API Reference | Roboflow Docs

Video Inference API methods for uploading video, scheduling jobs, and retrieving results.

The Video Inference API can be used through the Roboflow Python SDK and through a REST API.

Base URL

The API uses the following URL:

https://api.roboflow.com

API Methods

We highly recommend accessing video inference via the roboflow Pip package.

The raw Video Inference API at https://api.roboflow.com has three methods:

METHOD DESCRIPTION

METHOD	DESCRIPTION
`POST` `/video_upload_signed_url/?api_key={{WORKSPACE_API_KEY}}`	This endpoint returns a signed URL where a user can upload video. The endpoint accepts a JSON input with the filename, like so `{`

POST /video_upload_signed_url/?api_key={{WORKSPACE_API_KEY}}

This endpoint returns a signed URL where a user can upload video.

The endpoint accepts a JSON input with the filename, like so

"file_name": "my_video_file.mp4" } </code></pre>A signed URL is returned <pre class="language-json"><code class="lang-json">{ "signed_url": "URL" } </code></pre> You can then use your favorite upload program (like cURL) to PUT your video file to the signed URL.<pre class="language-bash"><code class="lang-bash">curl -X PUT "my_signed_url"
-H "Content-Type: application/octet-stream"
--data-binary "@your_video.mp4" </code></pre></td></tr><tr><td><code>POST</code> <code>/videoinfer/?api_key={{WORKSPACE_API_KEY}}</code></td><td>The endpoint accepts a json input to schedule a video inference job for processing. Note that the INPUT_URL can be any publicly available URL, you don't need to first create a signed URL and then upload a video to Roboflow.An example showing the body of the request is shown below:<pre><code>{ "input_url": "{{INPUT_URL}}", "infer_fps": 5, "models": [ { "model_id": "rock-paper-scissors-presentation", "model_version": "4", "inference_type": "object-detection", "inference_params": {"confidence": 0.4} } ] } </code></pre>Please be noted that <code>models[*].inference_params</code> is optional.The response is a JSON string, like so <pre class="language-json"><code class="lang-json">{ "job_id": "fec28362-f7d9-4cc0-a805-5e94495d063d", "message": "This endpoint will create videojob" } </code></pre> You can specify multiple models in the <code>models</code> array. The <code>infer_fps</code> field should be at least set to <code>1</code> and its value should not exceed the video frame-rate. For most use-cases, the video frame rate is an exact multiple of the <code>infer_fps</code> . </td></tr><tr><td><code>GET</code> <code>/videoinfer/?api_key={{WORKSPACE_API_KEY}}&job_id={{JOB_ID}}</code></td><td>This endpoint returns the current status of the job. This endpoint is rate-limited, please don't poll this endpoint more than once per minute. When the job is successful, the returned JSON's <code>status</code> key is set to 0, and the <code>output_signed_url</code> key contains the download link for the video inference results. If the <code>status</code> is set to 1, it indicates that the job processing is not complete. Any higher values indicates job failure.</td></tr><tr><td></td><td></td></tr></tbody></table>

Once you have downloaded the JSON file stored from the output_signed_url location, you can parse it to obtain inference information. The format of the json file is described here.