier Open Source Models","No minimums","Community support"]},{"id":"elastic","name":"Elastic Endpoints","rateLabel":"Early access","summary":"Private, optimized endpoints priced per million tokens, with per-workload tuning.","features":["Private optimized endpoints","Per-workload tuning","Dedicated support"]},{"id":"dedicated","name":"Dedicated deployments","rateLabel":"Reserved capacity","summary":"Reserved GPUs sized to your roadmap, with negotiated latency SLAs.","features":["Reserved GPUs, sized to you","Negotiated latency SLA","Dedicated support"]},{"id":"batch","name":"Batch","rateLabel":"Lowest rate","summary":"High-throughput offline jobs at the lowest per-token rate, on spare fleet capacity.","features":["Lowest per-token rate","Millions of requests per job","Great for evals & embeddings"]}]}