Pricing
Not listed
Official monthly price not confirmed
- API
- Not confirmed
Assistant · Vendor site 2026-10-04
LLMKube is an open-source Kubernetes operator for self-hosted LLM inference across NVIDIA, Apple Silicon, and AMD hardware, supporting runtimes such as vLLM, llama.cpp, and mlx-server with CLI deployment, autoscaling, GPU sharding, and Grafana metrics.
Platform and ML teams that want Kubernetes-native orchestration for local or private-cloud LLM inference instead of per-token cloud APIs.
You supply clusters, GPUs, and operational expertise; LLMKube does not publish a hosted SaaS price list.
LLMKube targets teams scaling beyond single-machine Docker setups by adding HPA autoscaling, inference metrics, and pluggable LLM runtimes under Kubernetes control.
What it can do
Unknown is different from unavailable. Each fact carries its own evidence.
| Capability | Value | Evidence | Checked |
|---|---|---|---|
| Kubernetes operator | Homepage markets LLMKube as a Kubernetes operator for self-hosted inference with vLLM, llama.cpp, and related runtimes. | Facts sourced | 2026-10-04 |
| CLI deploy | Site shows llmkube CLI commands to deploy named models with selectable GPU runtimes. | Facts sourced | 2026-10-04 |
| Hardware support | Header badges list Kubernetes native support for NVIDIA, Apple Silicon, and AMD accelerators. | Facts sourced | 2026-10-04 |
Understand the total cost
Pricing
Not listed
Official monthly price not confirmed
Salesforce Service Cloud is customer service software that combines case management, self-service, analytics, and Agentforce AI agents on one CRM platform. It supports contact centers, field service, IT service, and AI-assisted support workflows for large organizations.
Explore toolAmboras is an AI-native ecommerce store builder that generates storefronts, runs promotions, and optimizes for sales without plugins or agencies. Pricing tiers scale from a free trial store through paid plans with higher AI credits, analytics, and multi-store limits.
Explore toolCRAISEE is a multi-model creative workspace that lets users run many image, video, audio, and text models from one prompt, compare outputs, and switch models instantly. Subscriptions provide monthly credits for generation across supported models with Flow workflow tooling.
Explore toolThe practical questions
LLMKube is an open-source Kubernetes operator for self-hosted LLM inference across NVIDIA, Apple Silicon, and AMD hardware, supporting runtimes such as vLLM, llama.cpp, and mlx-server with CLI deployment, autoscaling, GPU sharding, and Grafana metrics.
Project is described as open source on the homepage with public documentation and GitHub access.. This record does not confirm an ongoing free plan.
A listed monthly price has not been confirmed. See the plan cards for entitlements, billing commitments and seat minimums.
Not confirmed. API access and subscription access may have different terms; consult the linked sources.
You supply clusters, GPUs, and operational expertise; LLMKube does not publish a hosted SaaS price list.
No retained pricing changes yet. A current price alone does not establish a historical trend.
Reviewed vendor source
Read original source ↗Facts apply to the named version and check date. Send a sourced correction if something changed.