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

Qdrant Collections API

Searchable collections of points.

Qdrant Collections API is one of 9 APIs that Qdrant publishes on the APIs.io network, described by a machine-readable OpenAPI specification.

Tagged areas include Collection. The published artifact set on APIs.io includes an OpenAPI specification and API documentation.

This API exposes 7 operations across 4 paths, and defines 97 schemas. It is described by OpenAPI 3.2.0, at version master.

Requests are made against a single base URL, {protocol}://{hostname}:{port}.

7 operations 4 paths 97 schemas 1 DELETE4 GET1 PATCH1 PUT

Metadata

The identity and technical contract details declared by the specification.

Specification
OpenAPI 3.2.0
API Version
master
Server
{protocol}://{hostname}:{port}
Authentication
API Key, HTTP Bearer
License
Resource Areas
1

Authentication & Security 2

Qdrant Collections API declares 2 security schemes for authenticating requests. An API key is passed in the header as api-key (api-key). It accepts HTTP bearer tokens (bearerAuth). By default, every request must be authenticated, though some operations may also be called without credentials.

  • api-key — Authorization key, either read-write or read-only

Paths & Operations 7

Across 4 paths, the API surfaces 7 operations — 1 DELETE, 4 GET, 1 PATCH, 1 PUT. Each is listed below with its method, path, parameters, and response codes.

Collections 7

Searchable collections of points.

GET
/collections
List collections
get_collections → default4XX200
GET
/collections/{collection_name}
Collection info
get_collection 1 param → default4XX200
PUT
/collections/{collection_name}
Create collection
create_collection 2 params body → default4XX200
PATCH
/collections/{collection_name}
Update collection parameters
update_collection 2 params body → default4XX200
DELETE
/collections/{collection_name}
Delete collection
delete_collection 2 params → default4XX200
GET
/collections/{collection_name}/exists
Check the existence of a collection
collection_exists 1 param → default4XX200
GET
/collections/{collection_name}/optimizations
Get optimization progress
get_optimizations 3 params → default4XX200

Schemas 97

The contract defines 97 schemas that model the data the API accepts and returns. The most detailed are StrictModeConfig (20 properties), StrictModeConfigOutput (20 properties), CreateCollection (13 properties), TextIndexParams (11 properties). Each schema is shown below with its type and property counts.

VectorsConfig
Vector params separator for single and multiple vector modes Single mode: { "size": 128, "distance": "Cosine" } or multiple mode: { "default": { "size": 128, "…
ScalarQuantization
object
1 property 1 required
ModelUsage
object
1 property 1 required
VectorParams
object
Params of single vector data storage
7 properties 2 required
Disabled
string
CollectionInfo
object
Current statistics and configuration of the collection
9 properties 5 required
UpdateCollection
object
Operation for updating parameters of the existing collection
8 properties
CollectionExistence
object
State of existence of a collection, true = exists, false = does not exist
1 property 1 required
OptimizersConfigDiff
object
9 properties
PayloadSchemaParams
Payload type with parameters
TextIndexParams
object
11 properties 1 required
QuantizationConfigDiff
WalConfigDiff
object
3 properties
KeywordIndexType
string
Snowball
string
CollectionStatus
string
Current state of the collection. Green - all good. Yellow - optimization is running, 'Grey' - optimizations are possible but not triggered, Red - some operatio…
DatetimeIndexType
string
SnowballLanguage
string
Languages supported by snowball stemmer.
StrictModeMultivectorConfigOutput
object
UuidIndexParams
object
4 properties 1 required
IntegerIndexType
string
OptimizationsResponse
object
Optimizations progress for the collection
5 properties 2 required
OptimizersConfig
object
9 properties 2 required
CollectionParamsDiff
object
5 properties
ProductQuantizationConfig
object
2 properties 1 required
OptimizationsSummary
object
4 properties 4 required
ScalarType
string
StrictModeSparse
object
1 property
ShardingMethod
string
BoolIndexType
string
PayloadIndexInfo
object
Display payload field type & index information
3 properties 2 required
QuantizationConfig
StrictModeConfig
object
20 properties
ScalarQuantizationConfig
object
3 properties 1 required
StrictModeSparseConfigOutput
object
CreateCollection
object
Operation for creating new collection and (optionally) specify index params
13 properties
StrictModeConfigOutput
object
20 properties
SparseVectorParams
object
Params of single sparse vector data storage
2 properties
MultiVectorConfig
object
1 property 1 required
OptimizationSegmentInfo
object
2 properties 2 required
WalConfig
object
3 properties 2 required
HnswConfig
object
Config of HNSW index
7 properties 3 required
CollectionWarning
object
1 property 1 required
KeywordIndexParams
object
4 properties 1 required
StrictModeMultivectorConfig
object
PendingOptimization
object
2 properties 2 required
Distance
string
Type of internal tags, build from payload Distance function types used to compare vectors
CollectionsResponse
object
1 property 1 required
Datatype
string
SnowballParams
object
2 properties 2 required
GeoIndexParams
object
3 properties 1 required
StrictModeSparseOutput
object
1 property
FloatIndexParams
object
4 properties 1 required
HnswConfigDiff
object
7 properties
StopwordsInterface
Usage
object
Usage of the hardware resources, spent to process the request
2 properties
UpdateQueueInfo
object
2 properties 1 required
TextIndexType
string
StopwordsSet
object
2 properties
CompressionRatio
string
VectorParamsDiff
object
3 properties
ErrorResponse
object
3 properties
StrictModeMultivector
object
1 property
OptimizersStatus
Current state of the collection
StrictModeSparseConfig
object
ProgressTree
object
7 properties 1 required
TrackerStatus
Represents the current state of the optimizer being tracked
SparseVectorsConfig
object
DatetimeIndexParams
object
4 properties 1 required
CollectionDescription
object
1 property 1 required
InferenceUsage
object
1 property 1 required
FloatIndexType
string
PayloadSchemaType
string
All possible names of payload types
BinaryQuantizationConfig
object
3 properties
MaxOptimizationThreads
SparseIndexParams
object
Configuration for sparse inverted index.
3 properties
Payload
object
MultiVectorComparator
string
StrictModeMultivectorOutput
object
1 property
MaxOptimizationThreadsSetting
string
BinaryQuantizationQueryEncoding
string
BoolIndexParams
object
3 properties 1 required
CollectionConfig
object
Information about the collection configuration
7 properties 3 required
StemmingAlgorithm
Different stemming algorithms with their configs.
CollectionParams
object
9 properties
Optimization
object
5 properties 5 required
UuidIndexType
string
ProductQuantization
object
1 property 1 required
Language
string
IntegerIndexParams
object
6 properties 1 required
BinaryQuantization
object
1 property 1 required
HardwareUsage
object
Usage of the hardware resources, spent to process the request
7 properties 7 required
VectorsConfigDiff
object
Vector update params for multiple vectors { "vectorname": { "hnswconfig": { "m": 8 } } }
TokenizerType
string
GeoIndexType
string
Modifier
string
If used, include weight modification, which will be applied to sparse vectors at query time: None - no modification (default) Idf - inverse document frequency,…
BinaryQuantizationEncoding
string

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

qdrant-collections-api-openapi.yml Raw ↑

Other APIs Qdrant publishes across the network.

Qdrant Aliases API
Qdrant Beta API
Qdrant Distributed API
Qdrant Indexes API
Qdrant Points API
Qdrant Search API
Qdrant Service API
Qdrant Snapshots API
Where this information came from

This is an independent, third-party profile of Qdrant Collections 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.