- How to Use Agents in Your Applications
- GenAI Platform Pricing
- GenAI Platform Quickstart
- GenAI Platform Features
- Available Foundation and Embedding Models
- Create and Manage Agents
- How to Route to Multiple Agents
- Test and Compare Models Using the Model Playground
- How to Route Functions in Your Agent
- Create and Manage Guardrails
GenAI Platformpublic
Generated on 30 May 2025
The DigitalOcean GenAI Platform lets you work with popular foundation models and build GPU-powered AI agents with fully-managed deployment, or send direct requests using serverless inference. Create agents that incorporate guardrails, functions, agent routing, and retrieval-augmented generation (RAG) pipelines with knowledge bases.
Quickstarts and intermediate tutorials to get started.
How to accomplish specific tasks in detail, like creation/deletion, configuration, and management.
Native and third-party tools, troubleshooting, and answers to frequently asked questions.
Explanations and definitions of core concepts in GenAI Platform.
Features, plans and pricing, availability, limits, known issues, and more.
Get help with technical support and answers to frequently asked questions.
Latest Updates
14 May 2025
-
Serverless inference is now available on the GenAI Platform, allowing you to get direct responses from foundation models without creating an agent. A single API endpoint provides access to hosted models from providers like OpenAI and Anthropic. You can authenticate requests with model access keys, which provide secure access to all available models.
29 April 2025
-
You can now view token usage and performance metrics for GenAI agents.
28 April 2025
-
You can now rollback to a previous version of a GenAI Platform agent.
For more information, see all GenAI Platform release notes.