Inference
Was this helpful?
Was this helpful?
roboflow package) – Deprecated⚠️ Deprecated
Running inference using the roboflow Python SDK was deprecated. This method is no longer actively maintained, and we recommend migrating to the new Inference SDK and Serverless Hosted APIs for all current and future projects.
Roboflow has introduced more powerful and flexible inference options, including:
✅ Native support for all models
✅ Access to foundation models (YOLO-World, CLIP, OCR, SAM, Florence2, etc.)
✅ Improved performance and latency using GPU-accelerated infrastructure
✅ A simplified and unified inference endpoint
Use this package for running inference across a wide range of model types, with local and hosted backends supported out-of-the-box. It supports modern use cases like versionless models and foundation models.
👉 Explore:
A GPU-accelerated cloud API with unified endpoints for all tasks. Offers lower latency for inference requests and support for powerful models such as Florence2 and SAM2.
If you're using older models or workflows, the original serverless API is still available. This includes individual endpoints for object detection, classification, segmentation, and more.
While the roboflow Python SDK remains useful for other interactions (e.g., uploading data, managing datasets), its inference capabilities have been replaced by more efficient and modern solutions:
It does not support all models (models uploaded without dataset version, Roboflow Instant)
It offers limited access to newer model types
It lacks performance improvements found in GPU-accelerated APIs
It is not compatible with newer deployment workflows
If you're using the legacy SDK for inference and want help transitioning to the new tools, check out our guides at:
🔗 Learn more:
🔗 Learn more:
🔧
📘