DashboardContact Sales
⌘K

Vultr Docs

Everything you need to build, deploy, and scale on The Everywhere Cloud: product guides, references, and AI model docs in one place.

Start Building on The Everywhere Cloud. Ask Anything.

Ask about configs, errors, deployment steps, pricing, or anything else.

Product Documentation

Configure and deploy Vultr products like Compute, GPU, storage and networking.

Platform Documentation

How the Vultr platform works including account, billing and regions.

Support Documentation

Find solutions, troubleshooting tips and answers to common questions.

Reference Documentation

Technical reference covering API, CLI, Terraform Provider and SDKs.

Latest Guides & Articles

Explore Article & Guides
Reference Guide

How to Upgrade a Vultr Managed Database for PostgreSQL v14 to a Stable Version

Upgrade a Vultr Managed Database for PostgreSQL v14 to a newer stable version using cluster forking, testing, and a safe primary upgrade with a read replica.

Updated 20 Aug, 20269 min read
Hyperscaler Replacements

How to Deploy Apache Kafka as an AWS Kinesis Data Firehose Alternative

Deploy Apache Kafka with Strimzi on Kubernetes as a self-hosted Amazon Data Firehose alternative with Kafka Connect, S3 sinks, transformations, security, and monitoring.

Updated 6 Aug, 202633 min read
Hyperscaler Replacements

How to Deploy Apache Pulsar as a Google Pub/Sub Alternative

Deploy Apache Pulsar as a self-hosted Google Pub/Sub alternative with Docker, multi-tenancy, Pulsar Functions, IO connectors, and JWT authentication.

Updated 4 Aug, 202615 min read
Hyperscaler Replacements

How to Deploy Lustre as an AWS FSx Alternative

Deploy a self-hosted Lustre file system as an AWS FSx alternative with parallel storage, LNET networking, monitoring, high availability, and S3 integration.

Updated 10 Aug, 202622 min read
Hyperscaler Replacements

How to Deploy CephFS as a GCP Filestore Alternative

Deploy CephFS on a Kubernetes Engine cluster using Rook with dynamic storage provisioning, NFS exports, snapshots, authentication, and monitoring.

Updated 10 Aug, 202624 min read
Hyperscaler Replacements

How to Deploy ElasticMQ as an AWS SQS Alternative

Deploy ElasticMQ as a self-hosted AWS SQS alternative using Docker, Traefik, HTTPS, persistent queues, dead-letter queues, and a web UI.

Updated 4 Aug, 202613 min read

Latest Models

See All Models

DeepSeek V4

DeepSeek V4 Flash Vision Exp is a multimodal Mixture-of-Experts model designed for visual understanding and multimodal agentic workflows while maintaining strong text-only agent performance. It features 284B total parameters with 13B activated, using a 43-layer architecture with 4,096 hidden size, 64 attention heads, and 1 KV head. The model employs 256 routed experts with 6 activated per token alongside a shared expert, DeepSeek sparse attention, and 3 Multi-Token Prediction layers. Supporting up to a 1M-token context, it integrates a 32-layer vision encoder for enhanced multimodal reasoning and visual processing.

Tencent Hy4 Preview

Hy4 preview is a flagship Mixture-of-Experts model designed for advanced reasoning, coding, agentic workflows, and efficient long-context processing. It features 770B total parameters with 49B activated per token, using 78 layers with 6,144 hidden size and 64 attention heads. The architecture combines Gated DeepSeek Sparse Attention with IndexCache, 256 routed experts and 1 shared expert, activating 8 routed experts per token, while iHC expands residual information flow across 4 streams. It includes a native Multi-Token Prediction layer for speculative decoding and supports up to a 1M-token context window.

Z.ai GLM 5.3

GLM 5.3 is an advanced Mixture-of-Experts model designed for long-horizon reasoning and large-scale coding, delivering substantially improved performance over GLM-5.2 through post-training. Its architecture features 78 layers with hybrid linear and DeepSeek sparse attention, 64 attention heads, 64 KV heads, and 256 routed experts with 8 activated per token. The model incorporates IndexShare sparse attention to improve long-context efficiency and an enhanced multi-token prediction layer for faster speculative decoding. Supporting up to a 1M token context window, it is optimized for complex reasoning, extended coding workflows, and sustained long-context tasks.

Alibaba Qwen 3.8

Qwen3.8 Flash Next is a 125B parameter hybrid model with 6B activated parameters, along with 51B n-gram embedding and 4B MTP parameters, designed for efficient long-context and agentic workloads. Its architecture combines Gated DeltaNet with Qwen Sparse Attention, 512 experts with 10 routed and 1 shared expert, Gated Residuals, and n-gram embeddings for efficient scaling and inference. It supports 262K-token context, extensible to 1M tokens, with native vision and video understanding. The model targets efficient deployment while reducing long-context latency and memory demands.

IBM Granite 4.2

Granite 4.2 30B is the flagship reasoning model in the Granite 4.2 family, designed for advanced coding, mathematics, tool calling, agentic workflows, and multilingual dialogue. It features 30B parameters with a 64-layer dense transformer using 4,096 hidden size, 32 attention heads, and 8 KV heads. The architecture employs Grouped Query Attention, RoPE with a 50M theta, and a 32,768-dimensional SwiGLU feed-forward network, with native reasoning and flexible thinking modes for balancing quality and latency. Supporting 128K native context with extension to 512K, it is optimized for complex long-context reasoning and enterprise applications.

Inference Cookbook

Recipes and reference architectures for deploying AI inference workloads on Vultr. From single-model endpoints to multi-agent pipelines, ready to run.

Explore Cookbook