For AI agents: The documentation index is at 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).

Browse Models in Model Catalog

Identify the right model for your use case by filtering available foundation models by capabilities and price.

Use Model Playground

Test and compare foundation models in the Model Playground.

Use Serverless Inference

Send API requests directly to foundation models without creating an AI agent or managing infrastructure.

Deploy to Dedicated Inference Endpoints

Deploy open-source and commercial LLMs on dedicated GPUs as an inference endpoint.

Use Inference Router

Send requests to inference-router and let it pick the best model for each request.

Evaluate Models

Determine which model best fits your specific use case.

Use Batch Inference

Batch Inference lets you run large collections of LLM requests as a single asynchronous job.

Use Agent Platform

Use to build fully-managed AI agents with knowledge bases for retrieval-augmented generation, multi-agent routing, guardrails, and more.

Latest Updates

15 October 2026

• The following NVIDIA model is now available on DigitalOcean Inference for serverless inference:

  • NVIDIA Nemotron 3.5 Super VL

  For more information, see the Available Models page.

13 October 2026

• In public preview, you can now create spend alerts for Serverless Inference model access keys. Each key’s spend is tracked against its own monthly budget, and you receive email alerts as it crosses the thresholds you choose. You can also have the alert pause the key when its spend reaches 100% of its budget, which stops Serverless Inference requests for that key without affecting other keys. Paused keys resume at the start of the next billing cycle, or sooner if you raise the budget, turn off pausing, or delete the alert. For details, see Set Spend Thresholds on Keys.

12 October 2026

• Inference Router has been redesigned as a single managed router. Send requests to the inference-router model name, optionally with a routing_preference of balanced, budget, or quality, and the router selects the best model for each request.

  Preset routers and the Create Router flow have been removed from the Control Panel. Existing custom routers and preset router slugs continue to serve requests. For more information, see Use Inference Router.

For more information, see the full release notes.