Roboflow Infer API
The Infer API from Roboflow — 4 operation(s) for infer.
OpenAPI Specification
openapi: 3.2.0
info:
title: Roboflow Inference Server Infer API
description: Roboflow inference server
termsOfService: https://roboflow.com/terms
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
version: 1.3.8
tags:
- name: Infer
paths:
/infer/lmm:
post:
summary: Large multi-modal model infer
description: Run inference with the specified large multi-modal model
operationId: infer_lmm_infer_lmm_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/LMMInferenceRequest'
responses:
'200':
description: Successful Response
content:
application/json:
schema:
anyOf:
- $ref: '#/components/schemas/LMMInferenceResponse'
- type: array
items:
$ref: '#/components/schemas/LMMInferenceResponse'
- $ref: '#/components/schemas/StubResponse'
title: Response Infer Lmm Infer Lmm Post
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
tags:
- Infer
/infer/lmm/{model_id}:
post:
summary: Large multi-modal model infer with model ID in path
description: Run inference with the specified large multi-modal model. Model ID is specified in
the URL path (can contain slashes).
operationId: infer_lmm_with_model_id_infer_lmm__model_id__post
parameters:
- name: model_id
in: path
required: true
schema:
type: string
title: Model Id
- 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/LMMInferenceRequest'
responses:
'200':
description: Successful Response
content:
application/json:
schema:
anyOf:
- $ref: '#/components/schemas/LMMInferenceResponse'
- type: array
items:
$ref: '#/components/schemas/LMMInferenceResponse'
- $ref: '#/components/schemas/StubResponse'
title: Response Infer Lmm With Model Id Infer Lmm Model Id Post
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
tags:
- Infer
/infer/depth-estimation:
post:
summary: Depth Estimation
description: Run the depth estimation model to generate a depth map.
operationId: depth_estimation_infer_depth_estimation_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/DepthEstimationRequest'
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/DepthEstimationResponse'
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
tags:
- Infer
/infer/depth-estimation/{model_id}:
post:
summary: Depth Estimation with model ID in path
description: Run depth estimation. Model ID is specified in the URL path and can contain slashes.
operationId: depth_estimation_with_model_id_infer_depth_estimation__model_id__post
parameters:
- name: model_id
in: path
required: true
schema:
type: string
title: Model Id
- 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/DepthEstimationRequest'
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/DepthEstimationResponse'
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
tags:
- Infer
components:
schemas:
LMMInferenceRequest:
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
model_id:
anyOf:
- type: string
- type: 'null'
title: Model Id
description: A unique model identifier
example: raccoon-detector-1
model_type:
anyOf:
- type: string
- type: 'null'
title: Model Type
description: The type of the model, usually referring to what task the model performs
examples:
- object-detection
image:
anyOf:
- items:
$ref: '#/components/schemas/InferenceRequestImage'
type: array
- $ref: '#/components/schemas/InferenceRequestImage'
title: Image
disable_preproc_auto_orient:
anyOf:
- type: boolean
- type: 'null'
title: Disable Preproc Auto Orient
description: If true, the auto orient preprocessing step is disabled for this call.
default: false
disable_preproc_contrast:
anyOf:
- type: boolean
- type: 'null'
title: Disable Preproc Contrast
description: If true, the auto contrast preprocessing step is disabled for this call.
default: false
disable_preproc_grayscale:
anyOf:
- type: boolean
- type: 'null'
title: Disable Preproc Grayscale
description: If true, the grayscale preprocessing step is disabled for this call.
default: false
disable_preproc_static_crop:
anyOf:
- type: boolean
- type: 'null'
title: Disable Preproc Static Crop
description: If true, the static crop preprocessing step is disabled for this call.
default: false
prompt:
anyOf:
- type: string
- type: 'null'
title: Prompt
description: If set, use this prompt to guide the LMM
examples:
- caption
enable_thinking:
type: boolean
title: Enable Thinking
description: If true, enables thinking/reasoning mode for models that support it (e.g. Qwen3.5).
The model's reasoning will be included in the response.
default: false
max_new_tokens:
anyOf:
- type: integer
- type: 'null'
title: Max New Tokens
description: Maximum number of tokens to generate. If not set, the model's default will be used.
type: object
required:
- id
- model_id
- image
title: LMMInferenceRequest
HTTPValidationError:
properties:
detail:
items:
$ref: '#/components/schemas/ValidationError'
type: array
title: Detail
type: object
title: HTTPValidationError
DepthEstimationResponse:
properties:
normalized_depth:
anyOf:
- type: string
- items:
items:
type: number
type: array
type: array
title: Normalized Depth
description: 'Per-image normalized ordinal depth as a 2D array of floats between 0 and 1, where
1 is nearest and 0 is farthest. Values are not physical distances or directly comparable across
images or model families without calibration. The normalized depth map: a 2D array of floats
between 0 and 1 (`json` format, default) or a base64 grayscale PNG string (`png16`/`png8`),
per the request''s `depth_map_format`'
depth_map_format:
type: string
enum:
- json
- png16
- png8
title: Depth Map Format
description: The serialization format used for `normalized_depth`
default: json
image:
anyOf:
- type: string
- type: 'null'
title: Image
description: Base64 encoded visualization of the depth map if visualize_predictions is True
type: object
required:
- normalized_depth
title: DepthEstimationResponse
description: "Response for depth estimation inference.\n\nAttributes:\n normalized_depth (Union[str,\
\ List[List[float]]]): The per-image normalized ordinal\n depth map as a 2D array of floats\
\ between 0 and 1. Higher values\n indicate nearer predictions.\n serialized according\
\ to the request's `depth_map_format`: a 2D array of\n floats between 0 and 1 (`json`,\
\ the default) or a base64 grayscale PNG\n string (16-bit for `png16`, 8-bit for `png8`).\n\
\ depth_map_format (Literal[\"json\", \"png16\", \"png8\"]): The serialization\n format\
\ used for `normalized_depth`.\n image (Optional[str]): Base64 encoded visualization of the\
\ depth map if visualize_predictions is True.\n time (float): The processing time in seconds.\n\
\ visualization (Optional[str]): Base64 encoded visualization of the depth map if visualize_predictions\
\ is True."
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."
LMMInferenceResponse:
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 predictions including image preprocessing
image:
anyOf:
- items:
$ref: '#/components/schemas/InferenceResponseImage'
type: array
- $ref: '#/components/schemas/InferenceResponseImage'
title: Image
response:
anyOf:
- type: string
- additionalProperties: true
type: object
title: Response
description: Text/structured response generated by model
type: object
required:
- image
- response
title: LMMInferenceResponse
InferenceResponseImage:
properties:
width:
type: integer
title: Width
description: The original width of the image used in inference
height:
type: integer
title: Height
description: The original height of the image used in inference
type: object
required:
- width
- height
title: InferenceResponseImage
description: "Inference response image information.\n\nAttributes:\n width (int): The original\
\ width of the image used in inference.\n height (int): The original height of the image used\
\ in inference."
DepthEstimationRequest:
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
model_id:
anyOf:
- type: string
- type: 'null'
title: Model Id
model_type:
anyOf:
- type: string
- type: 'null'
title: Model Type
description: The type of the model, usually referring to what task the model performs
examples:
- object-detection
image:
anyOf:
- items:
$ref: '#/components/schemas/InferenceRequestImage'
type: array
- $ref: '#/components/schemas/InferenceRequestImage'
title: Image
depth_version_id:
anyOf:
- type: string
- type: 'null'
title: Depth Version Id
description: The version ID of the depth estimation model
default: small
examples:
- small
depth_map_format:
type: string
enum:
- json
- png16
- png8
title: Depth Map Format
description: 'Serialization format for `normalized_depth` in the response: `json` (default,
wire-compatible with older clients) returns the nested float list; `png16` returns a base64
16-bit grayscale PNG (quantization step 1/65535, typically >10x smaller payload - `inference_sdk`
decodes it back to a numpy array when requested via `depth_map_format=''png16''`); `png8`
returns a base64 8-bit grayscale PNG (256 depth levels, roughly another order of magnitude
smaller - fine for visualization/thresholding, lossy for geometric use).'
default: json
type: object
required:
- id
- image
title: DepthEstimationRequest
description: "Request for depth estimation.\n\nAttributes:\n image (Union[List[InferenceRequestImage],\
\ InferenceRequestImage]): Image(s) to be estimated.\n model_id (str): The model ID to use\
\ for depth estimation.\n depth_version_id (Optional[str]): The version ID of the depth estimation\
\ model.\n depth_map_format (Literal[\"json\", \"png16\", \"png8\"]): Serialization format\n\
\ for the normalized depth map in the response."
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
StubResponse:
properties:
visualization:
anyOf:
- type: string
- type: 'null'
title: Visualization
description: Base64 encoded string containing prediction visualization image data
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 predictions including image preprocessing
is_stub:
type: boolean
title: Is Stub
description: Field to mark prediction type as stub
model_id:
type: string
title: Model Id
description: Identifier of a model stub that was called
task_type:
type: string
title: Task Type
description: Task type of the project
type: object
required:
- is_stub
- model_id
- task_type
title: StubResponse