Create a Modal Sandbox for Python | BlockRun

Create a temporary, isolated Python 3.11 CPU environment without supplying a program. No input is required for the defaults: one CPU core, 512 MB of memory and a 300-second lifetime.

Your AI

Use with your AI

For tasks with several steps, continue in the AI you already use.

CodexClaude CodeCursorWindsurfCline

View instructions

Use `create-modal-sandbox-blockrun` to create a short-lived Python 3.11 CPU sandbox. Use one CPU core and 512 MB of memory, omit GPU selection, and use my requested supported short lifetime or the default 300 seconds. Reuse my Toolmu connection, or follow https://toolmu.com/SKILL.md if setup is needed. Work within my current budget and authorization. Report the actual sandbox identifier, creation state, creation time and returned resource configuration. Keep running code or other sandbox actions separate from creation.

Task:
Create a temporary Python workspace for [30 seconds].

Paste into your connected AI's conversation.

Connection guide

Up to 0.01452 credits / call

The final charge is based on confirmed usage. Unused reserved credits return to your available balance.

BlockRun

Create a Modal Sandbox for Python | BlockRun

Create a temporary, isolated Python 3.11 CPU environment without supplying a program. No input is required for the defaults: one CPU core, 512 MB of memory and a 300-second lifetime.

You receive

The creation response gives you a sandbox identifier, its state at creation and its creation timestamp, together with the returned CPU, memory, image, GPU selection and lifetime configuration. Your Agent can arrange these details so you can see what was created and keep the identifier as a reference for a separately supported sandbox action.

Start with your task

Create a temporary Python workspace for [30 seconds].

What to know

Creating the sandbox does not execute your code or return program output. The sandbox is temporary and the supplier terminates it when its configured lifetime ends. Python 3.11 is the managed image. GPU allocation and longer sessions depend on supplier support and the current Tool’s allowed configuration and cost; they are not guaranteed by an optional input. Any later action must meet the sandbox’s access requirements.

Inputs & outputs

Inspect the current inputs, availability, and maximum charge before starting.

Input schema

Input schema
Field / Path	Type	Requirement	Meaning
Sandbox preferences`body`	`object`	Optional	Optional resource and lifetime preferences. This creation request does not include a program or command.
CPU cores`body.cpu`	`number`	Optional	Requested CPU cores; default 1. The supplier CPU-only limit is one core.
GPU preference`body.gpu`	`string`	Optional	Optional GPU preference. Supplier type names are T4, L4, A10G, A100 and H100. Omit for CPU-only creation; allocation must fit supported resources and the current Tool allowance.
Runtime image`body.image`	`string`	Optional	Managed runtime image. The available image is python:3.11.
Memory`body.memory`	`number`	Optional	Requested RAM in MB; default 512. The supplier CPU-only limit is 1,024 MB.
Sandbox lifetime`body.timeout`	`number`	Optional	Requested sandbox lifetime in seconds; default 300. This is the resource lifetime, not a command timeout. Longer requests depend on supplier and Tool limits.

View raw JSON

{
  "type": "object",
  "required": [],
  "properties": {
    "body": {
      "type": "object",
      "required": [],
      "properties": {
        "cpu": {
          "type": "number",
          "description": "CPU cores (max 1 CPU-only, 8 for GPU sandboxes, default: 1)"
        },
        "gpu": {
          "type": "string",
          "description": "Optional GPU type. One of: T4, L4, A10G, A100, H100. Flat (â¤300s): T4 $0.05, L4 $0.08, A10G $0.1, A100 $0.2, H100 $0.4. Hourly: T4 $1.5, L4 $2, A10G $2.5, A100 $4, H100 $8/hour."
        },
        "image": {
          "type": "string",
          "description": "Managed image. Only `python:3.11` is currently available."
        },
        "memory": {
          "type": "number",
          "description": "Memory in MB (max 1024 CPU-only, 32768 for GPU sandboxes, default: 512)"
        },
        "timeout": {
          "type": "number",
          "description": "Sandbox lifetime in seconds (max 86400 = 24h, default: 300). >300s switches to hourly billing."
        }
      }
    }
  },
  "additionalProperties": false
}

Result schema

No fixed output contract is available. Field types reflect saved result evidence; individual responses can differ.

Result schema
Field / Path	Type	Meaning
Sandbox identifier`result.sandbox_id`	`string`	Identifier assigned to the created sandbox. Use the actual returned value as a reference for separately supported actions.
Creation state`result.status`	`string`	Resource state reported at creation. A running state does not mean a program has executed successfully or that the resource remains active later.
Created at`result.created_at`	`string`	Resource creation timestamp in ISO 8601 format. Read its stated time offset; this is distinct from the Tool call completion time.
Returned configuration`result.config`	`object`	Resource settings returned after creation. Read these values to see the assigned configuration rather than assuming every preference was applied.
CPU cores`result.config.cpu`	`number`	Returned CPU-core configuration.
GPU selection`result.config.gpu`	`null`	Returned GPU selection. Null indicates no GPU selection for that request; it is not a numeric zero.
Runtime image`result.config.image`	`string`	Returned managed runtime image.
Memory`result.config.memory`	`number`	Returned RAM configuration in MB.
Sandbox lifetime`result.config.timeout`	`number`	Returned sandbox lifetime in seconds. It does not describe how long a program took to run.

Additional notes

Choosing a resource profile

The BlockRun Modal sandbox documentation describes the managed Python environment and its resource controls. For CPU-only creation, the supplier limits resources to one CPU core and 1,024 MB of memory. The defaults use 512 MB and a lifetime of 300 seconds.

GPU configurations and longer lifetimes use different supplier pricing. A configuration must fit both the supplier’s supported limits and this Tool’s current call allowance. Increasing your personal budget does not expand the Tool’s allowed request. Use the CPU defaults or a supported short request rather than assuming every larger setting in supplier documentation is available here.

After creation

Keep the actual returned identifier when a separate supported action needs to refer to this resource. Follow-up use depends on that action’s access requirements; the creation response alone does not establish control from a personal wallet or account. The returned state describes the resource at creation, rather than providing continuous monitoring.

Questions about this tool.

Inputs, results and details to know before running it.

Get connected

The managed image available through this Tool is python:3.11. Custom images and setup commands are not offered by this creation request.

Create a Modal Sandbox for Python | BlockRun

Create a Modal Sandbox for Python | BlockRun

You receive

Start with your task

What to know

Inputs & outputs

Input schema

Result schema

Choosing a resource profile

After creation

Tell your AI what you need

Choose how long to keep it

Check what was created

Questions about this tool.

You receive

Start with your task

What to know

Inputs & outputs

Input schema

Result schema

Choosing a resource profile

After creation

Tell your AI what you need

Choose how long to keep it

Check what was created

Questions about this tool.

Can I use another container image?

Can I keep the sandbox indefinitely?