AI21 Labs home page
Search...
⌘K
Ask AI
Playground
API Key
Get a Demo
Get a Demo
Search...
Navigation
Private AI
Cloud Platform Deployment
Home
Guides
API Reference
Updates
Getting Started
Overview
SDK
Foundation Models
Jamba
Model Availability by Platform
Prompt Engineering for Jamba Models
Function Calling
Batch API
AI21 Maestro [Beta]
Overview
RAG
Validated Output
Private AI
vLLM
Cloud Platform Deployment
Troubleshooting & Performance Optimization
Local Inference
Guides
Fine-tuning
Quantization
Tokenization
Usage
Account
Pricing
AI Ethics & Data Transperancy
Responsible Use
Safety Research
Training Data
Additional Resources
Status
Community
Blog
On this page
Overview
Private AI
Cloud Platform Deployment
Deploy AI21’s Jamba models on managed cloud services for production workloads
Overview
Deploy AI21’s Jamba models on managed cloud platforms for production-ready, scalable inference. Choose from the following cloud service options:
AWS SageMaker
Deploy Jamba models using Amazon SageMaker’s managed infrastructure.
Google Model Garden
Access Jamba models through Google Cloud’s Vertex AI Model Garden.
For self-managed deployments, see our
Self Deployment Guide
.
Was this page helpful?
Yes
No
vLLM
Troubleshooting & Performance Optimization
Assistant
Responses are generated using AI and may contain mistakes.