Google Kubernetes Engine (GKE)
Run and scale open models on managed Kubernetes clusters with Google Cloud GPUs and TPUs.
Overview
Google Kubernetes Engine (GKE) is Google Cloud's managed Kubernetes service. It's a popular way to serve open models at scale with servers like vLLM, automatically adding GPU or TPU nodes as traffic grows. You pay for the underlying machines and GPUs per hour, plus a small cluster management fee.
Specifications
| Hosting type | GPU cloud |
|---|---|
| Model families | gpt-oss, Qwen, DeepSeek, Llama, Gemma, Mistral |
| LLM models | gpt-oss-120b, Qwen2.5 72B Instruct, DeepSeek-V3, Llama 3.3 70B Instruct, Llama 3.1 8B Instruct, gpt-oss-20b, Gemma 3 27B, Gemma 3 12B, Gemma 3 4B, Gemma 2 27B, Gemma 2 9B, Qwen3 30B-A3B, Qwen3 32B, Qwen3 235B-A22B, Qwen2.5-Coder 32B Instruct, DeepSeek-V3.1, DeepSeek-R1, Codestral 22B, Mistral Small 3.1, Mistral NeMo |
| Pricing range | From US$0.35 |
| Pricing model | Per GPU-hour, Reserved or committed capacity |
| Free tier available | No |
| Data center locations | United States, Canada, Brazil, Chile, Mexico, Belgium, Netherlands, Germany, Finland, United Kingdom, France, Italy, Spain, Switzerland, Poland, Sweden, Israel, Qatar, Saudi Arabia, South Africa, India, Japan, South Korea, Taiwan, Hong Kong SAR China, Singapore, Indonesia, Australia |
| Hardware / GPU options | NVIDIA T4, L4, A100, H100, H200, B200 and GB200 GPUs, plus Google Cloud TPUs (v5e, v6e Trillium and later). |
| VRAM & memory | 16 GB – 180 GB |
| Maximum model size | 671B |
| OpenAI-compatible API | No |
News about Google Cloud
All news →LLM Hosting Roundup: Anthropic’s capacity crunch, Vera Rubin and DeepSeek’s $15B (23 Oct 2026)
Anthropic's hunt for cloud capacity, NVIDIA's DSX POD and new Vera Rubin inference benchmarks, Dell's first Groq 3 rack, DeepSeek's reported $15B raise and Reflection's open-weights Beam model.
