Microsoft
microsoftMicrosoft's 4 models on ModelRunner span Image-to-Image and Image-to-Text, from $0.01 per image upward.
4 public models — every one runnable in a free playground, through the REST API and JavaScript SDK, or from an AI assistant over MCP.
Microsoft models & pricing
Florence-2 Large Dense Region Caption
microsoft
Detect the salient regions in a photo and get back an annotated image where each region is boxed and labeled with a short natural-language caption of what it contains.
Florence-2 Large OCR with Region
microsoft
Locate and read the text in a photo and get back an annotated image with each detected text region boxed and labeled with what it says.
Florence-2 Large Caption
microsoft
Generate a concise one-sentence caption describing any photo — no prompt needed.
Florence-2 Large Object Detection
microsoft
Detect and label every object in a photo and get back an annotated image with bounding boxes drawn on it.
What you can build with Microsoft models
- Caption every region of a photo with a short description of what it contains Florence-2 Large Dense Region Caption
- Get grounded region captions with the location of each described area Florence-2 Large Dense Region Caption
- Densely describe a scene beyond plain object-class labels Florence-2 Large Dense Region Caption
- Auto-annotate an image with labeled boxes and natural-language region tags Florence-2 Large Dense Region Caption
- Region-level image understanding for scene review or dataset labeling Florence-2 Large Dense Region Caption
- Read the text on a storefront sign or product label from a photo Florence-2 Large OCR with Region
- Extract text from a receipt or document scan and see where each line sits Florence-2 Large OCR with Region
- Detect and box text regions in an image for placement QA Florence-2 Large OCR with Region
Browse by capability
Call a Microsoft model in one request
Every endpoint shares the same lifecycle: submit to the queue, poll the status URL, fetch the result. Swap the endpoint to switch models — nothing else changes.
cURL
curl -X POST https://queue.modelrunner.run/microsoft/florence-2-large/dense-region-caption \
-H "Authorization: Key $MRUN_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "prompt": "..." }'
# → { "request_id": "...", "status_url": "...", "response_url": "..." }Use Microsoft models from Claude & Cursor
Connect the ModelRunner MCP server once and your AI assistant can run every Microsoft model on this page as a tool — authorized via OAuth, results returned as hosted URLs in the conversation.
Claude Code
claude mcp add --transport http modelrunner https://mcp.modelrunner.run/mcpFrequently asked questions
What Microsoft models can I run on ModelRunner?
The catalog has 4 public Microsoft models: Florence-2 Large Dense Region Caption, Florence-2 Large OCR with Region, Florence-2 Large Caption and 1 more. They cover image-to-image and image-to-text. Each one has its own page with a free playground, the full input schema, and copy-paste code.
How much do Microsoft models cost?
Pay-per-use, with no subscription: the 3 Microsoft models billed per image start at $0.01, and every page publishes its own rate — some are tiered, so a lower resolution or a shorter clip costs less per run. You buy credits and pay only for what you generate.
How do I call a Microsoft model from the API?
POST to https://queue.modelrunner.run/microsoft/florence-2-large/dense-region-caption with an Authorization: Key header and the input fields as the top-level JSON body (no wrapper object), then poll the returned status_url and fetch the result from response_url. The JavaScript SDK (@modelrunner/client) wraps that in a single subscribe() call, which is the one place an { input } object is used.
Can I run Microsoft models from Claude or Cursor?
Yes. Connect the ModelRunner MCP server (https://mcp.modelrunner.run/mcp) once and all 4 Microsoft models become tools your assistant can call with run_model — authorized over OAuth 2.1, so no API key goes into a config file. Results come back as hosted URLs in the conversation.
More on ModelRunner
Browse the full model catalog, compare live per-configuration rates on the pricing page, see curated sets on explore, or view every model creator.