01
Shared
Virtual machines on shared vCPUs. Dev, staging and small production.
From
$5
/ month · billed hourly
- 1 to 32 vCPU, 1 GB to 192 GB RAM
- 25 GB to 3.8 TB NVMe storage
- Full root access, SSH keys
- Snapshots and backups
- Billed by the hour
INFERENCE API
33 models on one OpenAI-compatible endpoint, one key, up to 1M context.
Everything you need to
build and scale.
GPU Pods
GPU Pods
H100, H200 and B200 accelerators on demand. Reserve a single GPU or a multi-node cluster, provisioned in under 90 seconds and billed by the second, with persistent volumes that follow your workload between sessions.
H100H200B200B300
Explore GPU PodsNeed bigger?
Reserve a cluster.
Multi-node H200, B200 and B300 clusters with NVIDIA NVLink 5.0 fabric, dedicated capacity and committed pricing. From a single 8-GPU node to thousand-GPU training runs; we handle the rest.
Ready to build?
Talk to our infrastructure team and get a custom quote.
Multi-node NVLink fabric
8× B300 SXM per node · 1.8 TB/s GPU-to-GPU
Reserved pricing
Up to 60% off on-demand · 1-mo to 3-yr terms
Dedicated support
Priority access, 24/7 coverage, SLA-backed
Rapid provisioning
Clusters ready in hours, not days
Custom networking
Tailored VPC, routing and isolation
99.99% uptime SLA
Enterprise-grade reliability you can build on
Cluster configurationReview & request
NVIDIA B300 SXM · 8-node cluster
NVLink fabric · Redundant power · PCIe 5.0
- GPUs
- 64× NVIDIA B300
- GPU memory
- 18.4 TB (288 GB / GPU)
- Interconnect
- NVLink Switch System 5.0
- vCPUs / node
- 96 vCPUs
- Networking
- 800 Gbps · RDMA
- Term
- 12-month reserved
Every provider behind
a single integration.
33 models, 8 providers, one OpenAI- and Anthropic-compatible endpoint. Switch providers with a string change.
33
Models
8
Providers
1M
Max context
1
API key
StreamingTool callingJSON modeVisionLong contextBYOKOff-peak pricing
Browse the full catalogclaude-opus-5
Anthropic
Frontier · Tools · 1M context
gpt-6-astra
OpenAI
Frontier · Tools · 1M context
grok-4.6
xAI
Reasoning · Tools · 500k
kimi-k3
Moonshot
Open weights · Tools · 1M
glm-5.3
Zhipu
Open weights · Tools · 1M
deepseek-v4-pro
DeepSeek
Reasoning · Tools · 1M
claude-opus-5
Anthropic
Frontier · Tools · 1M context
gpt-6-astra
OpenAI
Frontier · Tools · 1M context
grok-4.6
xAI
Reasoning · Tools · 500k
kimi-k3
Moonshot
Open weights · Tools · 1M
glm-5.3
Zhipu
Open weights · Tools · 1M
deepseek-v4-pro
DeepSeek
Reasoning · Tools · 1M
claude-sonnet-5
Anthropic
Balanced · Tools · 1M context
gpt-5.6-terra
OpenAI
Balanced · Tools · 1M context
grok-4.5
xAI
Reasoning · Tools · 500k
kimi-k2.7-code
Moonshot
Code · Open weights · 256k
minimax-m3
MiniMax
Open weights · Tools · 1M
glm-5.3-flash-derisked
Zhipu
Derisked · Hosted · 1M
claude-sonnet-5
Anthropic
Balanced · Tools · 1M context
gpt-5.6-terra
OpenAI
Balanced · Tools · 1M context
grok-4.5
xAI
Reasoning · Tools · 500k
kimi-k2.7-code
Moonshot
Code · Open weights · 256k
minimax-m3
MiniMax
Open weights · Tools · 1M
glm-5.3-flash-derisked
Zhipu
Derisked · Hosted · 1M
claude-haiku-4.5
Anthropic
Fast · Tools · 200k
gpt-5.4-mini
OpenAI
Fast · Tools · 400k
gpt-5.3-codex
OpenAI
Code · Tools · 400k
deepseek-v4-flash
DeepSeek
Fast · Open weights · 1M
doubao-seed-2.1-turbo
ByteDance
Fast · Tools · 256k
claude-fable-5.1
Anthropic
Frontier · Tools · 1M context
claude-haiku-4.5
Anthropic
Fast · Tools · 200k
gpt-5.4-mini
OpenAI
Fast · Tools · 400k
gpt-5.3-codex
OpenAI
Code · Tools · 400k
deepseek-v4-flash
DeepSeek
Fast · Open weights · 1M
doubao-seed-2.1-turbo
ByteDance
Fast · Tools · 256k
claude-fable-5.1
Anthropic
Frontier · Tools · 1M context
Compute
Three tiers on one control plane. Move between them without rebuilding your stack: same API, same billing, same audit trail, whether you are running a staging box or a regulated workload on its own hardware.
15 regions · hourly + monthly · API-first
02
VDS
Virtual dedicated servers on pinned physical cores. Production APIs and databases.
From
$24
/ month · billed hourly
- Dedicated cores, no noisy neighbours
- 2 to 256 vCPU, 4 GB to 512 GB RAM
- 41 GB to 5.1 TB NVMe storage
- Guaranteed baseline performance
- Full root access, SSH keys
- Same API and billing as Shared
03
Bare metal servers
A whole physical server, no hypervisor. Your kernel, your hardware.
From
$59
/ month · 16 configurations
- 6 to 192 cores, 64 GB to 1.5 TB RAM
- AMD EPYC and Ryzen, Intel Xeon
- IPMI out-of-band access
- Custom OS, hardware RAID
- Single tenant, monthly term
Global infrastructure
15 regions·13 countries·In-region residency
Mumbai
Singapore
Dubai
Tokyo
Sydney
London
Frankfurt
Amsterdam
Paris
Madrid
Stockholm
New YorkSan FranciscoLos Angeles
São Paulo