Infrastructure — professional stack.
For each requirement below, pick the option that fits your build — recommended first, then free and cheaper alternatives — or skip what your project doesn't need. Tap the info icon next to any requirement to see why it matters.
GPU Compute Rental (A100 / H100 / B200 Fleet)
Where your code actually runs and serves requests. Picking the right host affects speed, scaling, and how much ops work you do.Pricing & free-tier limitsFree: Modal $30/mo credits, 1x T4/A10G dev; Colab T4 12h session. Paid: RunPod T4 $0.22/hr, A100 40GB $1.19/hr, H100 $3.49/hr; Lambda A100 $1.50/hr, H100 $3.99/hr (on-demand), $2.49/hr 1yr reserved; CoreWeave H100 $4.25/hr OD, $2.99/hr reserved, B200 $7.50/hr OD $4.99/hr 3yr; Overage: Idle keep-alive $0.05/hr, egress $0.08/GB
Bare Metal Provisioning & Fleet Management
Enterprise single sign-on and user provisioning. Usually required to sell to larger organizations.Pricing & free-tier limitsFree: MaaS self-hosted $0, Ironic open-source. Cheaper: Vultr BM from $120/mo (1x RTX 4000), Latitude.sh c3.large $0.75/hr. Paid: Equinix Metal c3.medium $0.85/hr ~$550/mo, GPU BM g2.large A100 $2,200/mo + $1.5/hr metering; OVH A100 BM €1,800/mo. Overage: Provisioning API $0.01/call after 10k/mo, support $500/mo
GPU Virtualization / Fractional GPU (MIG, vGPU)
Powers AI features — model access, embeddings, and inference. Costs scale with usage, so watch the meter.Pricing & free-tier limitsFree: KVM+MIG self-host $0, up to 7x MIG slices per A100/H100. Open tools free. Cheaper: Modal 0.1 GPU $0.15/hr fractional. Paid: Run:ai $0.45/GPU/hr license ($350/GPU/mo), VMware Bitfusion $500/GPU/mo. Overage: Extra MIG profile $0.10/slice/hr, Run:ai over-quota $0.55/GPU/hr
Kubernetes for GPU Workloads (GPU Operator & Scheduler)
Powers AI features — model access, embeddings, and inference. Costs scale with usage, so watch the meter.Pricing & free-tier limitsFree: K3s OSS $0, GPU Operator OSS $0 (self-manage). Cheaper: DOKS GPU $1.10/node/hr includes control plane $0. EKS $0.10/hr cluster + EC2 p4d H100 $4.56/hr. Paid: Run:ai $450/GPU/mo platform fee, OpenShift AI $0.50/GPU/hr. Overage: Karpenter scale-up 30s, extra control plane $0.10/hr, GPU Operator enterprise support $2k/mo
Serverless GPU Platform / Model Hosting Platform
Where your code actually runs and serves requests. Picking the right host affects speed, scaling, and how much ops work you do.Pricing & free-tier limitsFree: Modal $30/mo credits, 100 GPU sec free; Replicate free $5 credits, 500ms cold start. Cheaper: Baseten $0.0005/sec per A100 ($1.80/hr effective), Banana $0.00008/sec. Paid: Anyscale $1.00/hr worker + $1.50/A100/hr, Replicate $0.000725/s A100 40GB, Together $0.90/hr L4 + token pricing. Overage: Scale-to-zero wake $0.02, concurrent limit $5 per extra concurrency over 10
Inference Server Engine (vLLM, TGI, Triton)
Where your code actually runs and serves requests. Picking the right host affects speed, scaling, and how much ops work you do.Pricing & free-tier limitsFree: vLLM/TGI OSS $0, self-host on existing GPU. Cheaper: Ollama $0 + $10/mo managed. Paid: NVIDIA NIM $0.45/GPU/hr license ($1/hr with H100 included via NGC), Baseten $1.80/hr managed vLLM. Overage: 8k RPS license +$0.10/GPU/hr, enterprise support $3k/mo for Triton
Inference Autoscaling (Scale-to-Zero, KEDA)
Powers AI features — model access, embeddings, and inference. Costs scale with usage, so watch the meter.Pricing & free-tier limitsFree: KEDA/Knative OSS $0, scale-to-zero <2s on self-host. Cheaper: Fly.io scale-to-zero $0.10/hr min + $1.50/A100/hr active. Paid: Anyscale $50/mo autoscaler addon + GPU costs, Run:ai $100/GPU/mo autoscale license. Overage: KEDA queue lag scaling $0.001/s metric poll, excess scale events $0.02 per 1k over 100k/mo
Vector Database (Embedding Store for RAG)
Persistent storage for your app’s data — users, products, orders. The single most important architectural decision for most projects.Pricing & free-tier limitsFree: Qdrant OSS $0 unlimited self-host; Qdrant Cloud Free 1GB, 1M vectors, 1k QPS; Pinecone Free 100k vectors, 1 pod p1.x1. Cheaper: Qdrant Cloud $25/mo 5GB, Chroma $30/mo 5M vectors. Paid: Pinecone Starter $70/mo 1M vectors + $0.40/1M queries, $0.20/1M writes; Zilliz Standard $0.25/hr cluster. Overage: Pinecone $0.20 per 1M vectors over, Qdrant $5/GB over, $0.20/1M searches over 10M
Model Registry & Versioning (HuggingFace-like)
Powers AI features — model access, embeddings, and inference. Costs scale with usage, so watch the meter.Pricing & free-tier limitsFree: HF Hub Free: public models unlimited, private 1 model, 100GB bandwidth; MLflow OSS $0. Cheaper: W&B Free 100GB artifact. HF Pro $9/mo, 50 private models. Paid: HF Enterprise $50/user/mo, private unlimited, 2TB/mo bandwidth, SSO; CoreWeave registry $0.20/GB/mo stored. Overage: HF $0.10/GB bandwidth over 2TB, $0.05/GB storage over 500GB
Object Storage for Multi-GB Model Weights
Where you keep files users upload or you serve — images, videos, documents — and how fast they reach visitors around the world.Pricing & free-tier limitsFree: MinIO self-host $0, B2 Free 10GB storage. R2 Free 10GB store, 10M Class B ops/mo, zero egress. Cheaper: B2 $0.006/GB/mo, R2 $0.015/GB/mo store, $0 egress. Paid: S3 Standard $0.023/GB/mo store, $0.09/GB egress, $0.005/1k PUT; R2 $15/mo 500GB included. Wasabi $7.99/TB/mo no egress. Overage: S3 egress $0.09/GB, R2 $0 egress, ops $0.36/M, Wasabi over 1TB $7.99/TB
CDN / Edge Distribution for Model Weights
Where you keep files users upload or you serve — images, videos, documents — and how fast they reach visitors around the world.Pricing & free-tier limitsFree: Cloudflare Free: unlimited egress, 100GB R2 fetch free. Cheaper: Bunny CDN $0.01/GB, $1/mo min; CF Pro $20/mo 20% more edge. Paid: Fastly $0.12/GB first 10TB, $0.08/GB next, $50/mo min; Cloudflare Enterprise $5k/mo + custom bandwidth. Overage: Fastly $0.12/GB, Bunny $0.02/GB over 10TB, CF no overage on free but $0.05/GB cache reserve
Model Training Orchestration (Jobs & Queues)
Powers AI features — model access, embeddings, and inference. Costs scale with usage, so watch the meter.Pricing & free-tier limitsFree: Kubeflow OSS $0 self-host, Modal Jobs $30 credits. Cheaper: RunPod Jobs $0.20 setup + GPU $1.19/hr. Paid: Anyscale Jobs $0.25/hr orchestrator + GPU cost $1.50-3.99/hr, CoreWeave SUNK $0.10/hr management + GPU. Overage: Job retry $0.005/job, queue wait $0, failed job logs $0.20/GB, priority queue +25% GPU cost
Experiment Tracking & ML Metadata (W&B, MLflow)
Ships features to a subset of users or toggles them without redeploying. De-risks releases and enables experiments.Pricing & free-tier limitsFree: MLflow OSS $0 unlimited; W&B Free: 100GB, 3 team members, 10M logged steps. Cheaper: Neptune Free 200GB, W&B Teams Starter $50/mo 100GB + 10 users. Paid: W&B Teams $25/user/mo (min $250) + $0.50/GB over 250GB; Growth $50/user/mo. Databricks MLflow $0.15/DBU. Overage: W&B storage $0.50/GB/mo over, tracked hours $0.10/hr
Distributed Training Framework (Ray, NCCL, Deepspeed)
A piece of your stack you may or may not need, depending on scope. Pick the option that fits — or skip it if your project doesn’t require this capability yet.Pricing & free-tier limitsFree: DDP/DeepSpeed/Ray OSS $0 self-host. SkyPilot OSS free launcher. Cheaper: Modal distributed jobs $30 credits included then $1.50/hr. Paid: Anyscale Enterprise $400/mo + $0.40/hr worker overhead, CoreWeave IB fabric $0.30/hr per GPU IB addon. Overage: Cross-node NCCL traffic on-demand $0.02/GB on cloud, Anyscale extra workers $0.45/hr
Container Registry (GPU Optimized, Multi-arch)
Powers AI features — model access, embeddings, and inference. Costs scale with usage, so watch the meter.Pricing & free-tier limitsFree: GHCR 500MB storage free, 1GB transfer free public unlimited; Docker Hub free 1 private repo. Harbor OSS $0 self-host. Cheaper: Quay free 1 org, ECR free 500MB. Paid: ECR $0.10/GB/mo storage, $0.09/GB egress outside AWS; GAR $0.10/GB/mo; Docker Pro $24/mo 50GB. Overage: ECR storage $0.10/GB/mo, egress $0.09/GB over 1GB free, API $0.60/M
Container Security & Image Scanning
Where you keep files users upload or you serve — images, videos, documents — and how fast they reach visitors around the world.Pricing & free-tier limitsFree: Trivy/Grype OSS unlimited scans $0, Scout free 3 repos. Cheaper: Anchore free 10 images. Paid: Snyk $25/dev/mo container scanning, 200 images/mo; Wiz $0.30/container/mo min $500/mo; Aqua $1/container/mo. Overage: Snyk $0.15/image scan over 200, Wiz $0.40/container over, vuln DB $20/mo
CI/CD for Model & Infra Deployment (GPU builds)
Automates testing and deploying your code. Saves enormous time and prevents “works on my machine” releases.Pricing & free-tier limitsFree: GHA Free 2000 min/mo (2-core), ArgoCD $0 self-host. Cheaper: GitLab Free 400 min GPU (shared runners). Paid: GitHub Team $4/user/mo + GPU runner self-host cost; Buildkite $15/user/mo unlimited minutes + Own GPU runner $50/mo; CircleCI GPU $0.08/credit (A100 ~2c/min). Overage: GHA $0.008/min Linux, GPU self-host $1.50/hr build, ArgoCD support $2k/mo
GPU Monitoring (Utilization, DCGM, Health, Xid)
Tells you when things break and why. You cannot fix what you cannot see — this is how you keep downtime short.Pricing & free-tier limitsFree: DCGM/Prom/Grafana OSS $0 self-host unlimited metrics. Cheaper: Netdata Cloud free 5 nodes. Paid: Datadog Infrastructure Pro $15/host/mo + custom metrics $0.05/100 metrics, GPU monitoring included; New Relic $0.30/GB ingest; Run:ai $150/GPU/mo monitoring. Overage: Datadog $0.30/GB logs, $0.05/100 custom metrics over 100, APM $31/host/mo
Inference Observability (Latency, Tokens/sec, Traces)
Tells you when things break and why. You cannot fix what you cannot see — this is how you keep downtime short.Pricing & free-tier limitsFree: Langfuse OSS $0 self-host unlimited; Cloud Free 50k traces/mo. Helicone Free 10k requests/mo, 30d retention. Cheaper: Langfuse Cloud $39/mo 100k traces, Helicone Pro $20/mo 250k req. Paid: Langfuse Pro $99/mo 500k traces, $0.30/1k over; Helicone Teams $199/mo 5M req, $0.05/1k over. Overage: Langfuse $0.40/1k traces over quota, 90d retention +$50/mo
Centralized Logging / SIEM for Infra (Loki/ELK)
Keeps you secure and compliant with regulations. Required for enterprise customers and handling sensitive data.Pricing & free-tier limitsFree: Loki OSS $0, 50GB local storage. Better Stack free 30GB/mo 3d retention. Cheaper: Logtail $28/mo 20GB, 7d retention. Paid: Datadog Log $0.10/GB ingest $0.16/GB 15d retention, Elastic Cloud $95/mo 2GB RAM + $0.10/GB ingest; Splunk $70/mo 5GB. Overage: Loki Cloud $0.50/GB over, Datadog $0.20/GB over 100GB, Elastic $0.12/GB over
Multi-Region Deployment & Global Load Balancer
Automates testing and deploying your code. Saves enormous time and prevents “works on my machine” releases.Pricing & free-tier limitsFree: CF LB free 2 origins, health checks 10s. Fly free 3 regions. Cheaper: CF Pro LB $5/mo per origin, Fly $0.10/hr per region overhead. Paid: AWS Global Accel $0.025/hr + $0.015/GB + $0.025/hr per endpoint, Cloudflare Enterprise $500/mo LB. Overage: Health checks $0.50/10k over 100k, failover $0.02/event, cross-region bandwidth $0.08/GB
API Gateway for Inference Endpoints
Controls and protects your APIs — quotas, abuse prevention, and firewalls. Important once you have real traffic or many clients.Pricing & free-tier limitsFree: Kong OSS $0 unlimited traffic self-host; CF API GW free 100k calls. Tyk CE 1 gateway free. Cheaper: Kong Konnect free tier 1M req/mo. Paid: Kong Enterprise $3k/mo or $0.02/1k req ($2.50/M), AWS API GW $3.50/M REST, HTTP API $1.00/M. Tyk Cloud $300/mo 1M calls. Overage: AWS $3.50/M over, Kong $0.02/1k over 10M, $50/month workspace
Usage Metering (GPU-seconds, tokens, storage)
Where you keep files users upload or you serve — images, videos, documents — and how fast they reach visitors around the world.Pricing & free-tier limitsFree: OpenMeter OSS $0 unlimited events, self-host ClickHouse. Cloud free 10M events/mo. Cheaper: OpenMeter Starter $49/mo 100M events. Orb free 10M events trial. Paid: OpenMeter Pro $199/mo 1B events, $0.15/M over; Orb $400/mo + $0.10/M; Metronome $500/mo base + usage. Overage: $0.15 per 1M metering events over, aggregation query $0.01 per 1k queries
Usage-Based Billing & Subscriptions (Stripe)
Moves money — charges, payouts to sellers, taxes, fraud checks. Highest-stakes integration: get it wrong and you break compliance or lose revenue.Pricing & free-tier limitsFree: Lago OSS $0 self-host, Stripe Billing free 0.5% on billing volume < $1M. Lago Cloud free 10k customers. Cheaper: Lago $50/mo Starter 20k events. Paid: Stripe Billing 0.5-0.7% of recurring revenue + $0.20/invoice, Orb $400/mo + 1% over $100k; Metronome $0.40 per invoice. Overage: Stripe $0.4% over $1M, Orb $0.50 per 1k invoices over 50k
Identity, API Key & Tenant Management (Multi-tenant)
How users sign up, log in, and are authorized. Getting roles and access control right early prevents painful rewrites.Pricing & free-tier limitsFree: Clerk 10k MAU free, Auth0 free 25k MAU & 7.5k M2M tokens, Supabase Auth free 50k MAU. Cheaper: Clerk Pro $25/mo 10k MAU + $0.02/MAU over, Auth0 B2C essentials $35/mo. Paid: Auth0 $0.07/MAU over 25k, WorkOS $125/mo base + $0.05/seat, SSO $0.40/SSO connection. Enterprise $1k/mo min. Overage: Clerk $0.02/MAU over, Auth0 MFA $0.05/attempt, SSO $0.50/connection
Rate Limiting & Quota Enforcement (per tenant/GPU)
Powers AI features — model access, embeddings, and inference. Costs scale with usage, so watch the meter.Pricing & free-tier limitsFree: Redis OSS $0 self-host, Upstash Free 10k commands/day, 10k rate limit req/day. Cheaper: Upstash $10/mo 100k req/day, CF free 1 rule 10s/10req. Paid: Upstash Pay-as-you-go $0.20/100k commands, Redis Cloud $15/mo 30MB + $0.10/10k ops; Cloudflare $5/mo per 10k good req. Overage: Redis Cloud $0.40/GB transfer over, Upstash $0.30/100k over, CF RL $0.05/10k over
DDoS Protection & WAF for Inference API
Controls and protects your APIs — quotas, abuse prevention, and firewalls. Important once you have real traffic or many clients.Pricing & free-tier limitsFree: CF free unlimited DDoS, 5 WAF rules free, Shield Standard free auto. Cheaper: CF Pro $20/mo 20 rules, WAF managed rules $5/mo. Paid: CF Enterprise $5k/mo unlimited WAF + DDoS, Fastly WAF $0.30/1k req min $500/mo, Shield Advanced $3k/mo + $0.05/GB. Overage: CF $1 per 10k blocked threats over 1M, Shield Advanced data transfer $0.02/GB over
Secrets Management for Model Keys & API Tokens
Powers AI features — model access, embeddings, and inference. Costs scale with usage, so watch the meter.Pricing & free-tier limitsFree: Vault OSS $0 self-host, Infisical OSS unlimited secrets, Doppler free 3 projects. Cheaper: Doppler Starter $8/mo 200 secrets. Infisical Cloud free 10k secrets. Paid: Vault Cloud $0.03/hr cluster $22/mo, AWS Secrets $0.40/secret/mo + $0.05/10k API calls, Doppler Teams $12/user/mo. Overage: AWS $0.40/secret over 50, Vault $0.03/hr, audit log $0.10/GB
Status Page & Uptime Monitoring (Infra Uptime)
Tells you when things break and why. You cannot fix what you cannot see — this is how you keep downtime short.Pricing & free-tier limitsFree: Upptime $0 (GitHub Actions), Uptime Kuma OSS unlimited checks. Instatus Free 1 status page. BetterStack Free 10 monitors 3min interval. Cheaper: Instatus Startup $29/mo 2 pages 500 subscribers. Paid: Statuspage Startup $29/mo 250 subs, Growth $99/mo 1k subs; Instatus Growth $99/mo 5 pages; BetterStack $28/mo 100 monitors. Overage: Instatus $0.10/sub over 1k, SMS $0.05/SMS, monitors $0.20/monitor over
Support / Ticketing & Customer Portal API
Understands your users and supports them. Drives product decisions and retention.Pricing & free-tier limitsFree: Tawk.to free unlimited agents, Crisp free 2 seats 1 website. Plain free 5 seats 1k customers. Cheaper: Crisp Mini $25/mo 2 seats, Plain Startup $39/mo. Paid: Intercom Starter $74/mo, Growth $115/mo per seat; Zendesk Suite Team $55/agent/mo; Plain Growth $199/mo. Overage: Intercom $0.99 per 1k extra contacts over 2k, $0.01 per resolution over 500
How this professional infrastructure checklist works.
Each requirement below is something a professional infrastructure build typically needs. Pick one of the four researched options — recommended, free, cheaper or paid — add your own with "Other", or skip the requirement if your project doesn't need it. Nothing is mandatory; the plan on the right tracks what you've decided so nothing gets forgotten.
Your picks are saved in this browser automatically, so you can come back anytime. Options are researched per build level and refreshed as vendors change their plans — always verify details on the provider's page before committing.