ModelCloud runs your models on managed GPU fleets — inference, training, observability, and fleet management — without you operating a single server.
From a single serving endpoint to a dedicated, compliance-ready fleet. Each product stands alone or composes with the others.
Serve any open-weights or fine-tuned model behind one OpenAI-compatible endpoint.
Fine-tune and train across many GPUs with checkpointing and deterministic resume.
Latency, throughput, token accounting, and cost attribution per model and deployment.
Run dedicated and reserved capacity with VPC peering, quotas, and role-based access.
Start free, scale per GPU-hour, or commit to reserved capacity at a discount.
| Plan | Starter | Production | Enterprise |
|---|---|---|---|
| Pricing | $0 /mo | $1.90 / GPU-hr + $49/mo | Custom / annual |
| Included |
|
|
|
| Support & SLA |
|
|
|
Industry scenarios, not case studies. No names, no logos — just the workloads.
A payments team runs fraud-detection models that must score a transaction in milliseconds. They keep warm replicas in three regions, peer a VPC for data isolation, and pay only for the GPUs serving during settlement windows.
A robotics team ships defect-classification models that run against conveyor cameras. Autoscaling tracks shift schedules, and the observability product attributes token cost down to each camera line.
A legal-tech product reviews contracts in overnight batches on spot capacity, resuming from checkpoint on interruption, with the entire workload held inside a VPC for client confidentiality.
Bring weights, point the CLI at them, and get an OpenAI-compatible endpoint back.
# install the CLI curl -fsSL https://modelcloud.cloud/install.sh | sh # deploy your model modelcloud deploy ./qwen2.5-7b --gpu h100 --min 0 --quantize fp8 # call it curl https://api.modelcloud.cloud/v1/chat/completions \ -H "Authorization: Bearer $MODELCLOUD_KEY" \ -d '{"model":"qwen2.5-7b","messages":[{"role":"user","content":"hi"}]}'
We moved a serving stack that took two engineers a week to babysit. Now it autoscales and we read the dashboard instead of the pager.
Cold starts used to dominate our tail latency. Warm pools got us where our users expect us to be.
The VPC and compliance posture is what let us sign enterprise clients. That part matters as much as the GPUs.
Start on the free tier and scale to a dedicated fleet when you need it.
Get started