Coding & apps

Denvr

Deploy dedicated single-tenant GPU VMs, bare-metal clusters, and OpenAI-compatible private AI inference endpoints billed per GPU-hour with zero per-token fees.

Pay-as-you-go

On-Demand (Pay-as-You-Go)

Pay as you go

0 free credits included; $250 USD minimum prepaid top-up billed by actual GPU, CPU, and storage runtime

Request an account at console.cloud.denvrdata.com, top up at least $250 USD via Stripe card to launch on-demand GPUs or private inference endpoints, or apply to AI Ascend for startup credits.

Card requiredChinese supportedCommercial useAPI available

Overview & quick start

Official docs

Custom model serving (vLLM / Ollama)

Configure quantization, context length, and batch size

OpenAI-compatible dedicated inference endpoints

Single-tenant hardware; drop-in OpenAI base URL replacement

Best for

AI engineering teams and startups training models or serving high-throughput private LLM endpoints on dedicated H100/H200/A100 GPUs without per-token charges.

How to get started

Request an account at console.cloud.denvrdata.com, top up at least $250 USD via Stripe card to launch on-demand GPUs or private inference endpoints, or apply to AI Ascend for startup credits.

Platforms & clients
OpenAI-Compatible Inference & Cloud API · CLI · Web Console · API
Region & network
GlobalOperated by Denvr Dataworks Corp. in Canada with owned data centers in Calgary (MSC1) and Houston (HOU1); open to global organizations and startups.
Payment & sign-in
Credit / debit card / InvoiceSign in: Email
Data & privacy
AI Ascend Startup Program: Not used for training;On-Demand (Pay-as-You-Go): Not used for training;Reserved Contracts: Not used for trainingCompliance: SOC 2 / GDPR
Rate limits
Unlimited tokens and sessions up to dedicated GPU capacity; zero per-token rate caps