LLM Hosting Plans
Every plan we track, with its provider, pricing model and the LLMs it can run.
| Plan | LLM host | Type | Pricing range | Model families |
|---|---|---|---|---|
| Amazon EC2 | Amazon AWS | GPU cloud | From US$0.526Per GPU-hour, Reserved or committed capacity | Mistral, DeepSeek, Gemma, gpt-oss, Llama, Qwen |
| Amazon SageMaker | Amazon AWS | Dedicated endpoint | From US$0.736Per GPU-hour, Reserved or committed capacity | Llama, Mistral, DeepSeek, Qwen, Gemma, gpt-oss |
| Azure GPU Virtual Machines | Microsoft Azure | GPU cloud | From US$0.526Per GPU-hour, Reserved or committed capacity | gpt-oss, Qwen, DeepSeek, Llama, Gemma, Mistral |
| Azure Kubernetes Service (AKS) | Microsoft Azure | GPU cloud | From US$0.526Per GPU-hour, Reserved or committed capacity | gpt-oss, Qwen, DeepSeek, Llama, Gemma, Mistral |
| Azure Machine Learning | Microsoft Azure | Dedicated endpoint | From US$0.526Per GPU-hour, Reserved or committed capacity | gpt-oss, Qwen, DeepSeek, Llama, Gemma, Mistral |
| Cloudflare Workers AI | Cloudflare | Serverless API | From US$0.045Pay per token | Llama, Mistral, Qwen, gpt-oss |
| Compute Engine | Google Cloud | GPU cloud | From US$0.35Per GPU-hour, Reserved or committed capacity | gpt-oss, Qwen, DeepSeek, Llama, Gemma, Mistral |
| Google Kubernetes Engine (GKE) | Google Cloud | GPU cloud | From US$0.35Per GPU-hour, Reserved or committed capacity | gpt-oss, Qwen, DeepSeek, Llama, Gemma, Mistral |
| Model Garden | Google Cloud | Serverless API | US$0.07 – US$5.4Pay per token, Per GPU-hour | Llama, Mistral, DeepSeek, Qwen, gpt-oss, Gemma |
Are you a LLM Hosting provider? Submit your plans.