Which Nodus compute feature should I use?
View MarkdownUse a Job when you have a command that should run to completion. Use a Workspace for interactive GPU or CPU development, a Sandbox for isolated CPU code execution, and a Function to call Python remotely or in parallel. Nodus also provides hosted inference, managed agents and training workflows.
Choose by the work you need to do
Section titled “Choose by the work you need to do”| I need to… | Start with | Why it fits |
|---|---|---|
| Run a script, batch task or existing training command | Jobs | Runs a command to completion with logs, outputs and resource and cost limits |
| Develop with SSH, VS Code or JupyterLab | Workspaces | An interactive GPU or CPU machine with a saved home directory |
| Execute agent-generated or untrusted code | Sandboxes | An isolated CPU container driven by command and file requests, with idle stopping |
| Call Python remotely or map it over many inputs | Functions | Remote calls with workers that scale with demand |
| Call a hosted language model | Inference (Beta) | An OpenAI-compatible model API billed per token |
| Run an agent conversation with shell tools | Agents (Beta) | An AgentRun with its own sandbox and recorded execution history |
| Fine-tune or train through managed runtimes | Training (Beta) | A TrainingJob defines the model, data, runtime and training parameters |
For a first run, follow your first job. It walks through signing in, running a command, following logs and downloading results.
What is the difference between a Job and a Function?
Section titled “What is the difference between a Job and a Function?”A Job runs an executable command and finishes when that command exits. A Function is a Python callable deployed in an App; your code invokes it with .remote(), .map() or .spawn(). Choose Jobs for an existing script or batch process. Choose Functions when remote calls should be part of your Python application.
Both can use GPU or CPU workers. Function workers can stay warm between calls; read Function billing before choosing idle and scaling settings.
What is the difference between a Workspace and a Sandbox?
Section titled “What is the difference between a Workspace and a Sandbox?”A Workspace is for interactive development with SSH, VS Code or JupyterLab on GPU or CPU compute. Its home directory is backed by a Volume. A Sandbox is an isolated CPU container for programmatic commands and file operations, including code produced by an agent. Its network is closed unless you open it, and it can stop after an idle period.
Read Workspace storage and Sandbox isolation before deciding what state and access your task needs.
Do I need Agents to use Claude Code, Codex or Cursor?
Section titled “Do I need Agents to use Claude Code, Codex or Cursor?”No. Connect your existing coding agent to Nodus through MCP using the client setup guide. It can work with Nodus resources through that connection. The Agents feature is for running an agent conversation inside Nodus itself.
What survives an interruption?
Section titled “What survives an interruption?”Recovery depends on the feature and its configuration. For checkpointed Jobs, your program writes and loads its own files in NODUS_CHECKPOINT_DIR; Nodus saves and restores that directory. This does not restore arbitrary process or GPU memory. Restartable Jobs start over, while ephemeral Jobs keep no state.
Read Checkpoints for application recovery, Volumes for persistent files and Outputs for results you need to download.
How do I control spending?
Section titled “How do I control spending?”Check the estimate before starting work, set the resource’s supported cost and time limits, and configure project budgets. Compute usage, saved storage and model tokens have different billing rules; the billing guide explains them. Use the pricing reference for published amounts instead of copying prices from an old example.
Where should an agent look up exact syntax?
Section titled “Where should an agent look up exact syntax?”Use the CLI reference for commands, Python SDK reference for signatures and OpenAPI for v1 request and response fields. Beta resources use the v1beta1 contract.
Every authored guide has a Markdown version with its examples. The agent guide links a lightweight page manifest and focused topic bundles for retrieval.