Float16DocumentationFloat16 Documentation
Learn how to deploy GPU instances, serverless endpoints, and build AI applications with Float16 Cloud.
Quick Start
Get up and running in 5 minutes
API Reference
Complete API documentation
Console
Access the Float16 dashboard
Getting Started
Learn the basics of Float16 Cloud platform
Introduction to Float16 Cloud
Learn what Float16 Cloud is and how it can help you deploy AI workloads
Quick Start Guide
PopularGet up and running with Float16 Cloud in under 5 minutes
Authentication
Learn how to sign in to Float16 Cloud
Workspaces
Organize your resources with workspaces
Dashboard Overview
Navigate the Float16 console and understand key features
Platform Guides
In-depth guides for using Float16 Cloud features
GPU Platform Overview
Create and manage dedicated GPU instances on Float16 Cloud
Serverless GPU
NewRun AI workloads on-demand without managing infrastructure
One-Click Deployment
Deploy vLLM models instantly with pre-configured settings
Volumes & Storage
Manage persistent storage for your GPU instances
Blueprints
Use pre-configured templates to deploy common AI workloads
AI Services
AI and LLM services for inference and deployment
AI Services Overview
Explore Float16's AI capabilities including LLM deployment, vLLM Playground, and OCR
LLM Deployment
Deploy and serve large language models on Float16 Cloud
vLLM Playground
InteractiveInteractive environment for testing deployed vLLM models
Typhoon OCR
Extract text from Thai and English documents using vision-language OCR
Tool Calling
Enable LLMs to interact with external tools and functions
Structured Outputs
Generate responses in specific formats using JSON Schema, Regex, or Choice constraints
API Reference
Complete API documentation for Float16 Cloud
Billing & Payments
Credits, payments, and billing management