Open-source InferCrane in your environment.
Launch pricing
Start open. Pay when it earns its place.
InferCrane is currently in private preview. Approved teams pay no platform fee while we qualify real workloads together. Final hosted pricing will be published before billing begins.
Compare launch plans ↓How the bill works
Know exactly what creates the bill.
Subscription pricing begins only after preview terms are published.
Your BYOC cloud, GPU, storage, and model API charges remain yours.
Future managed compute will be metered separately. It will not be hidden inside the control-plane subscription.
Choose your operating model
One product. Three ways to adopt it.
Open SourcePublic launch
Freeopen-source software
Run InferCrane in your environment and keep full control of the stack.
- CLI, API, SDKs, and Terraform workflows
- Stable endpoints and existing-workload adoption
- Durable deployment, scaling, and recovery
- Request evidence and guarded releases
- Your cloud, cluster, runtimes, and provider accounts
Cloud PreviewSelected teams
Freeduring private preview
Use the hosted operating experience while we qualify it with real workloads.
- Hosted control plane and operational console
- Organization, project, and environment workflows
- Monitoring, alerts, optimization, and cost evidence
- Guided onboarding and qualification support
- No automatic billing and no production SLA during preview
EnterpriseDesign partners
Customannual agreement at GA
Shape the private deployment, security, and support model your platform needs.
- Private or self-hosted control-plane options
- BYOC networking and workload identity requirements
- Project and environment authorization boundaries
- Backup, restore, and upgrade qualification
- Provider and runtime qualification support
Common questions
Know the boundaries before you join.
01Why are hosted GA prices not listed yet?
InferCrane is in private preview. We are measuring support cost, control-plane load, and the value of the operating workflows with design partners before setting a durable public price. No approved preview user will be billed automatically, and commercial terms will be shared before GA.
02What would I pay for during the private preview?
There is no InferCrane platform fee for selected preview teams. You remain responsible for GPU infrastructure, storage, networking, and external model APIs in your own accounts.
03Does InferCrane add a per-token fee to my own infrastructure?
No. BYOC infrastructure and external model-provider charges remain between you and those providers. The planned hosted control plane will use subscription pricing instead of adding a token markup to infrastructure you already pay for.
04Does InferCrane provide GPUs?
Not in the current preview. Today InferCrane operates compute in your AWS, GCP, Kubernetes, or supported provider account, or connects inference you already run. Managed InferCrane compute is planned as a separate, usage-metered option after the BYOC path is qualified.
05Can I self-host InferCrane?
Yes. The open-source distribution is intended to run in your environment. Enterprise design partners can also help define the operational and support requirements for private control-plane deployments.
06Do I need to migrate my existing vLLM, SGLang, or gateway setup?
No. You can begin by connecting a compatible endpoint in observe-only mode. InferCrane can earn additional traffic and lifecycle ownership later without requiring a day-one replacement.
07Which models can I run?
InferCrane can work with models supported by the selected runtime or external endpoint. Every exact artifact, runtime, GPU, and workload combination still needs qualification before performance or reliability claims are trusted.
08What happens to prompts, credentials, and request data?
Credentials remain server-side and ordinary telemetry does not retain prompt or response content by default. Your chosen infrastructure and model providers still have their own data-handling policies, which remain part of the deployment decision.
09Is there a production SLA during private preview?
No. The current preview is for qualification and design-partner use. Production SLAs, support levels, and final enterprise terms will be defined for GA after the relevant infrastructure paths are proven.
Private preview
Bring one real workload. Shape the right plan.
Join the waitlist for launch updates and consideration for a preview invitation. No credit card and no automatic billing.