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

Cognite Vision API

Vision API is deprecated. See [Deprecated and retired features](https://docs.cognite.com/cdf/deprecated) for details and timelines.The Vision contextualization endpoints enable extraction of information from imagery data based on their visual content. For example, you can detect external ID or name of assets, detect and read value of gauges or identify common industrial objects in images.This service has support for batch processing which enables processing of multiple image files via an asynchronous prediction request. A new contextualization job is triggered by sending a POST request to the service. The response of the POST request contains a job ID, which can then be used to make subsequent calls to check the status and retrieve the results of the job once it is completed.

Cognite Vision API is one of 90 APIs that Cognite publishes on the APIs.io network, described by a machine-readable OpenAPI specification.

Tagged areas include Vision. The published artifact set on APIs.io includes an OpenAPI specification.

This API exposes 2 operations across 2 paths, and defines 56 schemas. It is described by OpenAPI 3.2.0, at version v1.

Requests are made against a single base URL, https://{cluster}.cognitedata.com/api/v1/projects/{project}.

2 operations 2 paths 56 schemas 1 GET1 POST

Metadata

The identity and technical contract details declared by the specification.

Specification
OpenAPI 3.2.0
API Version
v1
Base URL
https://api.cognitedata.com
Authentication
HTTP Bearer, OAuth 2.0, OAuth 2.0, OAuth 2.0, OpenID Connect
Resource Areas
1

Authentication & Security 5

Cognite Vision API declares 5 security schemes for authenticating requests. It accepts HTTP bearer tokens (OpenID Connect or OAuth2 token) (oidc-token). It supports OAuth 2.0 (oauth2-client-credentials) using the clientCredentials flow, exposing 1 scope. It supports OAuth 2.0 (oauth2-auth-code) using the authorizationCode flow, exposing 1 scope. It supports OAuth 2.0 (oauth2-open-industrial-data) using the clientCredentials flow, exposing 1 scope. It supports OpenID Connect (org-oidc-token) discovered at https://auth.cognite.com/.well-known/openid-configuration. By default, every request must be authenticated.

  • oidc-token — Access token issued by the CDF project's configured identity provider. Access token must be an OpenID Connect token, and the project must be configured to acce…
  • oauth2-client-credentials — Access token issued by the CDF project's configured identity provider. Access token must be an OpenID Connect token, and the project must be configured to acce…
  • oauth2-auth-code — Access token issued by the CDF project's configured identity provider. Access token must be an OpenID Connect token, and the project must be configured to acce…
  • oauth2-open-industrial-data — Auth flow for Open Industrial Data. Get your client secret from https://hub.cognite.com/open-industrial-data-211.
  • org-oidc-token — Access token issued by the Cognite authorization server, and valid for the target organization. The token must be an OpenID Connect token, and it can be obtain…

Paths & Operations 2

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

Vision 2

Vision API is deprecated. See [Deprecated and retired features](https://docs.cognite.com/cdf/deprecated) for details and timelines. The Vision contextualization endpoints enable e…

POST
/context/vision/extractdeprecated
Extract features from images
postVisionExtract 1 param body → 200400
GET
/context/vision/extract/{jobId}deprecated
Retrieve results from a feature extraction job on images
getVisionExtract 2 params → 200400

Schemas 56

The contract defines 56 schemas that model the data the API accepts and returns. The most detailed are VisionExtractPredictions (9 properties), FeatureParameters (9 properties), Annotations.ObjectDetection (6 properties), StatusSchema (5 properties). Each schema is shown below with its type and property counts.

Annotations.Point
object
Point in a 2D-Cartesian coordinate system with origin at the top-left corner of the page
3 properties 2 required
Annotations.PolyLine
object
A polygonal chain consisting of n vertices
2 properties 1 required
MinLevel
number
The min value of the gauge.
FileReference
object
An external-id or instance-id reference to the referenced file.
3 required
ValveDetection
string
Detect and read state of a valve in an image. In beta. Available only when the cdf-version: beta header is provided.
DialGaugeDetectionParameters
object
Parameters for dial gauge detection and reading. In beta. Available only when the cdf-version: beta header is provided.
5 properties
AssetTagDetection
string
Detect external ID or name of assets (from your CDF projects) in images. Usage of this feature requires ['assetsAcl:READ'] capability.
FeatureParameters
object
Feature-specific parameters. New feature extractor parameters may appear.
9 properties
MaxLevel
number
The max value of the gauge.
VisionFileExternalId
string
The external ID of a file in CDF.
DeadAngle
number
The angle between the start and end point on the bottom part of an analog gauge, measured in degrees.
VisionInstanceId
object
The instance id of a file in CDF.
2 properties 2 required
Annotations.cogmono__annotation_types__images__AssetLink
object
Models a link to a CDF Asset referenced in an image
5 properties 3 required
Annotations.AssetRef
object
A reference to an asset. Either the internal ID or the external ID must be provided (exactly one).
2 properties
LevelGaugeDetection
string
Detect and read value of level gauges in images. In beta. Available only when the cdf-version: beta header is provided.
EpochTimestamp
integer
The number of milliseconds since 00:00:00 Thursday, 1 January 1970, Coordinated Universal Time (UTC), minus leap seconds.
LevelGaugeDetectionParameters
object
Parameters for level gauge detection and reading. In beta. Available only when the cdf-version: beta header is provided.
3 properties
Annotations.Numerical
object
The numerical value of something
3 properties 2 required
Annotations.ObjectDetection
object
Models an image object detection represented by a label, a geometry, and optionally a confidence value.
6 properties 1 required
IndustrialObjectDetection
string
Detect industrial objects such as gauges and valves in images. In beta. Available only when the cdf-version: beta header is provided.
Annotations.BoundingBox
object
A plain rectangle
5 properties 4 required
FailedBatch
object
List of the items and the corresponding error message(s) per failed batch.
2 properties
JobId
integer
Contextualization job ID.
Annotations.TextRegion
object
Models an extracted text region in an image
3 properties 2 required
CommaPos
integer
Number of digits after comma in a digital gauge.
NonLinAngle
number
If the gauge is nonlinear, the non-linear angle from the metadata is used to part the scale in two separate linear scales. The first scale goes from min to 0.…
Annotations.Polygon
object
A closed polygon represented by n vertices. In other words, we assume that the first and last vertex are connected.
2 properties 1 required
PersonalProtectiveEquipmentDetectionParameters
object
Parameters for industrial personal protective equipment detection. In beta. Available only when the cdf-version: beta header is provided.
1 property
MinNumDigits
integer
Minimum number of digits on a digital gauge.
DialGaugeDetection
string
Detect and read value of dial gauges in images. In beta. Available only when the cdf-version: beta header is provided.
InstanceSpace
string
DigitalGaugeDetection
string
Detect and read value of digital gauges in images. In beta. Available only when the cdf-version: beta header is provided.
VisionAllOfFileId
object
3 properties 1 required
MaxNumDigits
integer
Maximum number of digits on a digital gauge.
Annotations.Boolean
object
The boolean value of something
3 properties 2 required
Annotations.KeypointCollection
object
Models a collection of keypoints represented by a label, a dictionary of keypoints (mapping from a (unique) label name to a keypoint), and optionally a confide…
4 properties 2 required
PeopleDetection
string
Detect people in images.
TextDetectionParameters
object
Parameters for text detection
1 property
Annotations.cogmono__annotation_types__primitives__geometry2d__Geometry
object
A geometry represented by exactly one of boundingbox, polygon and polyline which, respectively, represents a BoundingBox, Polygon and PolyLine.
3 properties
IndustrialObjectDetectionParameters
object
Parameters for industrial object detection. In beta. Available only when the cdf-version: beta header is provided.
1 property
StatusSchema
object
5 properties 4 required
PersonalProtectiveEquipmentDetection
string
Detect personal protective equipment, such as helmet, protective eyewear, and mask in images. In beta. Available only when the cdf-version: beta header is prov…
InstanceExternalId
string
PeopleDetectionParameters
object
Parameters for people detection.
1 property
VisionFileId
integer
The ID of a file in CDF.
TextDetection
string
Detect text in images.
Annotations.Keypoint
object
A point attached with additional information such as a confidence value and various attribute(s).
3 properties 1 required
JobStatus
string
The status of the job.
Error
object
Cognite API error.
4 properties 2 required
DigitalGaugeDetectionParameters
object
Parameters for digital gauge detection and reading. In beta. Available only when the cdf-version: beta header is provided.
4 properties
VisionExtractItem
object
3 properties 2 required
ThresholdParameter
number
The confidence threshold returns predictions as positive if their confidence score is the selected value or higher. A higher confidence threshold increases pre…
AssetTagDetectionParameters
object
Parameters for asset tag detection.
3 properties
ValveDetectionParameters
object
Parameters for detecting and reading the state of a valve. In beta. Available only when the cdf-version: beta header is provided.
1 property
VisionExtractPredictions
object
Detected features in images. New fields may appear in case new feature extractors are add.
9 properties
VisionExtractFeature

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

cognite-vision-api-openapi.yml Raw ↑

Other APIs Cognite publishes across the network.

Cognite Data Fusion API
Cognite 3D Asset Mapping API
Cognite 3D Files API
Cognite 3D Jobs API
Cognite 3D Model Revisions API
Cognite 3D Models API
Cognite Annotations API
Cognite Assets API
Cognite Connections API
Cognite Containers API
Cognite Data models API
Cognite Data point subscriptions API
Where this information came from

This is an independent, third-party profile of Cognite Vision 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.