All systems operational
changelog v3.2.0 · status.modelcloud.cloud
MModelCloud
Sign in Get started
Menu
Platform
Inference Training Observability Fleet
Solutions
Solutions by industry
Developers
Documentation Quickstart Changelog
Company
About Customers Pricing
Get started
Model hosting & inference cloud

You bring the model,
we run it.

ModelCloud runs your models on managed GPU fleets — inference, training, observability, and fleet management — without you operating a single server.

Deploy a model Explore the platform
Autoscaling to zero Warm pools for cold starts VPC private connectivity
modelcloud — deploy
$ modelcloud deploy ./qwen2.5-7b target h100 · replicas 0–8 · region us-east quantize fp8 · warm pool on   ✓ built · pushing weights… ✓ endpoint ready https://api.modelcloud.cloud/v1 $ curl https://api.modelcloud.cloud/v1/chat/completions
The platform

Four products, one GPU fleet

From a single serving endpoint to a dedicated, compliance-ready fleet. Each product stands alone or composes with the others.

01 / INFERENCE GA

Inference

Serve any open-weights or fine-tuned model behind one OpenAI-compatible endpoint.

  • Autoscale replicas from zero to demand
  • Warm pools to cut cold starts
  • FP8 / INT8 / INT4 quantization
View inference → 02 / TRAINING Beta

Training

Fine-tune and train across many GPUs with checkpointing and deterministic resume.

  • Distributed multi-GPU jobs
  • Spot capacity with auto-reschedule
  • Resume from any checkpoint
View training → 03 / OBSERVABILITY GA

Observability

Latency, throughput, token accounting, and cost attribution per model and deployment.

  • Per-model latency & throughput
  • Token and cost accounting
  • Export logs and traces to your stack
View observability → 04 / FLEET GA

Fleet

Run dedicated and reserved capacity with VPC peering, quotas, and role-based access.

  • VPC peering and private connectivity
  • Quotas and role-based access
  • Compliance posture (SOC 2, HIPAA, GDPR)
View fleet →
modelcloud console — deployments & fleet
ModelCloud console showing the deployment matrix and GPU fleet overview
Pricing

Pay for the GPUs you use, not for idling

Start free, scale per GPU-hour, or commit to reserved capacity at a discount.

PlanStarterProductionEnterprise
Pricing $0 /mo $1.90 / GPU-hr + $49/mo Custom / annual
Included
  • 40 GPU-hours / month
  • 2 concurrent models
  • Shared capacity
  • Autoscaling to zero
  • Warm pools
  • Priority queue
  • Reserved or dedicated fleet
  • VPC peering
  • Compliance (SOC 2, HIPAA, GDPR)
Support & SLA
  • Community support
  • Best effort
  • Email support
  • 99.9% SLA
  • Dedicated support & SSO
  • 99.95% SLA
Full pricing details →
Customers

How teams run on ModelCloud

Industry scenarios, not case studies. No names, no logos — just the workloads.

Financial services

Real-time fraud scoring

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.

sub-100msVPCmulti-region
Robotics & logistics

Vision on the warehouse floor

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.

shift-aware autoscalingcost attribution
Legal & compliance

Document review at volume

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.

spot capacitycheckpointingVPC
Read all customer stories →
Developers

Deploy in three commands

Bring weights, point the CLI at them, and get an OpenAI-compatible endpoint back.

QuickstartCLIOpenAI-compatible
# 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"}]}'
Read the docs →
What teams say

Built for people who run models in production

“
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.
Sarah CohenStaff ML Engineer, logistics platform
“
Cold starts used to dominate our tail latency. Warm pools got us where our users expect us to be.
Diego AlvarezHead of Platform, fintech startup
“
The VPC and compliance posture is what let us sign enterprise clients. That part matters as much as the GPUs.
Emily WatsonCTO, legal-tech product

Bring your model. We'll run it.

Start on the free tier and scale to a dedicated fleet when you need it.

Get started