Update to Roboflow

{
  "description": "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.",
  "included_files": [
    {
      "relative_path": "api-key-management.md",
      "size_in_bytes": 13349
    },
    {
      "relative_path": "inference.md",
      "size_in_bytes": 6197
    },
    {
      "relative_path": "rest-api.md",
      "size_in_bytes": 6257
    }
  ],
  "name": "roboflow-api-reference",
  "skill_md_contents": "---\nname: roboflow-api-reference\ndescription: 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.\n---\n\n> **For agents:** This skill is authored in [`roboflow/computer-vision-skills`](https://github.com/roboflow/computer-vision-skills). If your client already has it loaded as a skill (for example from a Roboflow plugin), use that copy. The `roboflow://skills/<name>/...` MCP resources serve the same skills for clients that don't have them loaded.\n\n> **Tip:** If you're connected to the [Roboflow MCP server](https://mcp.roboflow.com), prefer its tools (`projects_*`, `versions_*`, `models_*`, `workflows_*`, `images_*`, …) 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.\n\n# Roboflow API Reference — Overview\n\n## API Hosts\n\n| Host | Base URL | Purpose |\n|------|----------|---------|\n| Platform API | `https://api.roboflow.com` | CRUD for projects, images, versions, training, upload |\n| Serverless Inference | `https://serverless.roboflow.com` | Model inference + Workflow execution |\n| Dedicated Deployment | `https://<name>.roboflow.cloud` | Private GPU inference (same API as serverless) |\n| Self-hosted Inference | `http://localhost:9001` | Local inference server via `inference` package |\n\nUse the `inference-sdk` Python package as the preferred client for all inference hosts. It handles auth, retries, and response parsing.\n\n## Authentication\n\n| Method | Where | Format |\n|--------|-------|--------|\n| Query parameter | All hosts | `?api_key=YOUR_KEY` |\n| Request body | Platform API + Workflow inference | `\"api_key\": \"YOUR_KEY\"` in JSON body |\n| Header | MCP server (`mcp.roboflow.com`) | `x-api-key: YOUR_KEY` (handled automatically by MCP) |\n\nAPI keys are workspace-scoped. Get yours from **Workspace Settings > API Keys** in the Roboflow dashboard (`app.roboflow.com/{workspace}/settings/api`). Personal API keys are at `/settings/account` → API Keys tab.\n\n## SDKs\n\n| SDK | Install | Primary Use |\n|-----|---------|-------------|\n| Python (`inference-sdk`) | `pip install inference-sdk` | Inference via `InferenceHTTPClient` |\n| Python (`roboflow`) | `pip install roboflow` | Upload, training, project management |\n| JavaScript (`roboflow.js`) | Browser script tag | Real-time on-device web inference |\n| iOS (Swift) | CocoaPods/SPM | On-device mobile inference |\n\n### Python inference-sdk Quick Start\n\n```python\nfrom inference_sdk import InferenceHTTPClient\n\nCLIENT = InferenceHTTPClient(\n    api_url=\"https://serverless.roboflow.com\",  # or dedicated URL, or localhost\n    api_key=\"YOUR_KEY\"\n)\nresult = CLIENT.infer(\"image.jpg\", model_id=\"your-project/1\")\n```\n\n### Python roboflow SDK Quick Start\n\n```python\nimport roboflow\n\nrf = roboflow.Roboflow(api_key=\"YOUR_KEY\")\nproject = rf.workspace(\"my-workspace\").project(\"my-project\")\n\n# Upload\nproject.upload(image_path=\"image.jpg\", split=\"train\")\n\n# Inference\nmodel = project.version(1).model\nresult = model.predict(\"image.jpg\", confidence=40).json()\n```\n\n## Host Selection Guide\n\n| Task | Host to Use |\n|------|-------------|\n| Run model inference | `serverless.roboflow.com` |\n| Run Workflows | `serverless.roboflow.com` |\n| Upload images | `api.roboflow.com` |\n| Manage projects/versions | `api.roboflow.com` |\n| Start training | `api.roboflow.com` |\n| High-throughput / SLA inference | Dedicated deployment URL |\n| Air-gapped / on-prem inference | Self-hosted `localhost:9001` |\n| Real-time video / webcam / RTSP | WebRTC via `inference_sdk.webrtc` against serverless or local — see `roboflow://skills/roboflow-inference/workflows` (\"Video Stream\" section). Not a plain HTTP call. |\n\n## Rate Limits\n\n- Serverless API: rate limits vary by plan\n- File upload max: 20 MB\n\n## Related Pages\n\n- `roboflow://skills/roboflow-api-reference/inference` — inference URL patterns, request/response formats\n- `roboflow://skills/roboflow-api-reference/rest-api` — platform REST API endpoints (CRUD, upload, training)\n- `roboflow://skills/roboflow-api-reference/api-key-management` — creating and managing API keys via REST, MCP tools, and Python CLI. **When creating a key, scope it to least privilege** if the workspace has Advanced API Keys; if not, tell the user scoped keys are an Enterprise feature.\n"
}