Roboflow Clip API
The Clip API from Roboflow — 3 operation(s) for clip.
The Clip API from Roboflow — 3 operation(s) for clip.
Every API here is available over the APIs.io API and to AI agents over MCP.
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.curl "https://apis.io/api/v1/apis/roboflow-clip-api"
curl "https://apis.io/api/v1/apis?limit=25"
Discovery needs no key. Ratings and market analysis are Pro.
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
openapi: 3.2.0
info:
title: Roboflow Clip API
version: 1.3.8
contact:
name: Roboflow Inc.
url: https://roboflow.com/contact
email: help@roboflow.com
license:
name: Apache 2.0
url: https://www.apache.org/licenses/LICENSE-2.0.html
termsOfService: https://roboflow.com/terms
description: 'Operations tagged Clip across 2 of this provider''s published API definitions: roboflow-clip-api-openapi.yml, roboflow-inference-openapi.json. Each path carries the servers of the definition it was published in.'
servers:
- url: https://serverless.roboflow.com
description: Base URL declared by the provider in apis.yml (roadmap#122).
tags:
- name: Clip
paths:
/clip/embed_image:
post:
summary: CLIP Image Embeddings
description: Run the Open AI CLIP model to embed image data.
operationId: clip_embed_image_clip_embed_image_post
parameters:
- name: api_key
in: query
required: false
schema:
anyOf:
- type: string
- type: 'null'
description: Roboflow API Key that will be passed to the model during initialization for artifact retrieval
title: Api Key
description: Roboflow API Key that will be passed to the model during initialization for artifact retrieval
- name: countinference
in: query
required: false
schema:
anyOf:
- type: boolean
- type: 'null'
title: Countinference
- name: service_secret
in: query
required: false
schema:
anyOf:
- type: string
- type: 'null'
title: Service Secret
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/ClipImageEmbeddingRequest'
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/ClipEmbeddingResponse'
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
tags:
- Clip
servers:
- url: https://serverless.roboflow.com
description: Base URL declared by the provider in apis.yml (roadmap#122).
/clip/embed_text:
post:
summary: CLIP Text Embeddings
description: Run the Open AI CLIP model to embed text data.
operationId: clip_embed_text_clip_embed_text_post
parameters:
- name: api_key
in: query
required: false
schema:
anyOf:
- type: string
- type: 'null'
description: Roboflow API Key that will be passed to the model during initialization for artifact retrieval
title: Api Key
description: Roboflow API Key that will be passed to the model during initialization for artifact retrieval
- name: countinference
in: query
required: false
schema:
anyOf:
- type: boolean
- type: 'null'
title: Countinference
- name: service_secret
in: query
required: false
schema:
anyOf:
- type: string
- type: 'null'
title: Service Secret
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/ClipTextEmbeddingRequest'
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/ClipEmbeddingResponse'
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
tags:
- Clip
servers:
- url: https://serverless.roboflow.com
description: Base URL declared by the provider in apis.yml (roadmap#122).
/clip/compare:
post:
summary: CLIP Compare
description: Run the Open AI CLIP model to compute similarity scores.
operationId: clip_compare_clip_compare_post
parameters:
- name: api_key
in: query
required: false
schema:
anyOf:
- type: string
- type: 'null'
description: Roboflow API Key that will be passed to the model during initialization for artifact retrieval
title: Api Key
description: Roboflow API Key that will be passed to the model during initialization for artifact retrieval
- name: countinference
in: query
required: false
schema:
anyOf:
- type: boolean
- type: 'null'
title: Countinference
- name: service_secret
in: query
required: false
schema:
anyOf:
- type: string
- type: 'null'
title: Service Secret
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/ClipCompareRequest'
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/ClipCompareResponse'
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
tags:
- Clip
servers:
- url: https://serverless.roboflow.com
description: Base URL declared by the provider in apis.yml (roadmap#122).
components:
schemas:
ValidationError:
properties:
loc:
items:
anyOf:
- type: string
- type: integer
type: array
title: Location
msg:
type: string
title: Message
type:
type: string
title: Error Type
type: object
required:
- loc
- msg
- type
title: ValidationError
ClipCompareResponse:
properties:
inference_id:
anyOf:
- type: string
- type: 'null'
title: Inference Id
description: Unique identifier of inference
frame_id:
anyOf:
- type: integer
- type: 'null'
title: Frame Id
description: The frame id of the image used in inference if the input was a video
time:
anyOf:
- type: number
- type: 'null'
title: Time
description: The time in seconds it took to produce the similarity scores including preprocessing
similarity:
anyOf:
- items:
type: number
type: array
- additionalProperties:
type: number
type: object
title: Similarity
parent_id:
anyOf:
- type: string
- type: 'null'
title: Parent Id
description: Identifier of parent image region. Useful when stack of detection-models is in use to refer the RoI being the input to inference
type: object
required:
- similarity
title: ClipCompareResponse
description: "Response for CLIP comparison.\n\nAttributes:\n similarity (Union[List[float], Dict[str, float]]): Similarity scores.\n time (float): The time in seconds it took to produce the similarity scores including preprocessing."
ClipImageEmbeddingRequest:
properties:
id:
type: string
title: Id
api_key:
anyOf:
- type: string
- type: 'null'
title: Api Key
description: Roboflow API Key that will be passed to the model during initialization for artifact retrieval
usage_billable:
type: boolean
title: Usage Billable
default: true
start:
anyOf:
- type: number
- type: 'null'
title: Start
source:
anyOf:
- type: string
- type: 'null'
title: Source
source_info:
anyOf:
- type: string
- type: 'null'
title: Source Info
stream_pipeline_context_id:
anyOf:
- type: string
- type: 'null'
title: Stream Pipeline Context Id
description: Internal stream-pipeline frame pairing id. Not part of the public API.
disable_model_monitoring:
anyOf:
- type: boolean
- type: 'null'
title: Disable Model Monitoring
description: If true, disables model monitoring for this request
default: false
clip_version_id:
anyOf:
- type: string
- type: 'null'
title: Clip Version Id
description: The version ID of CLIP to be used for this request. Must be one of RN101, RN50, RN50x16, RN50x4, RN50x64, ViT-B-16, ViT-B-32, ViT-L-14-336px, and ViT-L-14.
default: ViT-B-16
examples:
- ViT-B-16
model_id:
anyOf:
- type: string
- type: 'null'
title: Model Id
image:
anyOf:
- items:
$ref: '#/components/schemas/InferenceRequestImage'
type: array
- $ref: '#/components/schemas/InferenceRequestImage'
title: Image
type: object
required:
- id
- image
title: ClipImageEmbeddingRequest
description: "Request for CLIP image embedding.\n\nAttributes:\n image (Union[List[InferenceRequestImage], InferenceRequestImage]): Image(s) to be embedded."
ClipEmbeddingResponse:
properties:
inference_id:
anyOf:
- type: string
- type: 'null'
title: Inference Id
description: Unique identifier of inference
frame_id:
anyOf:
- type: integer
- type: 'null'
title: Frame Id
description: The frame id of the image used in inference if the input was a video
time:
anyOf:
- type: number
- type: 'null'
title: Time
description: The time in seconds it took to produce the embeddings including preprocessing
embeddings:
items:
items:
type: number
type: array
type: array
title: Embeddings
description: A list of embeddings, each embedding is a list of floats
examples:
- '[[0.12, 0.23, 0.34, ..., 0.43]]'
type: object
required:
- embeddings
title: ClipEmbeddingResponse
description: "Response for CLIP embedding.\n\nAttributes:\n embeddings (List[List[float]]): A list of embeddings, each embedding is a list of floats.\n time (float): The time in seconds it took to produce the embeddings including preprocessing."
InferenceRequestImage:
properties:
type:
type: string
title: Type
description: The type of image data provided, one of 'url', 'base64', or 'numpy'
examples:
- url
value:
anyOf:
- {}
- type: 'null'
title: Value
description: Image data corresponding to the image type, if type = 'url' then value is a string containing the url of an image, else if type = 'base64' then value is a string containing base64 encoded image data, else if type = 'numpy' then value is binary numpy data serialized using pickle.dumps(); array should 3 dimensions, channels last, with values in the range [0,255].
examples:
- http://www.example-image-url.com
type: object
required:
- type
title: InferenceRequestImage
description: "Image data for inference request.\n\nAttributes:\n type (str): The type of image data provided, one of 'url', 'base64', or 'numpy'.\n value (Optional[Any]): Image data corresponding to the image type."
ClipCompareRequest:
properties:
id:
type: string
title: Id
api_key:
anyOf:
- type: string
- type: 'null'
title: Api Key
description: Roboflow API Key that will be passed to the model during initialization for artifact retrieval
usage_billable:
type: boolean
title: Usage Billable
default: true
start:
anyOf:
- type: number
- type: 'null'
title: Start
source:
anyOf:
- type: string
- type: 'null'
title: Source
source_info:
anyOf:
- type: string
- type: 'null'
title: Source Info
stream_pipeline_context_id:
anyOf:
- type: string
- type: 'null'
title: Stream Pipeline Context Id
description: Internal stream-pipeline frame pairing id. Not part of the public API.
disable_model_monitoring:
anyOf:
- type: boolean
- type: 'null'
title: Disable Model Monitoring
description: If true, disables model monitoring for this request
default: false
clip_version_id:
anyOf:
- type: string
- type: 'null'
title: Clip Version Id
description: The version ID of CLIP to be used for this request. Must be one of RN101, RN50, RN50x16, RN50x4, RN50x64, ViT-B-16, ViT-B-32, ViT-L-14-336px, and ViT-L-14.
default: ViT-B-16
examples:
- ViT-B-16
model_id:
anyOf:
- type: string
- type: 'null'
title: Model Id
subject:
anyOf:
- $ref: '#/components/schemas/InferenceRequestImage'
- type: string
title: Subject
description: The type of image data provided, one of 'url' or 'base64'
examples:
- url
subject_type:
type: string
title: Subject Type
description: The type of subject, one of 'image' or 'text'
default: image
examples:
- image
prompt:
anyOf:
- items:
$ref: '#/components/schemas/InferenceRequestImage'
type: array
- $ref: '#/components/schemas/InferenceRequestImage'
- type: string
- items:
type: string
type: array
- additionalProperties:
anyOf:
- $ref: '#/components/schemas/InferenceRequestImage'
- type: string
type: object
title: Prompt
prompt_type:
type: string
title: Prompt Type
description: The type of prompt, one of 'image' or 'text'
default: text
examples:
- text
type: object
required:
- id
- subject
- prompt
title: ClipCompareRequest
description: "Request for CLIP comparison.\n\nAttributes:\n subject (Union[InferenceRequestImage, str]): The type of image data provided, one of 'url' or 'base64'.\n subject_type (str): The type of subject, one of 'image' or 'text'.\n prompt (Union[List[InferenceRequestImage], InferenceRequestImage, str, List[str], Dict[str, Union[InferenceRequestImage, str]]]): The prompt for comparison.\n prompt_type (str): The type of prompt, one of 'image' or 'text'."
HTTPValidationError:
properties:
detail:
items:
$ref: '#/components/schemas/ValidationError'
type: array
title: Detail
type: object
title: HTTPValidationError
ClipTextEmbeddingRequest:
properties:
id:
type: string
title: Id
api_key:
anyOf:
- type: string
- type: 'null'
title: Api Key
description: Roboflow API Key that will be passed to the model during initialization for artifact retrieval
usage_billable:
type: boolean
title: Usage Billable
default: true
start:
anyOf:
- type: number
- type: 'null'
title: Start
source:
anyOf:
- type: string
- type: 'null'
title: Source
source_info:
anyOf:
- type: string
- type: 'null'
title: Source Info
stream_pipeline_context_id:
anyOf:
- type: string
- type: 'null'
title: Stream Pipeline Context Id
description: Internal stream-pipeline frame pairing id. Not part of the public API.
disable_model_monitoring:
anyOf:
- type: boolean
- type: 'null'
title: Disable Model Monitoring
description: If true, disables model monitoring for this request
default: false
clip_version_id:
anyOf:
- type: string
- type: 'null'
title: Clip Version Id
description: The version ID of CLIP to be used for this request. Must be one of RN101, RN50, RN50x16, RN50x4, RN50x64, ViT-B-16, ViT-B-32, ViT-L-14-336px, and ViT-L-14.
default: ViT-B-16
examples:
- ViT-B-16
model_id:
anyOf:
- type: string
- type: 'null'
title: Model Id
text:
anyOf:
- items:
type: string
type: array
- type: string
title: Text
description: A string or list of strings
examples:
- The quick brown fox jumps over the lazy dog
type: object
required:
- id
- text
title: ClipTextEmbeddingRequest
description: "Request for CLIP text embedding.\n\nAttributes:\n text (Union[List[str], str]): A string or list of strings."
x-refined-from:
- roboflow-clip-api-openapi.yml
- roboflow-inference-openapi.json