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

Portkey Guardrails API

Create, List, Retrieve, Update, and Delete prompt Guardrails.

Portkey Guardrails API is one of 51 APIs that Portkey publishes on the APIs.io network, described by a machine-readable OpenAPI specification.

Tagged areas include Guardrails. The published artifact set on APIs.io includes an OpenAPI specification, API documentation, an API reference, and a getting-started guide.

This API exposes 5 operations across 2 paths, and defines 43 schemas. It is described by OpenAPI 3.2.0, at version 2.0.0.

Requests are made against a single base URL, https://api.portkey.ai/v1.

5 operations 2 paths 43 schemas 1 DELETE2 GET1 POST1 PUT

Metadata

The identity and technical contract details declared by the specification.

Specification
OpenAPI 3.2.0
API Version
2.0.0
Base URL
https://api.portkey.ai/v1
Authentication
API Key, API Key, HTTP Bearer, API Key, API Key, API Key
License
Terms of Service
Resource Areas
1

Authentication & Security 6

Portkey Guardrails API declares 6 security schemes for authenticating requests. An API key is passed in the header as x-portkey-api-key (Portkey-Key). An API key is passed in the header as x-portkey-virtual-key (Virtual-Key). It accepts HTTP bearer tokens (Provider-Auth). An API key is passed in the header as x-portkey-provider (Provider-Name). An API key is passed in the header as x-portkey-config (Config). An API key is passed in the header as x-portkey-custom-host (Custom-Host). By default, every request must be authenticated.

Paths & Operations 5

Across 2 paths, the API surfaces 5 operations — 1 DELETE, 2 GET, 1 POST, 1 PUT. Each is listed below with its method, path, parameters, and response codes.

Guardrails 5

Create, List, Retrieve, Update, and Delete prompt Guardrails.

POST
/guardrails
Create a new guardrail
createGuardrail body → 200400403500
GET
/guardrails
List guardrails
listGuardrails 4 params → 200400403
GET
/guardrails/{guardrailId}
Get a specific guardrail
getGuardrail 1 param → 200403500
PUT
/guardrails/{guardrailId}
Update a guardrail
updateGuardrail 1 param body → 200400403
DELETE
/guardrails/{guardrailId}
Delete a guardrail
deleteGuardrail 1 param → 200403500

Schemas 43

The contract defines 43 schemas that model the data the API accepts and returns. The most detailed are AcuvityScanParameters (21 properties), GuardrailSummary (10 properties), JWTParameters (6 properties), AzureContentSafetyParameters (5 properties). Each schema is shown below with its type and property counts.

SentenceCountParameters
object
3 properties
AcuvityScanParameters
object
21 properties
PillarScanParameters
object
2 properties 1 required
GuardrailDetails
CharacterCountParameters
object
3 properties
RequiredMetadataKeysParameters
object
2 properties 2 required
ModelWhitelistParameters
object
1 property 1 required
AzureContentSafetyParameters
object
5 properties
PANWPrismaParameters
object
3 properties 1 required
EndsWithParameters
object
2 properties 1 required
JSONKeysParameters
object
2 properties 2 required
AzurePIIParameters
object
5 properties
JWTParameters
object
6 properties 2 required
AllowedRequestTypesParameters
object
Parameters for default.allowedRequestTypes check. Restrict which request types are allowed or blocked. You can use either or both; when both are specified, blo…
2 properties
PatronusCustomParameters
object
2 properties 1 required
CreateGuardrailResponse
object
3 properties 3 required
WordCountParameters
object
3 properties
GuardrailSummary
object
10 properties 6 required
UppercaseParameters
object
1 property
CreateGuardrailRequest
object
5 properties 3 required
JSONSchemaParameters
object
2 properties 1 required
PromptfooParameters
object
2 properties
ErrorResponse
object
1 property 1 required
Error
object
4 properties 4 required
ValidUrlsParameters
object
2 properties
RegexMatchParameters
object
2 properties 1 required
UpdateGuardrailRequest
object
3 properties
PatronusParameters
object
2 properties
ContainsParameters
object
2 properties 2 required
PortkeyModerationParameters
object
2 properties 1 required
BedrockGuardParameters
object
4 properties 2 required
GuardrailActions
object
Actions to take when guardrail checks fail or pass
4 properties 4 required
BasicParameters
object
Basic parameters with no specific requirements
AporiaParameters
object
2 properties 1 required
ListGuardrailsResponse
object
2 properties 2 required
WebhookParameters
object
4 properties 1 required
ContainsCodeParameters
object
2 properties 1 required
PortkeyLanguageParameters
object
3 properties
SydeGuardParameters
object
4 properties
PortkeyPIIParameters
object
3 properties 1 required
UpdateGuardrailResponse
object
3 properties 2 required
MistralModerationParameters
object
2 properties 1 required
GuardrailCheck
object
4 properties 1 required

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

portkey-guardrails-api-openapi.yml Raw ↑

Other APIs Portkey publishes across the network.

Portkey Analytics > Graphs API
Portkey Analytics > Groups API
Portkey Analytics > Summary API
Portkey Api-Keys API
Portkey Assistants API
Portkey Audio API
Portkey Audit Logs API
Portkey Batch API
Portkey Chat API
Portkey Collections API
Portkey Completions API
Portkey Configs API
Where this information came from

This is an independent, third-party profile of Portkey Guardrails 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.