Inference API Logo

Enterprise Plan

We offer custom enterprise plans with SLAs, dedicated resources and infrastructure, auto-scaling, and lower marginal costs based on volume. Starts at $2k/mo with annual contracts. Please share more information about your requirements and our sales we’ll be in touch.​

SLAs

SLAs

Production level support, 24/7 SLAs and uptime guarantees.
Infrastructure

Infrastructure

Auto-scaling and dedicated resources to achieve desired latency and throughput.
Large Models Support

Large Models Support

Dedicated infrastructure and maintenance to support large models (>10gb).
Lower Marginal Costs

Lower Marginal Costs

Lower marginal costs based on volume and yearly contract commitment.