Plans & Pricing
Capacity planning tools for production multi-GPU clusters, high-concurrency SLA verification, and procurement documentation.
Basic
$0 /month
Free forever
Inference estimation and fine-tuning on local hardware.
- VRAM allocation and token throughput estimation
- Local inference and parameter-efficient fine-tuning
- Memory offloading, quantization, and runtime diagnostics
- API and MCP server access
- Standard ad-supported experience
Pro
$19 /month
Billed monthly · Cancel anytime
Production multi-GPU servers and standard clusters.
- Full datacenter and workstation GPU catalog
- Production concurrency and batch scaling
- Multi-GPU server and distributed topology modeling
- Workload SLA target optimization
- Ad-free experience
Pro+
$99 /month
Billed monthly · Cancel anytime
High-concurrency fleets and rack-scale deployments.
- Everything in the Pro plan
- High-scale fleet concurrency and large-batch capacity planning
- Hyperscale multi-node and rack-scale cluster topologies
- Multi-GPU host and cluster node configurations
- High-capacity API and MCP server rate limits