Browse Models in Model Catalog
Identify the right model for your use case by filtering available foundation models by capabilities and price.
Inference
Last verified 13 Jul 2026
Inference provides a single control plane for managing inference workflows. It includes a Model Catalog where you can view available foundation models, including both DigitalOcean-hosted and third-party commercial models, compare model capabilities and pricing, use routing to match inference requests to the best-fit model, and run inference using serverless or dedicated deployments.
Use Model Playground
Test and compare foundation models in the Model Playground.
Use Serverless Inference
Send API requests directly to foundation models without creating an AI agent or managing infrastructure.
Deploy to Dedicated Inference Endpoints
Deploy open-source and commercial LLMs on dedicated GPUs as an inference endpoint.
Use Inference Router
Route serverless inference requests to foundation models using rules.
Evaluate Models
Determine which model best fits your specific use case.
Use Batch Inference
Batch Inference lets you run large collections of LLM requests as a single asynchronous job.
Use Agent Platform
Use to build fully-managed AI agents with knowledge bases for retrieval-augmented generation, multi-agent routing, guardrails, and more.
Latest Updates
15 July 2026
-
The Gradient AI TypeScript SDK is deprecated. Use the official DigitalOcean TypeScript SDK (DoTs) or the DigitalOcean API directly. For installation and quickstart examples, see SDK and Client Libraries.
-
The Gradient AI Python SDK is deprecated. Use the official DigitalOcean Python SDK (PyDo) or the DigitalOcean API directly. For installation and quickstart examples, see SDK and Client Libraries.
-
The Gradient AI Go Library is deprecated. Use the official DigitalOcean Go SDK (Godo) or the DigitalOcean API directly. For installation and quickstart examples, see SDK and Client Libraries.
10 July 2026
-
The following OpenAI models are now available on DigitalOcean Inference for serverless inference:
For more information, see the Available Models page.
1 July 2026
-
Prompt caching for open-source models in serverless inference chat completions and responses API is now in public preview. Open-source models cache context automatically, so you do not need to set the
cache_controlorprompt_cache_retentionparameters.Prompt caching is available for the following open-source models:
- DeepSeek V3.2
- DeepSeek V4 Pro
- DeepSeek V4 Flash
- Kimi K2.5
- Kimi K2.6
- GLM 5
- GLM-5.1
- GLM-5.2
- gpt-oss-120b
- MiMo V2.5
- MiMo V2.5 Pro
- MiniMax M2.5
- Qwen 3.5
- Qwen3 Coder Flash
For more information, see Use Prompt Caching.
-
Claude Fable 5 is available again on DigitalOcean Inference for serverless inference, Agent Development Kit, and agents. For more information, see the Available Models page.
For more information, see the full release notes.