DigitalOcean Model Library
Whether you're building agents with code or in the DigitalOcean console, pick the model that fits your workflow.
| Model Name | Type | Capabilities | Price | Availability | |
|---|---|---|---|---|---|
| Mistral 7B Instruct v0.3 | Chat | N/A | Dedicated | Get Started | |
| Ministral 3 8B | Chat | N/A | Dedicated | Get Started | |
| Qwen 2.5 14B Instruct | Chat | N/A | Dedicated | Get Started | |
| Nemotron 3 Nano 30B A3B | Chat | N/A | Dedicated | Get Started | |
| DeepSeek V3 | Chat | N/A | Dedicated | Get Started | |
| Fal Fast SDXL | Image | Async | $0.00000111/second | Serverless | Get Started |
| Fal Flux Schnell | Image | Async | $0.000003/megapixel | Serverless | Get Started |
| Fal Stable Audio 2.5 | Audio | Async | $0.00000058/second | Serverless | Get Started |
| Fal ElevenLabs TTS Multilingual v2 | Audio | Async | $0.0001/1K chars | Serverless | Get Started |
| Qwen3 TTS | Audio | Audio, streaming, multilingual | $0.00002/1K chars | Serverless | Get Started |
| Stable Diffusion 3.5 Large | Image | Image generation | $0.08/image | Serverless | Get Started |
| Wan 2.2 T2V | Chat | $0.60/video | Serverless | Get Started | |
| Ideogram 3.0 Quality | Image | $0.09/image | Serverless | Get Started | |
| Ideogram 3.0 Default | Image | $0.06/image | Serverless | Get Started | |
| Ideogram 3.0 Flash | Image | $0.03/image | Serverless | Get Started |
Frequently asked questions
What is a Model Library?
The DigitalOcean Model Library helps you discover, compare, and evaluate AI models from leading providers. Filter by capabilities, pricing, and deployment options, then test models in the Playground and deploy them with Serverless or Dedicated Inference.
What's the difference between foundation models and embedding models?
Can I test and compare different models before choosing one?
Yes — the Model Playground allows you to run prompts against any available foundation model, compare outputs side-by-side, and fine-tune parameters. It's the fastest way to evaluate accuracy, speed, style, and cost.
How do I incorporate my own data with these models?
Use an embedding model to vectorize your documents and store them in a Knowledge Base. When attached to an agent, the platform will automatically retrieve relevant context and feed it into your foundation model during inference—enabling accurate, domain-specific RAG workflows.
Start building today
From GPU-powered inference and Kubernetes to managed databases and storage, get everything you need to build, scale, and deploy intelligent applications.
