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).

DigitalOcean Inference supports more than 70 foundation, embeddings, and reranking models, including OpenAI (GPT-5.x and open-weight gpt-oss), Anthropic Claude, Meta Llama, DeepSeek, Alibaba Qwen, Moonshot AI Kimi, NVIDIA Nemotron, and Z.ai GLM. All text models are served through OpenAI-compatible endpoints, so you can use an existing OpenAI SDK or client by changing the base URL to https://inference.do-ai.run and authenticating with a DigitalOcean API key. For endpoint details, see Serverless Inference Endpoints.

We regularly update our model offerings to provide the most performant and efficient models, and deprecate older models. For information on our model deprecation policy and recommended model replacements, see Model Support Policy.

Models by Provider

The following table summarizes the model providers and model family. For a model’s ID, context window, max output tokens, and supported features, see Foundation Models.

Foundation Models

Inference supports both open source and commercial foundation models. Open source models are generally published by research labs, available under open licenses. Commercial models are proprietary such as OpenAI and Anthropic models. All models are offered using DigitalOcean API access keys, but you can also bring your own provider’s API keys to access the commercial models.

We offer the following foundation models, subject to the AI Model Terms, our Service Terms, and the Terms of Service Agreement.

You can use these models in serverless inference, dedicated inference, inference routers, batch inference, agents, or Agent Development Kit (ADK). See the model-specific usage information below.

Embeddings Models

An embedding model converts data into vector embeddings. DigitalOcean stores vector embeddings in an OpenSearch database cluster for use with agent knowledge bases. The following embeddings models are available on the platform, along with their token windows and recommended chunking ranges.

Reranking Models

Reranking models reorder retrieved results to improve relevance after the initial retrieval step, and can also be used with vector databases. DigitalOcean supports the following reranking model for knowledge base retrieval: