Available Foundation and Embedding Models for DigitalOcean Gradient™ AI Platform

Validated on 7 Jun 2025 • Last edited on 2 Sep 2025

DigitalOcean Gradient™ AI Platform lets you build fully-managed AI agents with knowledge bases for retrieval-augmented generation, multi-agent routing, guardrails, and more, or use serverless inference to make direct requests to popular foundation models.

The following foundation and embedding models are available for Gradient AI Platform. For pricing, see Gradient AI Platform’s pricing page.

Foundation Models

A foundation model is a large-scale model pre-trained on a large corpus of data and adaptable to various tasks. We offer the following foundation models:

Provider Model and Version Model ID Source Availability Parameters Max Tokens
Alibaba Qwen3-32B alibaba-qwen3-32b Open source 32 billion 16,384
Anthropic Claude 3.7 Sonnet anthropic-claude-3.7-sonnet Proprietary Not published 64,000
Anthropic Claude 3.5 Sonnet anthropic-claude-3.5-sonnet Proprietary Not published 8,192
Anthropic Claude 3.5 Haiku anthropic-claude-3.5-haiku Proprietary Not published 8,192
Anthropic Claude 3 Opus anthropic-claude-3-opus Proprietary Not published 4,096
DeepSeek DeepSeek-R1 distill-llama-70B deepseek-r1-distill-llama-70b Open source 70 billion 16,384
Meta Llama 3.3 Instruct-70B llama3.3-70b-instruct Open source 70 billion 16,384
Meta Llama 3.1 Instruct-8B llama3-8b-instruct Open source 8 billion 16,384
Mistral NeMo mistral-nemo-instruct-2407 Open source 12 billion 16,384
OpenAI GPT-5 openai-gpt-5 Proprietary Not Published 128,000
OpenAI GPT-4o openai-gpt-4o Proprietary Not published 16,384
OpenAI GPT-4o mini openai-gpt-4o-mini Proprietary Not published 16,384
OpenAI o1 openai-o1 Proprietary Not published 100,000
OpenAI o3-mini openai-o3-mini Proprietary Not published 100,000
OpenAI gpt-oss-120b openai-gpt-oss-120b Proprietary 117 billion 16,384
OpenAI gpt-oss-20b openai-gpt-oss-20b Proprietary 21 billion 16,384

When using serverless inference, you can specify a model using its model ID. You can also experiment with models in the Model Playground.

Warning
When using DeepSeek models in a user-facing agent, we strongly recommend adding all available guardrails for a safer conversational experience.

Access to proprietary models are determined by your API keys with those providers, like your Anthropic API key or OpenAI API key.

Embedding Models

An embedding model converts data into vector embeddings. Gradient AI Platform stores vector embeddings in an OpenSearch database cluster for use with agent knowledge bases. We offer the following embedding models:

Provider Type Model and Version Parameters
Tongyi Lab, Alibaba General text embeddings (GTE) Alibaba-NLP/gte-large-en-v1.5 434 million
UKP Lab, Technical University of Darmstadt Sentence Transformer (SBERT) sentence-transformers/all-MiniLM-L6-v2 22.7 million
UKP Lab, Technical University of Darmstadt Sentence Transformer (SBERT) sentence-transformers/multi-qa-mpnet-base-dot-v1 109 million

We can't find any results for your search.

Try using different keywords or simplifying your search terms.