# IDEA-Research/DINO-X-API

DINO-X: The World's Top-Performing Vision Model for Open-World Object Detection and Understanding

Repository: https://github.com/IDEA-Research/DINO-X-API
Canonical: https://ross.abutalabs.com/products/dino-x-api
Homepage: https://arxiv.org/abs/2411.14347
Language: Python
License: Apache-2.0
License Family: permissive
Topics: open-set-object-detection, pose-estimation, region-caption, visual-prompt, open-set-object-segmentation
Last push: 2025-07-23T04:02:14+00:00

## Health v2 (maintenance only)
Score: 36/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 33, release rhythm 35, longevity 46
- inputs: {"age_days": 651, "days_push": 406, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1410, forks 63 (observed 2026-08-28T04:04:38.858661+00:00)

## What it is
DINO-X API is a Python client library and examples for accessing DINO-X, a hosted unified vision model for open-world object detection and understanding. It supports text, visual, and custom prompts to produce bounding boxes, segmentation masks, pose keypoints, and region captions.

## Use cases
- detect arbitrary objects in images without training
- segment objects with open-set prompts
- estimate human pose keypoints from photos
- generate captions for image regions
- count objects using visual prompts
- ground text phrases to image regions
- integrate object detection into AI agent workflows via MCP

## When to choose
- you need state-of-the-art zero-shot open-vocabulary detection
- you want one API for detection, segmentation, pose, and captioning
- you're okay calling a hosted cloud API rather than running models locally

## When to avoid
- you need fully offline or self-hosted inference
- you require a permissively self-hostable model rather than an API client
- you need guaranteed low-latency or no network dependency

## Facets
- artifact type: library
- maturity: active
- function: computer-vision, image-processing, sdk, machine-learning
- domain: computer-vision, artificial-intelligence, image-processing
- platform: python, cross-platform
- tags: open-set-object-detection, object-segmentation, pose-estimation, region-captioning, visual-prompting, phrase-grounding, api-client, zero-shot-detection

## Member repositories
- IDEA-Research/DINO-X-API (main) score 36

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:38.858661+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:38:26.698029+00:00, confidence not recorded.
  - readme: https://github.com/IDEA-Research/DINO-X-API (fetched 2026-08-28T04:04:38.858661+00:00, sha c71b9473ca43)
  - homepage: https://arxiv.org/abs/2411.14347 (fetched 2026-08-29T11:51:51.044282+00:00, sha a4b02567b375)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T11:51:51.053264+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T11:51:51.056464+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T11:51:51.058725+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T11:51:51.054898+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.