How AI is applied across API Evangelist and APIs.io. Read my AI disclosure →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

Need help?

Contact us
Prime Intellect

Prime Intellect Sandbox API

Secure remote code-execution sandboxes for AI agents. Create and manage Python-3.11-slim-based sandboxes, expose ports for HTTP services running inside the sandbox, open SSH sessions, pull rich error context for failures, and provision reverse tunnels back into a sandbox from an external network. Available as a lightweight `prime-sandboxes` Python package (~50KB) in addition to the full `prime` CLI/SDK.

Documentation Provider Profile APIs.io OpenAPI GitHub

Prime Intellect Sandbox API is one of 20 APIs that Prime Intellect publishes on the APIs.io network, described by a machine-readable OpenAPI specification.

This API exposes 1 JSON Schema definition.

Tagged areas include Sandbox, Code Execution, Agents, and Tunnels. The published artifact set on APIs.io includes API documentation, an OpenAPI specification, and 1 JSON Schema.

This API exposes 14 operations across 10 paths, and defines 21 schemas. It is described by OpenAPI 3.2.0, at version 0.1.0.

Requests are made against a single base URL, https://api.primeintellect.ai.

14 operations 10 paths 21 schemas 4 DELETE6 GET4 POST

Metadata

The identity and technical contract details declared by the specification.

Specification
OpenAPI 3.2.0
API Version
0.1.0
Base URL
https://api.primeintellect.ai
Authentication
HTTP Bearer
Contact
Prime Intellect
Resource Areas
1

Authentication & Security 1

Prime Intellect Sandbox API declares 1 security scheme for authenticating requests. It accepts HTTP bearer tokens (HTTPBearer). By default, every request must be authenticated.

Paths & Operations 14

Across 10 paths, the API surfaces 14 operations — 4 DELETE, 6 GET, 4 POST. Each is listed below with its method, path, parameters, and response codes.

Sandbox 14
POST
/api/v1/sandbox
Create Sandbox Endpoint
create_sandbox_endpoint_api_v1_sandbox_post body → 201401422
GET
/api/v1/sandbox
List Sandboxes
list_sandboxes_api_v1_sandbox_get 7 params → 200401422
DELETE
/api/v1/sandbox
Bulk Delete Sandboxes Endpoint
bulk_delete_sandboxes_endpoint_api_v1_sandbox_delete body → 200401422
GET
/api/v1/sandbox/expose/all
List All Exposed Ports Endpoint
list_all_exposed_ports_endpoint_api_v1_sandbox_expose_all_get → 200401422
GET
/api/v1/sandbox/{sandbox_id}
Get Sandbox Endpoint
get_sandbox_endpoint_api_v1_sandbox__sandbox_id__get 1 param → 200401422
DELETE
/api/v1/sandbox/{sandbox_id}
Delete Sandbox Endpoint
delete_sandbox_endpoint_api_v1_sandbox__sandbox_id__delete 1 param → 200401422
POST
/api/v1/sandbox/{sandbox_id}/auth
Get Sandbox Auth Token
get_sandbox_auth_token_api_v1_sandbox__sandbox_id__auth_post 1 param → 200401422
GET
/api/v1/sandbox/{sandbox_id}/error-context
Get Sandbox Error Context Endpoint
get_sandbox_error_context_endpoint_api_v1_sandbox__sandbox_id__error_context_get 1 param → 200401422
POST
/api/v1/sandbox/{sandbox_id}/expose
Expose Port Endpoint
expose_port_endpoint_api_v1_sandbox__sandbox_id__expose_post 1 param body → 200401422
GET
/api/v1/sandbox/{sandbox_id}/expose
List Exposed Ports Endpoint
list_exposed_ports_endpoint_api_v1_sandbox__sandbox_id__expose_get 1 param → 200401422
DELETE
/api/v1/sandbox/{sandbox_id}/expose/{exposure_id}
Unexpose Port Endpoint
unexpose_port_endpoint_api_v1_sandbox__sandbox_id__expose__exposure_id__delete 2 params → 200401422
GET
/api/v1/sandbox/{sandbox_id}/logs
Get Sandbox Logs Endpoint
get_sandbox_logs_endpoint_api_v1_sandbox__sandbox_id__logs_get 1 param → 200401422
POST
/api/v1/sandbox/{sandbox_id}/ssh-session
Create Ssh Session Endpoint
create_ssh_session_endpoint_api_v1_sandbox__sandbox_id__ssh_session_post 1 param body → 200401422
DELETE
/api/v1/sandbox/{sandbox_id}/ssh-session/{session_id}
Close Ssh Session Endpoint
close_ssh_session_endpoint_api_v1_sandbox__sandbox_id__ssh_session__session_id__delete 2 params → 200401422

Schemas 21

The contract defines 21 schemas that model the data the API accepts and returns. The most detailed are SandboxResponse (29 properties), CreateSandboxRequest (20 properties), SSHSessionResponse (12 properties), ExposedPortInfo (10 properties). Each schema is shown below with its type and property counts.

SandboxAuthResponse
object
5 properties 5 required
SandboxResponse
object
29 properties 21 required
BulkDeleteSandboxRequest
object
5 properties
ExposePortRequest
object
3 properties 1 required
ListExposedPortsResponse
object
1 property 1 required
DeleteSandboxResponse
object
2 properties 2 required
SandboxErrorContextResponse
object
Response for error context lookups
3 properties
CreateSSHSessionRequest
object
1 property
SandboxLogsResponse
object
1 property 1 required
GPUType
string
ErrorResponse
object
1 property 1 required
ErrorDetail
object
2 properties 2 required
CreateSandboxRequest
object
20 properties 2 required
SandboxListResponse
object
5 properties 5 required
BulkDeleteSandboxResponse
object
3 properties 1 required
SandboxStatus
string
UnexposePortResponse
object
2 properties 2 required
ExposedPortInfo
object
10 properties 6 required
SSHSessionResponse
object
12 properties 12 required
AdvancedConfigs
object
ExposePortResponse
object
9 properties 6 required

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

prime-intellect-sandbox-api-openapi.yml Raw ↑

Other APIs Prime Intellect publishes across the network.

Prime Intellect Training API
AE Profile APIs.io
Prime Intellect Inference API
AE Profile APIs.io
Prime Intellect admin-clusters API
AE Profile APIs.io
Prime Intellect admin-users API
AE Profile APIs.io
Prime Intellect Availability API
AE Profile APIs.io
Prime Intellect Billing API
AE Profile APIs.io
Prime Intellect Disks API
AE Profile APIs.io
Prime Intellect evals API
AE Profile APIs.io
Prime Intellect Feedback API
AE Profile APIs.io
Prime Intellect FRP Plugin API
AE Profile APIs.io
Prime Intellect hosted-evaluations API
AE Profile APIs.io
Prime Intellect Images API
AE Profile APIs.io
#Sandbox#Code Execution#Agents#Tunnels
← Back to P APIs
API Details
ID
prime-intellect:prime-intellect-sandbox-api
Base URL
https://api.primeintellect.ai
Docs
https://docs.primeintellect.ai/sandboxes/overview
Provider
Prime Intellect
APIs.io →  GitHub →
Explore more
All APIs Providers APIs.io Network
Work with this as data

Every API here is available over the API and to AI agents over MCP. APIs is not yet its own endpoint on the v1 API. Reach this content through network search and the tag graph, or the MCP server below.

Installs https://mcp.apievangelist.com/mcp in Claude, Cursor, VS Code and the rest — one button, every client.

MCP tools for apis
4 tools reach this content
  • search_api_evangelistSearch every content type across the network at once.
  • find_relatedThe shared-tag relevance graph — what else covers this.
  • get_tagEverything one tag labels, across all content types.
  • guide_topicPRO — a curated bundle for a topic: area, guidance, rules, papers, stories, services.
All tools & prompts
Call it yourself
curl for this page
Search the network for this 
curl "https://api.apievangelist.com/v1/search?q=prime-intellect-sandbox-api&limit=10"
Everything under a tag 
curl "https://api.apievangelist.com/v1/tags/prime-intellect-sandbox-api"

Discovery needs no key. Full bodies and the synthesis endpoints are Pro.

Get an API key

Free tier, no email required. Sign in with whichever identity you already have.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have. Your account

Where this information came from

This is an independent, third-party profile of Prime Intellect Sandbox API, published by API Evangelist. We do not operate, host, resell, or support these APIs, and we are not affiliated with or endorsed by the company unless stated above. Everything here is built from publicly available information — the company's own site, developer portal, documentation, public repositories, and the specifications it publishes for public use. Nothing is obtained by breaching a system, defeating an access control, or using credentials.

The Kin Score and Agent Readiness rating are independently calculated assessments of a company's public API artifacts, scored against a published rubric. They are not certifications, endorsements, security assessments, or audits.

Corrections, re-scores, and removal are free — no partnership or purchase required, and you do not need to justify the request. A removed company is recorded as unrated, never scored zero for having asked. Acknowledgement within one business day; removal within two.

info@apievangelist.com · Read the full data-sourcing policy →
On a security or compliance team? Put security in the subject line and you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.