# Inference | DigitalOcean Documentation > Inference is a centralized interface for browsing foundation models, comparing capabilities and pricing, testing models in the Model Playground, and running inference using serverless or dedicated deployments. - [Inference Support](https://docs.digitalocean.com/products/inference/support/index.html.md): Get help with technical support and answers to frequently asked questions. ## Getting Started with Inference Quickstarts and intermediate tutorials to get started. - [Getting Started with Inference](https://docs.digitalocean.com/products/inference/getting-started/index.html.md): Quickstarts and intermediate tutorials to get started. - [Inference Quickstart](https://docs.digitalocean.com/products/inference/getting-started/quickstart/index.html.md): Browse models, test them in the Model Playground, and send your serverless or dedicated inference requests in a few minutes. - [Test DigitalOcean Knowledge Base Retrieval Using RAG Playground](https://docs.digitalocean.com/products/inference/getting-started/use-rag-playground/index.html.md): Test how foundation models answer questions using content retrieved from a knowledge base.## Inference How-Tos How to accomplish specific tasks in detail, like creation/deletion, configuration, and management. - [Inference How-Tos](https://docs.digitalocean.com/products/inference/how-to/index.html.md): How to accomplish specific tasks in detail, like creation/deletion, configuration, and management. - [Serverless Inference Overview](https://docs.digitalocean.com/products/inference/how-to/si-overview/index.html.md): What is serverless inference and how it differs from dedicated inference. - [How to Manage Serverless Inference Prepayment](https://docs.digitalocean.com/products/inference/how-to/manage-serverless-inference-prepayment/index.html.md): Fund Serverless Inference with the Inference and Agents balance or your account prepayment balance, and enable auto-reload to replenish your balance automatically. - [Serverless Inference API Endpoints](https://docs.digitalocean.com/products/inference/how-to/si-endpoints/index.html.md): Synchronous and asynchronous API endpoints for serverless inference. - [How to Browse Models in Model Catalog](https://docs.digitalocean.com/products/inference/how-to/browse-model-catalog/index.html.md): Identify the right model for your use case by filtering available foundation models by capabilities and price. - [How to Import Your Own Models (BYOM)](https://docs.digitalocean.com/products/inference/how-to/import-models/index.html.md): Import Bring Your Own Models (BYOM) models into Model Catalog from Hugging Face or Spaces buckets and folders. - [How to Use Web Search](https://docs.digitalocean.com/products/inference/how-to/use-server-side-tools/use-web-search/index.html.md): Add the web search server-side tool to DigitalOcean Inference requests so the model can search for real-time information during a turn. - [Test and Compare Models Using the Model Playground](https://docs.digitalocean.com/products/inference/how-to/use-model-playground/index.html.md): Test and compare foundation models in the Model Playground. - [Use Serverless Inference](https://docs.digitalocean.com/products/inference/how-to/use-serverless-inference/index.html.md): Send API requests directly to foundation models without creating an AI agent or managing infrastructure. - [How to Use Web Fetch](https://docs.digitalocean.com/products/inference/how-to/use-server-side-tools/use-web-fetch/index.html.md): Add the DigitalOcean-hosted web fetch tool to Inference requests so models can retrieve full web page and PDF content during a turn. - [How to Retrieve Available Models](https://docs.digitalocean.com/products/inference/how-to/retrieve-available-models/index.html.md): How to retrieve models available for serverless inference. - [How to Use Dedicated Inference](https://docs.digitalocean.com/products/inference/how-to/use-dedicated-inference/index.html.md): Deploy open-source and commercial LLMs on dedicated GPUs as an inference endpoint. - [How to Use Batch Inference](https://docs.digitalocean.com/products/inference/how-to/use-batch-inference/index.html.md): Batch inference runs text jobs asynchronously through batch APIs compatible with OpenAI and Anthropic using your serverless inference model access key. - [How to Send Prompts to a Model Using the Chat Completions API](https://docs.digitalocean.com/products/inference/how-to/use-chat-completions-api/index.html.md): Send prompts and use reasoning with the Chat Completions API. - [How to Use the Model Synthesis Tool](https://docs.digitalocean.com/products/inference/how-to/use-server-side-tools/use-model-synthesis-tool/index.html.md): Run multiple models on the same task with the model synthesis server-side tool, then return one synthesized answer from DigitalOcean Inference. - [How to Send Prompts to a Model Using the Responses API](https://docs.digitalocean.com/products/inference/how-to/use-responses-api/index.html.md): Send prompts with the Responses API. - [How to Send Requests to a Model Using the System One API](https://docs.digitalocean.com/products/inference/how-to/use-system-one-api/index.html.md): Send a state and structured questions to the TypeSafe Jev model and get typed decisions with calibrated probabilities. - [How to Use Prompt Caching in Serverless Inference](https://docs.digitalocean.com/products/inference/how-to/use-prompt-caching/index.html.md): Use prompt caching with the Chat Completions, Messages, and Responses APIs. - [How to Use Reasoning with the Chat Completions and Responses API](https://docs.digitalocean.com/products/inference/how-to/use-reasoning/index.html.md): Use reasoning with the Chat Completions and Responses API. - [How to Retrieve Knowledge Base Content](https://docs.digitalocean.com/products/inference/how-to/use-server-side-tools/retrieve-knowledge-base/index.html.md): Add knowledge base retrieval to DigitalOcean Inference requests so the model can query your private data sources with retrieval-augmented generation (RAG). - [How to Generate Images from Text Prompts](https://docs.digitalocean.com/products/inference/how-to/generate-images-from-text-prompts/index.html.md): Generate or edit images from text prompts. - [How to Use Multimodal Inference](https://docs.digitalocean.com/products/inference/how-to/use-multimodal-inference/index.html.md): Process and generate content across multiple data types, including images, audio, video, and text using multimodal models. - [How to Use Inference Router](https://docs.digitalocean.com/products/inference/how-to/use-inference-router/index.html.md): Send requests to Inference Router and optionally set a routing preference. - [How to Use Model Context Protocol (MCP)](https://docs.digitalocean.com/products/inference/how-to/use-server-side-tools/use-mcp/index.html.md): Connect DigitalOcean Inference requests to remote Model Context Protocol (MCP) servers so the model can call tools those servers expose. - [How to Use fal Models to Generate Image, Audio, or Text-to-Speech](https://docs.digitalocean.com/products/inference/how-to/use-fal-models/index.html.md): Generate image, audio, or text-to-speech using fal models. - [How to Convert Text Into Dense Vector Representations](https://docs.digitalocean.com/products/inference/how-to/generate-vector-embeddings/index.html.md): Convert text into dense vector representations for use in semantic search, retrieval-augmented generation (RAG), clustering, classification, and similarity matching. - [How to Use Claude Code and Other Agentic Workflows with Messages API on DigitalOcean](https://docs.digitalocean.com/products/inference/how-to/use-messages-api/index.html.md): Use the Messages API with Claude Code and similar agentic workflows. - [How to View Serverless Inference Metrics](https://docs.digitalocean.com/products/inference/how-to/view-serverless-inference-metrics/index.html.md): View metrics such as latency, throughput, error rates, token consumption, cost attribution, and rate limiting. - [How to Use Signals with Serverless Inference](https://docs.digitalocean.com/products/inference/how-to/use-signals-with-serverless-inference/index.html.md): Enable Signals for Serverless Inference, view sessions and dialogues, export data, and request deletion using doctl. - [How to Use Serverless Inference After Updating to Another Model](https://docs.digitalocean.com/products/inference/how-to/use-serverless-after-model-update/index.html.md): How to use serverless inference after updating a model. - [How to Use Provider Passthrough Tools](https://docs.digitalocean.com/products/inference/how-to/use-server-side-tools/use-provider-agentic-tools/index.html.md): Use Anthropic and OpenAI passthrough tools on DigitalOcean Inference, including tool search, computer use, bash, local shell, web fetch, code editing, and function calling. - [Use Agent Platform](https://docs.digitalocean.com/products/inference/how-to/use-agent-platform/index.html.md): Build fully-managed AI agents with knowledge bases for retrieval-augmented generation, multi-agent routing, guardrails, and more. - [How to Create Agents on DigitalOcean Inference](https://docs.digitalocean.com/products/inference/how-to/create-agents/index.html.md): Create an agent with domain-specific knowledge to provide information or take action. - [How to Create and Manage Model Access Keys](https://docs.digitalocean.com/products/inference/how-to/manage-model-access-keys/index.html.md): Create, scope, and manage model access keys for foundation models, inference routers, and batch inference, with VPC restrictions, team-owner visibility, and per-key spend thresholds. - [How to Use Coding Agents With DigitalOcean](https://docs.digitalocean.com/products/inference/how-to/use-with-coding-agents/index.html.md): Configure Codex CLI, Claude Code, Cline, OpenCode, Cursor, and OpenClaw to use inference with your model access key. - [How to Add, Edit, or Delete Partner Provider Keys on DigitalOcean Inference](https://docs.digitalocean.com/products/inference/how-to/manage-model-provider-keys/index.html.md): Add, edit, or delete API keys to use their models with your agents. - [How to Create and Manage Workspaces on DigitalOcean Inference](https://docs.digitalocean.com/products/inference/how-to/manage-workspaces/index.html.md): Create workspaces to group agents together and move agents between workspaces as needed. - [How to Use Agents in Your Applications on DigitalOcean Inference](https://docs.digitalocean.com/products/inference/how-to/use-agents/index.html.md): Use your agent in an application or through a chat bot interface. - [How to Test Agents Using the Agent Playground on DigitalOcean Inference](https://docs.digitalocean.com/products/inference/how-to/test-agents/index.html.md): Test the full agent experience with the directions and features you've configured using the Agent Playground. - [How to Evaluate Agent Performance on DigitalOcean Inference](https://docs.digitalocean.com/products/inference/how-to/evaluate-agents/index.html.md): Create test cases and measure how well your agents perform across criteria like factual accuracy, instruction following, and context relevance. - [How to View Agent Metrics and Logs on DigitalOcean Inference](https://docs.digitalocean.com/products/inference/how-to/view-agent-observability/index.html.md): View metrics and runtime logs for your agents to troubleshoot issues. - [How to Route to Multiple Agents on DigitalOcean Inference](https://docs.digitalocean.com/products/inference/how-to/route-agents/index.html.md): Integrate multiple generative AI agents. - [How to Route Functions in Agents on DigitalOcean Inference](https://docs.digitalocean.com/products/inference/how-to/route-agent-functions/index.html.md): Enable the foundation model in your agent to access the external data sources using functions. - [How to Rollback to a Previous Version of Agents on DigitalOcean Inference](https://docs.digitalocean.com/products/inference/how-to/manage-agent-versions/index.html.md): Rollback to a previous version of an agent to undo changes made to it. - [How to Create, Edit, and Destroy DigitalOcean Knowledge Bases on DigitalOcean Inference](https://docs.digitalocean.com/products/inference/how-to/create-manage-agent-knowledge-bases/index.html.md): Create, edit, manage data sources, verify, and permanently destroy knowledge bases. - [How to Attach and Detach DigitalOcean Knowledge Bases on DigitalOcean Inference](https://docs.digitalocean.com/products/inference/how-to/attach-agent-knowledge-bases/index.html.md): Attach or detach a knowledge base from your agents. - [How to Attach, Edit, Duplicate, and Destroy Agent Guardrails on DigitalOcean Inference](https://docs.digitalocean.com/products/inference/how-to/manage-agent-guardrails/index.html.md): Create, manage, edit, duplicate, or delete guardrails to control how your agents respond to sensitive or inappropriate content. - [How to Destroy Agents Using the Control Panel on DigitalOcean Inference](https://docs.digitalocean.com/products/inference/how-to/destroy-agents/index.html.md): Destroy an agent to permanently and irreversibly destroy the agent and removes all endpoints for the agent. - [Test DigitalOcean Knowledge Base Retrieval Using RAG Playground](https://docs.digitalocean.com/products/inference/how-to/test-knowledge-base-retrieval/index.html.md): Test how foundation models answer questions using content retrieved from a knowledge base. - [How to Use Server-Side Tools](https://docs.digitalocean.com/products/inference/how-to/use-server-side-tools/index.html.md): Extend inference requests with DigitalOcean-hosted and provider passthrough server-side tools, including web search, model synthesis tool, knowledge base retrieval, and MCP, on serverless inference, …## Inference Reference Native and third-party tools, troubleshooting, and answers to frequently asked questions. - [Inference Reference](https://docs.digitalocean.com/products/inference/reference/index.html.md): Native and third-party tools, troubleshooting, and answers to frequently asked questions. - [Serverless Inference Metrics](https://docs.digitalocean.com/products/inference/reference/serverless-inference-metrics/index.html.md): Metrics such as latency, throughput, error rates, token consumption, cost attribution, and rate limiting. - [Quota-Specific Response Headers For Serverless Inference](https://docs.digitalocean.com/products/inference/reference/quota-specific-response-headers/index.html.md): A list of available quota-specific response headers for serverless inference. - [Agent Evaluation Metrics](https://docs.digitalocean.com/products/inference/reference/agent-evaluation-metrics/index.html.md): A list of available agent evaluation metrics and their definitions. - [Chunking Parameters](https://docs.digitalocean.com/products/inference/reference/chunking-strategies/index.html.md): Reference for DigitalOcean Knowledge Bases chunking parameters, their recommendations, and their constraints across supported embeddings models. - [Agent Inference](https://docs.digitalocean.com/products/inference/reference/api/agent-inference/index.html.md): - [Agent Platform API](https://docs.digitalocean.com/products/inference/reference/api/agent-platform-api/index.html.md): - [Batch Inference](https://docs.digitalocean.com/products/inference/reference/api/batch-inference/index.html.md): - [Dedicated Inference](https://docs.digitalocean.com/products/inference/reference/api/dedicated-inference/index.html.md): - [Embeddings](https://docs.digitalocean.com/products/inference/reference/api/embeddings/index.html.md): - [Serverless Inference](https://docs.digitalocean.com/products/inference/reference/api/serverless-inference/index.html.md): - [Signals](https://docs.digitalocean.com/products/inference/reference/api/signals/index.html.md): - [Inference CLI Reference](https://docs.digitalocean.com/products/inference/reference/cli/index.html.md): doctl command groups for managing serverless inference, dedicated inference endpoints, and agent knowledge bases. - [Inference PyDo SDK Reference](https://docs.digitalocean.com/products/inference/reference/pydo/index.html.md): PyDo modules for managing serverless inference, dedicated inference endpoints, agents, and knowledge bases from Python. - [Inference API Reference](https://docs.digitalocean.com/products/inference/reference/api/index.html.md): The Inference API endpoints are organized into the following groups: Dedicated Inference (13 endpoints): Dedicated Inference delivers scalable production-grade LLM hosting on DigitalOcean. Create, …## Inference Concepts Explanations and definitions of core concepts in Inference. - [Inference Concepts](https://docs.digitalocean.com/products/inference/concepts/index.html.md): Explanations and definitions of core concepts in Inference. - [Best Practices for Context Management when Generating Code with AI Agents](https://docs.digitalocean.com/products/inference/concepts/context-management/index.html.md): Improve AI output quality by carefully managing LLM context. - [Agent Instructions Best Practices for DigitalOcean Inference](https://docs.digitalocean.com/products/inference/concepts/agent-instructions/index.html.md): Write effective agent instructions to align responses with your goals, minimize hallucinations, and enhance performance. - [Function Instructions Best Practices for DigitalOcean Inference](https://docs.digitalocean.com/products/inference/concepts/function-instructions/index.html.md): Write concise and actionable function instructions by defining purpose, specifying outputs, ensuring concise descriptions, and addressing constraints with structured examples. - [Prompt Writing Best Practices](https://docs.digitalocean.com/products/inference/concepts/prompts-best-practices/index.html.md): Write effective prompts to maintain a neutral tone, ask focused questions, simplify complexity, and enhance clarity with examples or screenshots. - [Effectively Group Agents in Workspaces for DigitalOcean Inference](https://docs.digitalocean.com/products/inference/concepts/workspaces/index.html.md): Learn to how you can effectively group agents in workspaces for various purposes. - [Chunking Best Practices for DigitalOcean Knowledge Base Indexing](https://docs.digitalocean.com/products/inference/concepts/chunking-strategies/index.html.md): Choose and configure chunking strategies to improve retrieval accuracy, reduce hallucinations, and optimize token usage when indexing knowledge bases. - [System Instructions Best Practices for DigitalOcean Knowledge Bases](https://docs.digitalocean.com/products/inference/concepts/system-instructions/index.html.md): Write effective system instructions for knowledge base responses by defining the model's role, limits, communication style, and source requirements. - [DigitalOcean Knowledge Base Retrieval Best Practices](https://docs.digitalocean.com/products/inference/concepts/retrieval/index.html.md): Guidance for improving knowledge base retrieval with hybrid search, chunking, filters, and reranking.## Inference Details Features, plans and pricing, availability, limits, known issues, and more. - [Inference Details](https://docs.digitalocean.com/products/inference/details/index.html.md): Features, plans and pricing, availability, limits, known issues, and more. - [Inference Features](https://docs.digitalocean.com/products/inference/details/features/index.html.md): Inference provides an interface for managing inference workflows. - [Inference Pricing](https://docs.digitalocean.com/products/inference/details/pricing/index.html.md): Inference pricing is usage-based. Serverless inference bills per input and output token, shown per million tokens and billed per thousand. - [Inference Availability](https://docs.digitalocean.com/products/inference/details/availability/index.html.md): Regional datacenter availability for Inference. - [Inference Limits](https://docs.digitalocean.com/products/inference/details/limits/index.html.md): Limits and known issues for Inference. - [Supported Models on DigitalOcean Inference](https://docs.digitalocean.com/products/inference/details/models/index.html.md): DigitalOcean Inference supports 70+ models including OpenAI GPT, Claude, Llama, DeepSeek, Qwen, and Kimi through an OpenAI-compatible API. - [DigitalOcean AI Data Privacy](https://docs.digitalocean.com/products/inference/details/data-privacy/index.html.md): Information about the data we collect when using Inference. - [DigitalOcean AI Website Crawler](https://docs.digitalocean.com/products/inference/details/website-crawler/index.html.md): Information about the web crawler DigitalOcean provides to crawl websites as data sources for knowledge bases. - [Model Support Policy](https://docs.digitalocean.com/products/inference/details/model-support-policy/index.html.md): Release process and deprecation policy for supported foundation and embeddings models. ## Inference Support Technical support articles for Inference. - [What retry or backoff behavior should I follow for 429 responses from serverless inference?](https://docs.digitalocean.com/support/what-retry-or-backoff-behavior-should-i-follow-for-429-responses-from-serverless-inference/index.html.md): Steps to follow for retry and backoff behavior for HTTP 429 responses from serverless inference. - [How do I schedule automatic reindexing for my knowledge bases?](https://docs.digitalocean.com/support/how-do-i-schedule-automatic-reindexing-for-my-knowledge-bases/index.html.md): Create a scheduled function to automatically reindex a knowledge base.