Deploy computer vision models at scale
Serve detection, segmentation, and classification models behind managed API endpoints. Send images as URLs, base64, or file payloads, and Beam scales the GPUs underneath.
Serve any computer vision model
Beam handles image ingestion, warm weights, burst scaling, and batch backfills.
Send images any way
Endpoints accept URLs, base64 payloads, or file uploads, so you can use whichever fits your client.
Explore docsWarm weights per container
on_start loads the model once per container so requests skip straight to inference.
Explore docsScale with request volume
Autoscaling adds containers as traffic grows and drops to zero when it stops, so you don't have to plan capacity.
Explore docsBatch over image archives
Backfill millions of images by fanning the same function out across containers with .map().
Explore docsCPU or GPU per model
Run small detectors on fractional CPUs and reserve GPUs for heavy segmentation. Both are priced per second.
Explore docsPer-second billing
Pay for compute while frames are being processed and never for idle capacity between bursts.
Explore docsWe would not have been able to get our API running and win our first enterprise contract without Beam.
Daniel Heinen, Founder & CEO, Graylark
inference requests in one month
production uptime
of requests per minute at peak
Deploy a vision model in three steps
Wrap your model
Load YOLO, DETR, SAM, or a custom classifier in on_start and declare the hardware inline.
Deploy the endpoint
beam deploy returns an authenticated HTTPS URL with autoscaling already wired up.
POST images, get predictions
Send a URL or file payload and get structured detections back as JSON.
$ beam deploy app.py:detect
=> Deployed 🎉
=> https://object-detection-abc123.app.beam.cloud
$ curl -X POST https://object-detection-abc123.app.beam.cloud \
-H 'Authorization: Bearer YOUR_TOKEN' \
-d '{"image_url": "https://example.com/warehouse.jpg"}'
{"detections": [
{"label": "forklift", "confidence": 0.94, "box": [102, 44, 380, 291]}
]}Frequently asked questions
How do I send images to the endpoint?
Three ways: pass a URL for the container to fetch, base64-encode the image into the JSON body, or send the file directly using Beam's file payload support.
Which vision models work?
Anything that runs in Python, including YOLO and ultralytics models, DETR, SAM, CLIP, and vision-language models via transformers.
Can I process video?
Yes. For long videos, deploy the job as a task queue: split into frames or segments inside the container, process on GPU, and get a webhook when results are ready.
What about latency-sensitive applications?
Use keep_warm_seconds to hold containers hot, and pick a GPU close to your model's size. Cold boots take seconds and you're never billed for them.
Do small models need a GPU at all?
Often not. Beam lets you request fractional CPUs for lightweight models and attach a GPU only where it pays for itself.
How do I run several vision models side by side?
Deploy each model as its own endpoint with its own dependencies, hardware, and scaling settings. Beam scales them independently. Deployments are versioned, so rolling back a misbehaving model takes one click. Raven manages multiple production vision models this way.
Related use cases
Run Stable Diffusion and Flux as an API
Host SDXL, Flux, and custom checkpoints behind an autoscaling API.
Batch ProcessingRun OCR and document extraction at scale
Private OCR and extraction pipelines, one container per document.
Task QueuesFan out batch jobs across thousands of containers
Fan out batch inference and ETL across thousands of containers.
Give your agents their own machines
Sign up, install the CLI, and launch a sandbox, VM, or GPU from your terminal or your coding agent.