GA
Paid
Hanzo Machines
Dedicated AI compute
GPU instances for training and inference. From A10G to H100, with spot pricing and preemption.
Machines Dashboard
Active Models
gpt-4o
claude-3.5
gemini-pro
llama-3.1
POST /v1/chat/completions
Request
{
"model": "gpt-4o",
"messages": [
{"role": "user",
"content": "Hello!"}
]
}Response 200
{
"choices": [{
"message": {
"content": "Hi!"
}
}],
"usage": {...}
}Requests/min
2.4K
Avg Latency
124ms
Success Rate
99.9%
Machines Dashboard
Active Models
gpt-4o
claude-3.5
gemini-pro
llama-3.1
POST /v1/chat/completions
Request
{
"model": "gpt-4o",
"messages": [
{"role": "user",
"content": "Hello!"}
]
}Response 200
{
"choices": [{
"message": {
"content": "Hi!"
}
}],
"usage": {...}
}Requests/min
2.4K
Avg Latency
124ms
Success Rate
99.9%
Features
Everything you need to get started
GPU instances
Spot pricing
Auto-scaling
Persistent storage
SSH access
SDKs & Libraries
Official Machines SDKs
Use our official SDKs to integrate Machines into your application
Community
Join the Machines Community
Get help, share ideas, and contribute to the project
Want to Contribute?
We welcome contributions of all kinds: bug reports, feature requests, documentation improvements, and code contributions.
Read our Contributing GuideRelated Products
More from Hanzo Compute
Ready to get started with Machines?
Deploy in minutes with Hanzo Cloud or self-host with our open-source release.