Vision
Providers using this tag (5)
Ranked by API Evangelist rating — Exemplar and Strong are expanded by default.
Exemplar 1 Complete, well-documented, and agent-ready
Thin 1 Limited public surface area
Minimal 3 Almost no public developer surface
APIs with this tag (24)
Ranked by the provider's API Evangelist rating — the Kin Score is scored per provider, not per API, so every API of a provider shares its band. How the rating works →
Exemplar 1 Complete, well-documented, and agent-ready
Strong 1 Solid coverage with minor gaps
Developing 5 Usable, with meaningful gaps to close
Gemini Pro Vision APIMultimodal understanding of text and images.Google ML Kit Android APIsOn-device machine learning APIs for text recognition, face detection, barcode scanning, image labeling, and...Google Cloud Vision APIThe Cloud Vision API allows developers to integrate vision detection features within applications, includin...Screenpipe Vision APIManage screen capture monitorsCognite Vision APIVision API is deprecated. See [Deprecated and retired features](https://docs.cognite.com/cdf/deprecated) fo...
Thin 13 Limited public surface area
Nomic Embedding APIHosted embedding endpoint backed by the Nomic Embed model family (nomic-embed-text-v1.5 and nomic-embed-vis...nomic-embed-vision-v1.5 (Open Weights)Open-weights vision embedding model that shares an embedding space with nomic-embed-text-v1.5 to support cr...OpenMind LLM APIUnified chat-completions endpoint that proxies multiple LLM providers (OpenAI, Anthropic via OpenRouter, Go...IO Intelligence APIOpenAI-compatible inference API for open-source AI models hosted on io.net's decentralized GPU network. Exp...Samsara Vision APIThe Vision API from Samsara — 6 operation(s) for vision.DeepInfra Platform APIOpenAI- and Anthropic-compatible inference API for 100+ open-source models. Surfaces include chat completio...Lingyiwanwu Platform APIOpenAI-compatible chat completions and vision endpoints for the Yi model family. Base URL https://api.lingy...Voyage AI Multimodal Embeddings APIMultimodal embeddings endpoint backed by voyage-multimodal-3 that accepts interleaved text and images in a ...DashScope (Alibaba Cloud Model Studio) APINative Alibaba Cloud Model Studio API serving the Qwen model family. Provides chat completions, multimodal ...Rows Vision APIExtract structured data from files using Rows AI Vision.Writer Vision APIThe Vision API from Writer — 1 operation(s) for vision.Volcano Engine Ark APIOpenAI-compatible chat, responses, embedding, batch, image (Seedream), video (Seedance), 3D, and TTS APIs s...Hyperbolic Serverless Inference APIOpenAI-compatible inference API for 25+ open-source models. Surfaces include text chat, vision, image gener...
Emerging 4 Early or largely undocumented
Liquid AI Platform APIHosted inference and customization API for the LFM family. Includes Liquid Playground and LEAP customizatio...Naver Cloud CLOVA OCR APICLOVA OCR detects and extracts text from images and documents — supporting general OCR, document-template O...JD Cloud OCR / AI APIsJD Cloud AI Platform exposes OCR (general, ID card, bank card, business license), speech (STT, TTS), comput...Adept Fuyu-8B ModelOpen-source 9B-parameter image-text-to-text multimodal model designed for digital agents - simple architect...
Companies reaching this through an API (23)
These companies publish an API, specification or operation carrying “Vision” but do not classify their business under it. Listed unranked and kept out of the count above, because one tagged operation is not a statement about what a company does.
01.AI
Adept
Android
ByteDance Doubao
Cognite
DeepInfra
Google
Google Gemini
Hyperbolic
io.net
JD.com (Jingdong)
Liquid AI
Naver
Nomic AI
NVIDIA NIM
OpenMind
Qwen
Rows
Samsara
Screenpipe
Viam
Voyage AI
Writer
Score breakdown
Frequency
42.2
log-scaled weighted occurrences
Breadth
0.1
spread across providers
Quality lift
29.0
mean composite of providers using it
Cohesion
9.1
strength of nearest seed neighbor
Related tags
Chat Completions 7 co-occurrences
OpenAI-Compatible 8 co-occurrences
Multi-Modal 7 co-occurrences
Speech 5 co-occurrences
Embeddings 7 co-occurrences
Image-Generation 6 co-occurrences
Inference 9 co-occurrences
LLM 14 co-occurrences
Where this tag comes from
Api tag24
Provider tag5
Openapi tag6
Openapi op tag18
Work with this as data
Every tag here is available over the APIs.io API and to AI agents over MCP.