7 docs tagged with "inference"

Base models supported by Serverless Inference on Crusoe's Intelligence Foundry

Choose a Crusoe Managed AI product to run, adapt, or deploy AI models without managing GPU infrastructure

Learn which metrics Serverless Inference records for your models and how to query them with PromQL

Reserved-capacity inference deployments on Crusoe's managed infrastructure with predictable performance and no shared rate limits

Choose how to run inference on hosted models based on your traffic patterns and latency requirements

How Serverless Inference enforces tokens-per-minute and requests-per-minute limits, and how to interpret 429 and 503 responses

Usage and billing information for Serverless Inference, Serverless Fine-Tuning, and Self-Serve Deployments