Loading...
Loading...
Protocol-level facts for Roboflow REST and Inference APIs — URL patterns, auth, parameters, error codes, and SDK quick-start. For deployment strategy and Workflow execution patterns, see roboflow-inference.
npx skill4agent add roboflow/computer-vision-skills roboflow-api-referenceFor agents: This skill is authored in. If your client already has it loaded as a skill (for example from a Roboflow plugin), use that copy. Theroboflow/computer-vision-skillsMCP resources serve the same skills for clients that don't have them loaded.skill://roboflow/<name>/SKILL.md
Tip: If you're connected to the Roboflow MCP server, prefer its tools (,projects_*,versions_*,models_*,workflows_*, …) over raw REST calls — they handle auth, pagination, and typed responses for you. The REST patterns below stay relevant if you're not using MCP.images_*
| Host | Base URL | Purpose |
|---|---|---|
| Platform API | | CRUD for projects, images, versions, training, upload |
| Serverless Inference | | Model inference + Workflow execution |
| Dedicated Deployment | | Private GPU inference (same API as serverless) |
| Self-hosted Inference | | Local inference server via |
inference-sdk| Method | Where | Format |
|---|---|---|
| Query parameter | All hosts | |
| Request body | Platform API + Workflow inference | |
| Header | MCP server ( | |
app.roboflow.com/{workspace}/settings/api/settings/account| SDK | Install | Primary Use |
|---|---|---|
Python ( | | Inference via |
Python ( | | Upload, training, project management |
JavaScript ( | Browser script tag | Real-time on-device web inference |
| iOS (Swift) | CocoaPods/SPM | On-device mobile inference |
from inference_sdk import InferenceHTTPClient
CLIENT = InferenceHTTPClient(
api_url="https://serverless.roboflow.com", # or dedicated URL, or localhost
api_key="YOUR_KEY"
)
result = CLIENT.infer("image.jpg", model_id="your-project/1")import roboflow
rf = roboflow.Roboflow(api_key="YOUR_KEY")
project = rf.workspace("my-workspace").project("my-project")
# Upload
project.upload(image_path="image.jpg", split="train")
# Inference
model = project.version(1).model
result = model.predict("image.jpg", confidence=40).json()| Task | Host to Use |
|---|---|
| Run model inference | |
| Run Workflows | |
| Upload images | |
| Manage projects/versions | |
| Start training | |
| High-throughput / SLA inference | Dedicated deployment URL |
| Air-gapped / on-prem inference | Self-hosted |
| Real-time video / webcam / RTSP | WebRTC via |
skill://roboflow/roboflow-api-reference/inference.mdskill://roboflow/roboflow-api-reference/rest-api.mdskill://roboflow/roboflow-api-reference/api-key-management.md