Roboflow Docs
DashboardResourcesProducts
  • Product Documentation
  • Developer Reference
  • Changelog
  • Roboflow Documentation
  • Quickstart
  • Workspaces
    • Workspaces, Projects, and Models
    • Create a Workspace
    • Rename a Workspace
    • Delete a Workspace
  • Team Members
    • Invite a Team Member
    • Role-Based Access Control (RBAC)
    • Change a Team Member Role
    • Remove a Team Member
  • Single Sign On (SSO)
  • Workflows
    • What is Workflows?
    • Create a Workflow
    • Build a Workflow
    • Test a Workflow
    • Deploy a Workflow
    • Workflow Examples
      • Multimodal Model Workflow
    • Share a Workflow
    • Workflows AI Assistant
  • Enterprise Integrations
  • Workflow Blocks
    • Run a Model
      • Object Detection Model
      • Single-Label Classification Model
    • Visualize Predictions
      • Bounding Box Visualization
      • Label Visualization
      • Circle Visualization
      • Background Color Visualization
      • Classification Label Visualization
      • Crop Visualization
  • Dataset Management
    • Create a Project
    • Upload Images, Videos, and Annotations
      • Import Data from Cloud Providers
        • AWS S3 Bucket
        • Azure Blob Storage
        • Google Cloud Storage
      • Import from Roboflow Universe
    • Manage Datasets
      • Dataset Batches
      • Search a Dataset
      • Set Dataset Classes
      • Add Tags to Images
      • Create an Annotation Attribute
      • Download an Image
      • Delete an Image
    • Dataset Versions
      • Create a Dataset Version
      • Preprocess Images
      • Image Augmentation
        • Add Augmentations to Images
      • Delete a Version
    • Dataset Analytics
    • Merge Projects
    • Rename a Project
    • Delete a Project
    • Project Folders
    • Make a Project Public
    • Download a Dataset
  • Annotate
    • Introduction to Roboflow Annotate
    • Annotate an Image
      • Keyboard Shortcuts
      • Comment on an Image
      • Annotation History
      • Similarity Search
    • AI Labeling
      • Label Assist
      • Enhanced Smart Polygon with SAM
        • Smart Polygon (Legacy)
      • Box Prompting
      • Auto Label
    • Set Keypoint Skeletons
    • Annotate Keypoints
    • Annotate Multimodal Data
    • Collaborate on Labeling
    • Annotation Insights
  • Roboflow Labeling Services
  • Train
    • Train a Model
      • Train from a Universe Checkpoint
      • Train from Azure Vision
      • Train from Google Cloud
    • Roboflow Instant
    • Cancel a Training Job
    • Stop Training Early
    • View Training Results
    • View Trained Models
    • Evaluate Trained Models
  • Deploy
    • Deploy a Model or Workflow
    • Supported Models
    • Managed Deployments
    • Serverless Hosted API V2
      • Use in a Workflow
      • Use with the REST API
      • Run an Instant Model
    • Serverless Hosted API
      • Object Detection
      • Classification
      • Instance Segmentation
        • Semantic Segmentation
      • Keypoint Detection
      • Foundation Models
        • CLIP
        • OCR
        • YOLO-World
      • Video Inference
        • Use a Fine-Tuned Model
        • Use CLIP
        • Use Gaze Detection
        • API Reference
        • Video Inference JSON Output Format
      • Pre-Trained Model APIs
        • Blur People API
        • OCR API
        • Logistics API
        • Image Tagging API
        • People Detection API
        • Fish Detection API
        • Bird Detection API
        • PPE Detection API
        • Barcode Detection API
        • License Plate Detection API
        • Ceramic Defect Detection API
        • Metal Defect Detection API
    • Dedicated Deployments
      • Create a Dedicated Deployment
      • Make Requests to a Dedicated Deployment
      • Manage Dedicated Deployments with an API
    • Batch Processing
    • SDKs
      • Python inference-sdk
      • Web Browser
        • inferencejs Reference
        • inferencejs Requirements
      • Lens Studio
        • Changelog - Lens Studio
      • Luxonis OAK
    • Upload Custom Model Weights
    • Download Model Weights
    • Enterprise Deployment
      • License Server
      • Offline Mode
      • Kubernetes
      • Docker Compose
    • Model Monitoring
      • Alerting
  • Universe
    • What is Roboflow Universe?
    • Find a Dataset on Universe
    • Explore Images in a Universe Dataset
    • Fork a Universe Dataset
    • Find a Model on Universe
    • Download a Universe Dataset
  • Set a Project Description
  • View Project Analytics
  • Support
    • Share a Workspace with Support
    • Delete Your Roboflow Account
    • Apply for Academic Credits
  • Billing
    • Premium Trial
    • Credits
      • View Credit Usage
      • Enable or Disable Flex Billing
      • Purchase Prepaid Credits
    • Plans
      • Purchase a Plan
      • Cancel a Plan
      • Update Billing Details
      • Update Payment Method
      • View Invoices
Powered by GitBook
On this page

Was this helpful?

  1. Deploy

Serverless Hosted API V2

Run Workflows and Model Inference on GPU-accelerated infrastructure in the Roboflow cloud.

PreviousManaged DeploymentsNextUse in a Workflow

Last updated 12 days ago

Was this helpful?

Models deployed to Roboflow have a REST API available through which you can run inference on images. This deployment method is ideal for environments where you have a persistent internet connection on your deployment device.

The API associated with your project scales with you: as you grow your project and have greater inference requirements, your API will grow.

Serverless Hosted API V2 is our newest API offering. It is faster than V1 and works with models that require a GPU such as Florence-2 and SAM-2.

Use the API in a Workflow

Use with the REST API

Benchmarks

The end-to-end latency of requests sent to the Serverless Hosted API V2 depends on several factors:

  1. Model architecture, which has a bearing on the execution time

  2. Size and resolution of the images that impact upload time and model inference time during execution

  3. Network latency and bandwidth, which affects request upload time and response download time.

  4. Service subscription and usage by other users at any specific time which could result in queueing latency

Model
V2 (E2E)
V2 (Exec)
V1 (E2E)
V1 (Exec)

yolov8x-640

401 ms

29 ms

4084 ms

821 ms

yolov8m-640

757 ms

21 ms

572 ms

265 ms

yolov8n-640

384 ms

17 ms

312 ms

63 ms

yolov8x-1280

483 ms

97 ms

6431 ms

3032 ms

yolov8m-1280

416 ms

52 ms

1841 ms

1006 ms

yolov8n-1280

428 ms

35 ms

464 ms

157 ms

We encourage users to run their own benchmarks for their model inferences and workflows to get real metrics on their specific usecases.

We show some representative benchmarks performed on the Serverless Hosted API V2 and the Hosted API V1 in the table below. The results for Serverless Hosted API V2 and Hosted Inference (V1) show the end-to-end latency (E2E) as well as the execution time (Exec). These numbers are for information only, we encourage users to perform their own benchmarks using or their own custom benchmarks.

our inference benchmark tools