> 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/workflows/blocks/blocks/run-a-model.md). # Run a Model Run fine-tuned models trained on Roboflow, foundation models, and third-party VLMs and LLMs directly in a Workflow. | Block | Description | | ---------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------- | | [Anthropic Claude](/workflows/blocks/blocks/run-a-model/anthropic-claude.md) | Run Anthropic Claude model with vision capabilities | | [Barcode Detection](/workflows/blocks/blocks/run-a-model/barcode-detection.md) | Detect and read barcodes in an image | | [Clip Comparison](/workflows/blocks/blocks/run-a-model/clip-comparison.md) | Compare CLIP image and text embeddings | | [CLIP Embedding Model](/workflows/blocks/blocks/run-a-model/clip-embedding-model.md) | Generate an embedding of an image or string | | [CogVLM](/workflows/blocks/blocks/run-a-model/cog-vlm.md) | DEPRECATED! Run a self-hosted vision language model | | [Cosmos 3](/workflows/blocks/blocks/run-a-model/cosmos3.md) | Reason about physical scenes with NVIDIA Cosmos 3 | | [Depth Estimation](/workflows/blocks/blocks/run-a-model/depth-estimation.md) | Estimate relative scene depth in an image | | [EasyOCR](/workflows/blocks/blocks/run-a-model/easy-ocr.md) | Extract text from an image using EasyOCR optical character recognition | | [Florence-2 Model](/workflows/blocks/blocks/run-a-model/florence2-model.md) | Run Florence-2 on an image | | [GLM-OCR](/workflows/blocks/blocks/run-a-model/glmocr.md) | Run GLM-OCR on an image to recognize text | | [Google Gemini](/workflows/blocks/blocks/run-a-model/google-gemini.md) | Run Google's Gemini model with vision capabilities | | [Google Gemma](/workflows/blocks/blocks/run-a-model/google-gemma.md) | Run Google's Gemma model with vision capabilities via OpenRouter | | [Google Vision OCR](/workflows/blocks/blocks/run-a-model/google-vision-ocr.md) | Detect text in images using Google Vision API | | [Instance Segmentation Model](/workflows/blocks/blocks/run-a-model/instance-segmentation-model.md) | Predict the shape, size, and location of objects | | [Keypoint Detection Model](/workflows/blocks/blocks/run-a-model/keypoint-detection-model.md) | Predict skeletons on objects | | [Llama 3.2 Vision](/workflows/blocks/blocks/run-a-model/llama3-2-vision.md) | Run Llama 3.2 Vision via OpenRouter | | [Moondream2](/workflows/blocks/blocks/run-a-model/moondream2.md) | Run Moondream2 on an image | | [MoonshotAI Kimi](/workflows/blocks/blocks/run-a-model/moonshot-ai-kimi.md) | Run Moonshot AI Kimi vision-language models via OpenRouter | | [Multi-Label Classification Model](/workflows/blocks/blocks/run-a-model/multi-label-classification-model.md) | Apply multiple tags to an image | | [Object Detection Model](/workflows/blocks/blocks/run-a-model/object-detection-model.md) | Predict the location of objects with bounding boxes | | [OCR Model](/workflows/blocks/blocks/run-a-model/ocr-model.md) | Extract text from an image using DocTR optical character recognition | | [OpenAI](/workflows/blocks/blocks/run-a-model/open-ai.md) | Run OpenAI's GPT models with vision capabilities | | [OpenAI-Compatible LLM](/workflows/blocks/blocks/run-a-model/open-ai-compatible-llm.md) | Send prompts to any OpenAI-compatible API endpoint | | [OpenRouter](/workflows/blocks/blocks/run-a-model/open-router.md) | Run any OpenRouter model by pasting its model slug | | [Perception Encoder Embedding Model](/workflows/blocks/blocks/run-a-model/perception-encoder-embedding-model.md) | Generate an embedding of an image or string | | [PP-OCR](/workflows/blocks/blocks/run-a-model/ppocr.md) | Extract text from an image using PP-OCR (PaddleOCR) optical character recognition | | [QR Code Detection](/workflows/blocks/blocks/run-a-model/qr-code-detection.md) | Detect and read QR codes in an image | | [Qwen-VL](/workflows/blocks/blocks/run-a-model/qwen-vl.md) | Run any Qwen vision model - natively or via OpenRouter | | [Qwen3.5](/workflows/blocks/blocks/run-a-model/qwen3-5.md) | Run Qwen3.5 on an image | | [Roboflow Visual Search Classifier](/workflows/blocks/blocks/run-a-model/roboflow-visual-search-classifier.md) | Classify an image by finding the most visually similar annotated image | | [SAM 3](/workflows/blocks/blocks/run-a-model/sam3.md) | Run SAM3 with text prompts for zero-shot segmentation | | [SAM 3 Interactive](/workflows/blocks/blocks/run-a-model/sam3-interactive.md) | Segment a specific object with SAM3 using point and/or bounding box prompts | | [Seg Preview](/workflows/blocks/blocks/run-a-model/seg-preview.md) | Seg Preview | | [Segment Anything 2 Model](/workflows/blocks/blocks/run-a-model/segment-anything2-model.md) | Convert bounding boxes to polygons, or run SAM2 on an entire image to generate a mask | | [Semantic Segmentation Model](/workflows/blocks/blocks/run-a-model/semantic-segmentation-model.md) | Assign a class label to every pixel in the image | | [Single-Label Classification Model](/workflows/blocks/blocks/run-a-model/single-label-classification-model.md) | Apply a single tag to an image | | [SmolVLM2](/workflows/blocks/blocks/run-a-model/smol-vlm2.md) | Run SmolVLM2 on an image | | [Stability AI Image Generation](/workflows/blocks/blocks/run-a-model/stability-ai-image-generation.md) | generate new images from text, or create variations of existing images | | [Stability AI Inpainting](/workflows/blocks/blocks/run-a-model/stability-ai-inpainting.md) | Use segmentation masks to inpaint objects within an image | | [Stability AI Outpainting](/workflows/blocks/blocks/run-a-model/stability-ai-outpainting.md) | Use object detection bounding box to crop the image and to outpaint within given directions | | [YOLO-World Model](/workflows/blocks/blocks/run-a-model/yolo-world-model.md) | Run a zero-shot object detection model | | [Gaze Detection (Deprecated)](/workflows/blocks/blocks/run-a-model/gaze-detection.md) | Detect faces and estimate gaze direction (deprecated) | | [Google Gemma API (Deprecated)](/workflows/blocks/blocks/run-a-model/google-gemma-api.md) | Run Google's Gemma model with vision capabilities via OpenRouter | | [LMM (Deprecated)](/workflows/blocks/blocks/run-a-model/lmm.md) | Run a large multimodal model such as ChatGPT-4v | | [LMM For Classification (Deprecated)](/workflows/blocks/blocks/run-a-model/lmm-for-classification.md) | Run a large multimodal model such as ChatGPT-4v for classification | | [Qwen 3.5 API (Deprecated)](/workflows/blocks/blocks/run-a-model/qwen3-5-api.md) | Run Qwen 3.5 vision-language models via OpenRouter | | [Qwen 3.6 API (Deprecated)](/workflows/blocks/blocks/run-a-model/qwen3-6-api.md) | Run Qwen 3.6 vision-language models via OpenRouter | | [Qwen2.5-VL (Deprecated)](/workflows/blocks/blocks/run-a-model/qwen2-5-vl.md) | Run Qwen2.5-VL on an image | | [Qwen3-VL (Deprecated)](/workflows/blocks/blocks/run-a-model/qwen3-vl.md) | Run Qwen3-VL on an image | | [Qwen3.5-VL (Deprecated)](/workflows/blocks/blocks/run-a-model/qwen3-5-vl.md) | Run Qwen3.5-VL on an image |