Available Foundation and Embedding Models for DigitalOcean Gradient™ AI Platform
Validated on 29 Sep 2025 • Last edited on 8 Oct 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.
Available Models
Gradient AI Platform supports both open source and commercial foundation models.
You can use these models in agents, for serverless inference, or in the Model Playground to test configurations.
Open Source Foundation Models
These models are generally published by research labs and made available under open licenses.
| Provider | Model | Model ID | Parameters | Max Tokens |
|---|---|---|---|---|
| Alibaba | Qwen3-32B | alibaba-qwen3-32b |
32 billion | 40,960 |
| DeepSeek | DeepSeek-R1 distill-llama-70B | deepseek-r1-distill-llama-70b |
70 billion | 32,768 |
| Meta | Llama 3.3 Instruct-70B | llama3.3-70b-instruct |
70 billion | 128,000 |
| Meta | Llama 3.1 Instruct-8B | llama3-8b-instruct |
8 billion | 128,000 |
| Mistral | NeMo | mistral-nemo-instruct-2407 |
12 billion | 128,000 |
| OpenAI | gpt-oss-120b | openai-gpt-oss-120b |
117 billion | 131,072 |
| OpenAI | gpt-oss-20b | openai-gpt-oss-20b |
21 billion | 131,072 |
Commercial Foundation Models
Access to proprietary models is determined by your API keys with those providers, such as your Anthropic API key or OpenAI API key.
| Provider | Model | Model ID | Parameters | Max Tokens |
|---|---|---|---|---|
| Anthropic | Claude Sonnet 4 | anthropic-claude-4-sonnet |
64,000 | |
| Anthropic | Claude Opus 4 | anthropic-claude-4-opus |
32,000 | |
| Anthropic | Claude 3.7 Sonnet | anthropic-claude-3.7-sonnet |
128,000 | |
| Anthropic | Claude 3.5 Sonnet | anthropic-claude-3.5-sonnet |
8,192 | |
| Anthropic | Claude 3.5 Haiku | anthropic-claude-3.5-haiku |
8,000 | |
| Anthropic | Claude 3 Opus | anthropic-claude-3-opus |
4,096 | |
| OpenAI | GPT-5 | openai-gpt-5 |
128,000 | |
| OpenAI | GPT-5 mini | openai-gpt-5-mini |
128,000 | |
| OpenAI | GPT-5 nano | openai-gpt-5-nano |
128,000 | |
| OpenAI | GPT-4.1 | openai-gpt-4.1 |
32,768 | |
| OpenAI | GPT-4o | openai-gpt-4o |
16,384 | |
| OpenAI | GPT-4o mini | openai-gpt-4o-mini |
16,384 | |
| OpenAI | o1 | openai-o1 |
100,000 | |
| OpenAI | o3 | openai-o3 |
100,000 | |
| OpenAI | o3-mini | openai-o3-mini |
100,000 | |
| OpenAI | GPT-image-1 | openai-gpt-image-1 |
16,384 |
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 |