Rate Limiter

Class: RateLimiterBlockV1

Source: inference.core.workflows.core_steps.flow_control.rate_limiter.v1.RateLimiterBlockV1

The Rate Limiter block controls the execution frequency of a branch within a Workflow by enforcing a cooldown period. It ensures that the connected steps do not run more frequently than a specified interval, helping to manage resource usage and prevent over-execution.

Block usage

Rate Limiter is useful when you have two blocks that are directly connected, as shown below:

--- input_a --> ┌───────────┐ ┌───────────┐ --- input_b --> │ step_1 │ --> output_a --> │ step_2 │ --- input_c --> └───────────┘ └───────────┘

If you want to throttle the Step 2 execution rate - you should apply rate limiter in between:

• keep the existing blocks configuration as is (do not change connections)

• set depends_on reference of Rate Limiter into output_a

• set next_steps reference to be a list referring to [$steps.step_2]

• adjust cooldown_seconds to specify what is the number of seconds that must be awaited before next time when step_2 is fired

Cooldown limitations

Current implementation of cooldown is limited to video processing - using this block in context of a Workflow that is run behind HTTP service (Roboflow Hosted API, Dedicated Deployment or self-hosted inference server) will have no effect for processing HTTP requests.

Type identifier

Use the following identifier in step "type" field: roboflow_core/rate_limiter@v1to add the block as as step in your workflow.

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
cooldown_seconds	float	The minimum number of seconds between allowed executions..	❌

The Refs column marks possibility to parametrise the property with dynamic values available in workflow runtime. See Bindings for more info.

Available Connections

Compatible Blocks

Check what blocks you can connect to Rate Limiter in version v1.

• inputs: Expression, Time in Zone, OpenAI, Line Counter, Line Counter Visualization, Cosine Similarity, SIFT Comparison, Dimension Collapse, LMM, Qwen2.5-VL, Data Aggregator, Multi-Label Classification Model, Model Comparison Visualization, Line Counter, OCR Model, Stability AI Image Generation, Image Slicer, QR Code Detection, Distance Measurement, Detection Offset, VLM as Detector, Keypoint Detection Model, Keypoint Detection Model, Delta Filter, YOLO-World Model, Slack Notification, Label Visualization, Byte Tracker, Image Threshold, Local File Sink, Cache Set, Polygon Visualization, Byte Tracker, Identify Outliers, Dominant Color, VLM as Classifier, Buffer, Pixelate Visualization, SIFT, Environment Secrets Store, Instance Segmentation Model, Detections Consensus, Clip Comparison, Rate Limiter, Bounding Rectangle, Keypoint Visualization, Polygon Zone Visualization, Template Matching, Stitch OCR Detections, Detections Stabilizer, Stability AI Inpainting, OpenAI, QR Code Generator, Stability AI Outpainting, Detections Stitch, Multi-Label Classification Model, Time in Zone, SIFT Comparison, Roboflow Dataset Upload, Blur Visualization, Velocity, Identify Changes, Color Visualization, Instance Segmentation Model, SmolVLM2, Halo Visualization, Mask Visualization, Time in Zone, Property Definition, Path Deviation, Background Color Visualization, Perception Encoder Embedding Model, VLM as Classifier, Byte Tracker, Detections Filter, Trace Visualization, Google Vision OCR, Dot Visualization, Classification Label Visualization, Model Monitoring Inference Aggregator, Stitch Images, Anthropic Claude, Email Notification, Pixel Color Count, Absolute Static Crop, Object Detection Model, Image Contours, Dynamic Crop, CSV Formatter, LMM For Classification, JSON Parser, Gaze Detection, CogVLM, Object Detection Model, Image Preprocessing, Circle Visualization, CLIP Embedding Model, Florence-2 Model, PTZ Tracking (ONVIF).md), Relative Static Crop, Image Slicer, Moondream2, Roboflow Dataset Upload, Cache Get, Reference Path Visualization, Depth Estimation, Dynamic Zone, Bounding Box Visualization, Icon Visualization, Roboflow Custom Metadata, Detections Transformation, Florence-2 Model, Path Deviation, Ellipse Visualization, Grid Visualization, Camera Focus, Single-Label Classification Model, Image Blur, Detections Classes Replacement, First Non Empty Or Default, Continue If, Size Measurement, Crop Visualization, Corner Visualization, Triangle Visualization, Twilio SMS Notification, Clip Comparison, Webhook Sink, OpenAI, Overlap Filter, Camera Calibration, Image Convert Grayscale, Single-Label Classification Model, Llama 3.2 Vision, Segment Anything 2 Model, VLM as Detector, Barcode Detection, Google Gemini, Perspective Correction, Detections Merge
• outputs: None

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Rate Limiter in version v1 has.

Bindings

• input

  • depends_on (*): Step immediately preceding this block..
  • next_steps (step): Steps to execute if allowed by the rate limit..
  • video_reference_image (image): Reference to a video frame to use for timestamp generation (if running faster than realtime on recorded video)..

• output

Example JSON definition of step Rate Limiter in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/rate_limiter@v1",
    "cooldown_seconds": 1.0,
    "depends_on": "$steps.model",
    "next_steps": [
        "$steps.upload"
    ],
    "video_reference_image": "$inputs.image"
}