> For the complete documentation index, see [llms.txt](https://docs.roboflow.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.roboflow.com/reference/inference.md).

# Inference

- [Choosing the Right Tool](https://docs.roboflow.com/reference/inference/choosing-the-right-tool.md): When to use the Inference server, the inference package, the Inference SDK, and the Inference CLI.
- [Inference Server OpenAPI](https://docs.roboflow.com/reference/inference/inference-server-openapi.md): Browse and test the HTTP API for a self-hosted Roboflow Inference Server.
- [Inference Python Package](https://docs.roboflow.com/reference/inference/inference-python.md): The inference Python package: load models, run inference in your own process, execute Workflows, and stream video.
- [Inference Benchmarks](https://docs.roboflow.com/reference/inference/inference-python/benchmarks.md): Measured throughput for RF-DETR, YOLOv8, ResNet, and ViT models on NVIDIA L4 and Jetson Orin NX, comparing ONNX and TensorRT.
- [Inference Pipeline](https://docs.roboflow.com/reference/inference/inference-python/inference-pipeline.md): Run models on video streams with InferencePipeline: video sources, custom inference logic, Workflows, and sinks.
- [Native Python API](https://docs.roboflow.com/reference/inference/inference-python/native-python-api.md): Load a model with get\_model, run inference on images in your own Python process, and visualize the results with supervision.
- [Model Weights Download](https://docs.roboflow.com/reference/inference/inference-python/offline-weights.md): How the inference package downloads and caches model weights, how to configure a persistent cache directory, and how to pre-download weights.
- [Inference SDK](https://docs.roboflow.com/reference/inference/inference-sdk.md): HTTP client for the Roboflow Inference Server, with local, hosted, async, and batch inference from Python.
- [Configuration](https://docs.roboflow.com/reference/inference/inference-sdk/configuration.md): Configure InferenceHTTPClient defaults, per-task model parameters, and Workflows execution options with InferenceConfiguration.
- [Core Models](https://docs.roboflow.com/reference/inference/inference-sdk/core-models.md): Call CLIP and DocTR foundation models through the inference-sdk HTTP client, with sync and async methods.
- [Model Management](https://docs.roboflow.com/reference/inference/inference-sdk/model-management.md): Pre-load, inspect, and unload models on an Inference Server with the inference-sdk client.
- [WebRTC Streaming](https://docs.roboflow.com/reference/inference/inference-sdk/webrtc.md): Stream video to an Inference server over WebRTC and receive live predictions, using a model ID or a Workflow, from webcams, RTSP cameras, video files, or manually sent frames.
- [Workflows](https://docs.roboflow.com/reference/inference/inference-sdk/workflows.md): Run a Roboflow Workflow through the inference-sdk client, by workflow ID or by inline specification.
- [Inference CLI](https://docs.roboflow.com/reference/inference/inference-cli.md): Command-line tool for running the Inference Server, processing data with Workflows, benchmarking, making predictions, and deploying to the cloud.
- [Benchmark Inference](https://docs.roboflow.com/reference/inference/inference-cli/benchmark.md): Measure throughput and latency of the Inference Server or the inference Python package with inference benchmark.
- [Deploy to Cloud](https://docs.roboflow.com/reference/inference/inference-cli/cloud.md): Deploy Roboflow Inference containers to CPU or GPU virtual machines on AWS and GCP with inference cloud.
- [Make Predictions](https://docs.roboflow.com/reference/inference/inference-cli/infer.md): Run predictions on images, image URLs, directories, and video files from the command line with inference infer.
- [Control the Inference Server](https://docs.roboflow.com/reference/inference/inference-cli/server.md): Start, configure, inspect, and stop a local Roboflow Inference Server with the inference server command.
- [Run Workflows](https://docs.roboflow.com/reference/inference/inference-cli/workflows.md): Process single images, directories of images, and video files with a Roboflow Workflow from the command line.