---
title: Inference DoTs SDK Reference
description: DoTs modules for managing serverless inference, dedicated inference endpoints, batch inference jobs, agents, and knowledge bases from TypeScript.
product: Inference
url: https://docs.digitalocean.com/products/inference/reference/dots/
last_updated: "2026-11-11"
---

> **For AI agents:** The documentation index is at [https://docs.digitalocean.com/llms.txt](https://docs.digitalocean.com/llms.txt). Markdown versions of pages use the same URL with `index.html.md` in place of the HTML page (for example, append `index.html.md` to the directory path instead of opening the HTML document).

# Inference DoTs SDK Reference

Inference provides a single control plane for managing inference workflows. It includes a Model Catalog where you can view available foundation models, including both DigitalOcean-hosted and third-party commercial models, compare model capabilities and pricing, use routing to match inference requests to the best-fit model, and run inference using serverless or dedicated deployments.

[DoTs](https://github.com/digitalocean/dots) is the official DigitalOcean TypeScript client library. Install it with `npm i @digitalocean/dots`.

The Inference modules are:

- [Dedicated Inference](https://docs.digitalocean.com/reference/dots/reference/dedicated-inference/index.html.md): Manage dedicated inference endpoints, including their accelerators, CA certificate, sizes, GPU model configuration, and access tokens. Dedicated Inference is available in [public preview](https://docs.digitalocean.com/platform/product-lifecycle/index.html.md#public-preview). You can opt in from the [**Feature Preview** page](https://cloud.digitalocean.com/account/feature-preview?utm_source=docs-agent&utm_medium=md).
- [Serverless Inference](https://docs.digitalocean.com/reference/dots/reference/serverless-inference/index.html.md): Access and use serverless inference models.
- [Batch Inference](https://docs.digitalocean.com/reference/dots/reference/batch-inference/index.html.md): Submit and manage asynchronous batch inference jobs.
- [Agent Platform](https://docs.digitalocean.com/reference/dots/reference/agent-platform-api/index.html.md): Build agents with pre-built or custom foundation models, add function and agent routes, and create retrieval pipelines backed by knowledge bases.
- [Agent Inference](https://docs.digitalocean.com/reference/dots/reference/agent-inference/index.html.md): Integrate agents into your applications using an agent-specific endpoint.

For install instructions and quickstart examples, see [DoTs](https://docs.digitalocean.com/reference/dots/index.html.md).