Available Foundation and Embedding Modelspublic
Validated on 7 Feb 2025 • Last edited on 28 May 2025
The DigitalOcean GenAI Platform lets you work with popular foundation models and build GPU-powered AI agents with fully-managed deployment, or send direct requests using serverless inference. Create agents that incorporate guardrails, functions, agent routing, and retrieval-augmented generation (RAG) pipelines with knowledge bases.
Foundation Models
A foundation model is a large-scale model pre-trained on a large corpus of data and adaptable to various tasks.
You can access all available models as a model endpoint, which simplifies model usage by removing the need to create and manage an AI agent. For details on model endpoint pricing, see our pricing page.
You can experiment with the following models in the Model Playground:
Anthropic Models
Anthropic models use Constitutional AI to guide responses and refine their self-improvement loop, ensuring more reliable and less biased outputs.
We support all Anthropic models, with access determined by your Anthropic API key.
Model | Version | Parameters | Max Tokens | Description | Use Cases | Training Dataset Summary | Language Support |
---|---|---|---|---|---|---|---|
Claude 3.7 Sonnet | 3.7 | Not published | 1024 | • Handles both small tasks and deeper reasoning • Follows instructions well and works with text, code, and images • Generates detailed outputs when needed |
• Software development • Chatbots • Q&A systems • Customer support agents • Content creation |
Not disclosed | • Multilingual |
Claude 3.5 Sonnet | 3.5 | Not published | 1024 | • Balanced model for multilingual dialogue and general tasks • Efficient for business and content generation |
• Business workflows • Content creation • Coding assistance |
Not disclosed | • Multilingual |
Claude 3.5 Haiku | 3.5 | Not published | 1024 | • Optimized for real-time responsiveness • Suitable for quick, accurate outputs |
• Chatbots • Real-time data extraction • Content classification |
Not disclosed | • Multilingual |
Claude 3 Opus | 3 | Not published | 1024 | • Optimized for complex and long-form content • Excels in reasoning, analysis, and multilingual tasks |
• Research • Strategic analysis • Advanced problem-solving |
Not disclosed | • Multilingual |
DeepSeek Models
DeepSeek models use Chain of Thought (CoT) and reinforcement learning to produce reasoned outputs. Since the model explains its reasoning, it may use significantly more tokens than others.
Model | Version | Parameters | Max Tokens | Description | Use Cases | Training Dataset Summary | Language Support |
---|---|---|---|---|---|---|---|
DeepSeek-R1 | distill-llama-70B model | 70B | 8000 | • Strong Mixture-of-Experts (MoE) language model • Excels in reasoning, analysis, and multilingual tasks |
• Chatbots • Content creation • Coding assistance |
• CoT • RLHF |
• Multilingual |
Meta Models
Meta models are open-source, multilingual, and lightweight models that provide a balance between performance and efficiency.
Model | Version | Parameters | Max Tokens | Description | Use Cases | Training Dataset Summary | Language Support |
---|---|---|---|---|---|---|---|
Llama | 3.3 Instruct-70B | 3.3 | 70B | 2048 | • Improved instruction-following and reasoning capabilities • Optimized for multilingual and long-context tasks |
• Complex dialogue • Long-form content |
Not disclosed |
Llama | 3.1 Instruct-70B | 70B | 2048 | • Handles multilingual dialogue and content generation • Trained for human-like responses in multiple languages |
• Translation • Summarization • Data analysis |
Not disclosed | • Multilingual |
Llama | 3.1 Instruct-8B | 8B | 512 | • Handles multilingual dialogue and instruction-following tasks • Supports multiple languages |
• Chatbots • Translation • Natural language generation |
Not disclosed | • Multilingual |
Mistral Models
Mistral models focus on making advanced LLM capabilities accessible with fewer parameters, aiming for faster inference and lower computational costs, while maintaining competitive quality.
Model | Version | Parameters | Max Tokens | Description | Use Cases | Training Dataset Summary | Language Support |
---|---|---|---|---|---|---|---|
Mistral | NeMo | 12B | 512 | • Handles multilingual applications, coding, and reasoning tasks • Processes large and complex documents • Supports multi-turn conversations |
• Problem-solving • Advanced coding tasks • Instruction-based interactions |
Not disclosed | • Multilingual |
OpenAI Models
OpenAI models provide reasoning and versatility, making them suitable for a wide range of tasks, including code generation, summarization, and content creation.
We support the following OpenAI models, with access determined by your OpenAI key.
Model | Version | Parameters | Max Tokens | Description | Use Cases | Training Dataset Summary | Language Support |
---|---|---|---|---|---|---|---|
OpenAI | GPT-4o | Not published | 16384 | • Advanced reasoning • High computational power • Accepts both text and image inputs |
• Creative projects • Advanced chatbots • Content creation • Code generation |
Not disclosed | • Multilingual |
OpenAI | GPT-4o mini | Not published | 16384 | • Compact and resource efficient • Good balance between performance and cost |
• Basic chatbots • Basic content creation • Summarization • Content classification |
Not disclosed | • Multilingual |
OpenAI | o1 | Not published | 100000 | • Trained with reinforcement learning • Advanced reasoning • Uses chain of thought |
• Complex tasks • Advanced problem-solving • Content creation • Code generation |
Not disclosed | • Multilingual |
OpenAI | 03-mini | Not published | 100000 | • Good balance of reasoning and efficiency • Optimized for speed |
• Straight forward answer responses • Code generation |
Not disclosed | • Multilingual |
Embedding Models
An embedding model converts data into vector embeddings, which are stored in an OpenSearch database cluster.
You can use these embedding models to generate embeddings for your knowledge base:
Alibaba Group
Alibaba’s models integrate with its cloud services and e-commerce platforms, focusing on business applications like customer service chatbots and automated product descriptions.
Model Type | Version | Parameters | Description | Use Cases |
---|---|---|---|---|
Text Embeddings | Alibaba-NLP/gte-large-en-v1.5 | 434M | • Handles long-form text and tasks with extensive context • Excels in understanding semantic relationships within content |
• Semantic search • Text summarization • Cross-lingual applications |
SBERT Models
SBERT is an open-source Python library for generating sentence embeddings, and can be used for semantic search, semantic textual similarity, and paraphrase mining.
Model Type | Version | Parameters | Description | Use Cases |
---|---|---|---|---|
Sentence-Transformers | sentence-transformers/all-MiniLM-L6-v2 | 22.7M | • Processes data quickly with minimal resources | • Semantic search • Clustering • Information retrieval |
Sentence-Transformers | sentence-transformers/multi-qa-mpnet-base-dot-v1 | 109M | • Performs well in production environments and scales efficiently | • Semantic search • Information retrieval • Question-answering systems |
For more details, read the GenAI Platform pricing page.