Hugging Face
The AI community building the future with open-source machine learning models, datasets, and applications.
Reference-quality API operations across every facet — a rich contract, published governance, transparent operations, and machine-readable commercial terms.
API Evangelist profiles Hugging Face the way a machine reads it — 436 machine-readable artifacts across 21 APIs, pulled from the provider's own public surface and indexed so a developer, an analyst, or an AI agent can evaluate it against every other provider on the network.
Every provider in the network is reduced to the same set of machine-readable artifacts — OpenAPI contracts, event specifications, GraphQL schemas, runnable collections, pricing and rate-limit signals, security posture, OAuth scopes, and the agent surfaces (MCP servers and skills) that let software drive the API on its own. We profile them because the interface is the part of a company you can actually inspect: it is a truer signal of what a provider does than any marketing page. From those artifacts we compute the Kin Score — Hugging Face scores 71.7/100 (exemplar), with a separate agent-readiness read of 64/100 (agent native). The full breakdown is below, followed by every artifact we hold — each card links through to its machine-readable definition on apis.io.
Kin Score
This is the API Evangelist rating — a single, repeatable read computed from the artifacts on this page. Green fill is points earned; the red track is points possible, so every bar shows earned-versus-possible at a glance.
Kin Score
How this is scored →scored 2026-07-27 · rubric v0.5
How we profile Hugging Face
Each block below is one kind of artifact we hold for Hugging Face. For each we say what it is and why it earns a place in the profile, then list every one we've indexed — capped at two rows, scroll within the panel for the rest.
APIs 21
Each API is captured as its own OpenAPI definition — every operation, parameter, and response. This is the single most useful machine-readable description of what an API does, and it's what lets us score, lint, mock, and generate against it without asking the provider for anything.
Individual APIs this provider publishes, each with its own machine-readable definition.
Hugging Face Audio API
Speech recognition, audio classification, and text-to-speech tasks
Hugging Face Chat API
OpenAI-compatible chat completion endpoints
Hugging Face Chat Completions API
OpenAI-compatible chat completion endpoints
Hugging Face Computer Vision API
Image classification, object detection, and segmentation tasks
Hugging Face Data Access API
Row-level data access and preview endpoints
Hugging Face Dataset Info API
Dataset validity and structure endpoints
Hugging Face Datasets API
Operations for managing and querying datasets on the Hub
Hugging Face Embeddings API
Text embedding endpoints
Hugging Face Endpoints API
Manage dedicated inference endpoints
Hugging Face Files & Metadata API
Parquet files, size, statistics, and metadata
Hugging Face Image Generation API
Text-to-image generation
Hugging Face Info API
Server and model information
Hugging Face Models API
Operations for managing and querying models on the Hub
Hugging Face Multimodal API
Tasks involving multiple modalities
Hugging Face Natural Language Processing API
NLP tasks including text generation, classification, and translation
Hugging Face Providers API
Available cloud providers and hardware
Hugging Face Repos API
General repository management operations
Hugging Face Search & Filter API
Search and filter dataset contents
Hugging Face Spaces API
Operations for managing and querying Spaces on the Hub
Hugging Face Text Generation API
Text generation endpoints
Hugging Face Users API
User account and organization management
Scroll within the panel for all 21 ·
Postman Collections 6
A runnable collection turns the contract into something a developer can execute in seconds. We profile them because the fastest way to trust an API is to make a real call against it.
Ready-to-run Postman collections for exercising this provider's APIs.
Open Collections 6
Open, tool-agnostic collections carry the same runnable value as Postman without locking you to one client — the portable, forkable form of the same exercise.
Open, tool-agnostic API collections (OpenAPI-derived and Bruno).
Hugging Face Dataset Viewer API
OPEN COLLECTIONHugging Face Hub API
OPEN COLLECTIONHugging Face Inference API
OPEN COLLECTIONHugging Face Inference Endpoints API
OPEN COLLECTIONHugging Face Inference Providers API
OPEN COLLECTIONHugging Face Text Generation Inference API
OPEN COLLECTIONArazzo Workflows 14
Real integrations are rarely a single call. Arazzo describes the multi-step sequences — auth, then create, then confirm — so both a human and an agent can follow the choreography, not just the endpoints.
Multi-step API workflows described with the Arazzo specification.
Hugging Face Chat Completion with Model Discovery
Discover an available router model, confirm it exists, then run an OpenAI-compatible chat completion.
ARAZZOHugging Face Create Repository and Configure
Identify the authenticated user, create a new repository, then set its visibility and gating.
ARAZZOHugging Face Dataset Filter Rows
Confirm a dataset supports filtering, resolve its split, then apply a SQL-like filter.
ARAZZOHugging Face Dataset Search and Statistics
Resolve a dataset split, full-text search within it, then pull column statistics.
ARAZZOHugging Face Dataset Size and Parquet Files
Confirm a dataset on the Hub, read its size profile, then list its Parquet files.
ARAZZOHugging Face Dataset Validate and Preview
Check a dataset is viewer-ready, list its splits, then preview the first rows.
ARAZZOHugging Face Deploy Inference Endpoint and Wait
Create a dedicated Inference Endpoint, then poll its status until it is running.
ARAZZOHugging Face Discover a Space
Search Hub Spaces by SDK and query, then load the top Space's details.
ARAZZOHugging Face Embeddings Pair
Confirm an embedding model is available, then embed a query and a document for comparison.
ARAZZOHugging Face Grounded Text Generation
Find a text-generation model on the Hub, confirm it, then run hosted text generation.
ARAZZOHugging Face Search and Inspect a Model
Search the Hub for a model, fetch its full record, then inspect a specific revision.
ARAZZOHugging Face Summarize Then Translate
Summarize a long document with one model, then translate the summary with another.
ARAZZOHugging Face TGI Inspect and Generate
Read a TGI server's info, tokenize a prompt to check its length, then generate text.
ARAZZOHugging Face Toggle Inference Endpoint State
Read an endpoint's current state, then pause it if running or resume it if paused.
ARAZZOScroll within the panel for all 14 ·
MCP Servers 1
Model Context Protocol servers expose these APIs directly to AI agents. We profile them because agent-native access is the fastest-growing way this provider's capabilities actually get used.
Model Context Protocol servers that expose these APIs to AI agents.
MCP Server
MCP SERVERAgent Skills 16
An agent skill packages the how-to for driving these APIs from an assistant — the prompts, the sequence, the guardrails — so the knowledge to use the API travels with it.
Packaged agent skills for driving this provider's APIs from an AI assistant.
hf-cli
AGENT SKILLhf-mcp
AGENT SKILLhuggingface-best
AGENT SKILLhuggingface-community-evals
AGENT SKILLhuggingface-datasets
AGENT SKILLhuggingface-gradio
AGENT SKILLhuggingface-llm-trainer
AGENT SKILLhuggingface-local-models
AGENT SKILLhuggingface-paper-publisher
AGENT SKILLhuggingface-papers
AGENT SKILLhuggingface-tool-builder
AGENT SKILLhuggingface-trackio
AGENT SKILLhuggingface-vision-trainer
AGENT SKILLhuggingface-zerogpu
AGENT SKILLtrain-sentence-transformers
AGENT SKILLtransformers-js
AGENT SKILLScroll within the panel for all 16 ·
GraphQL 1
Where a provider ships GraphQL, the schema is the contract. We profile it alongside the REST surface so the whole interface is legible in one place.
GraphQL schemas published by this provider.
Hugging Face GraphQL Schema
This conceptual GraphQL schema models the Hugging Face AI platform, covering the full surface area of its public APIs: the Hub API for managing models, datasets, and spaces; the...
GRAPHQLPricing Plans 1
Pricing is part of the interface. Machine-readable plans tell you what a tier costs and includes before you commit — one of the six things the Kin Score reads for commercial clarity.
Published pricing tiers and plan structures.
Rate Limits 1
Rate limits are the difference between a demo that works and a production integration that doesn't fall over. Publishing them is an operational-transparency signal — and a hard requirement for any agent that plans its own throughput.
Documented rate limits and quota policies.
Hugging Face Rate Limits
RATE LIMITSFinOps 1
Cost, billing, and metering signals let a buyer model the financial operations of an API before it's live. We profile them for the same reason we profile pricing: the money is part of the contract.
Cost, billing, and metering signals for API financial operations.
Hugging Face Finops
FINOPSFeatures 7
The notable capabilities this provider advertises, captured as structured features so they can be searched and compared instead of read one landing page at a time.
Notable capabilities this provider offers.
Model Inference
Run inference on 200,000+ ML models with a simple HTTP request across NLP, vision, audio, and multimodal tasks.
Hub Repository Management
Programmatically manage models, datasets, and spaces including creation, versioning, and access control.
Dedicated Endpoints
Deploy models on dedicated infrastructure with autoscaling, custom hardware, and private networking.
Multi-Provider Routing
Unified OpenAI-compatible API routing to 15+ inference providers with automatic model selection.
Dataset Exploration
Query, search, filter, and visualize datasets without downloading via the Dataset Viewer API.
Text Generation Inference
High-performance LLM serving with streaming, tool calling, structured output, and grammar constraints.
OpenAI Compatibility
Drop-in replacement for OpenAI API with chat completions, embeddings, and image generation endpoints.
Scroll within the panel for all 7 ·
Semantic Vocabularies 7
JSON-LD contexts give the data shared meaning across APIs. We profile them because semantics are what let a machine reconcile 'customer' here with 'customer' somewhere else.
JSON-LD contexts and semantic vocabularies used across these APIs.
Hugging Face Context
JSON-LDHugging Face Hub Context
JSON-LDScroll within the panel for all 7 ·
Spectral Rules 2
Governance rulesets we run against this provider's specs — the automated checks behind parts of the score. Profiling them makes the quality bar explicit and re-runnable, not a matter of opinion.
Hugging Face API Rules
SPECTRALHugging Face API Rules
SPECTRALJSON Schema 136
Standalone JSON Schema definitions describe the data models behind the API. We profile them so the shapes are validatable on their own — useful long after a single request is forgotten.
Standalone JSON Schema definitions for this provider's data models.
ChatCompletionRequest
JSON SCHEMAChatCompletionResponse
JSON SCHEMAChatCompletionStreamResponse
JSON SCHEMAClassificationResult
JSON SCHEMACompletionRequest
JSON SCHEMACompletionResponse
JSON SCHEMACompletionStreamResponse
JSON SCHEMACreateEndpointRequest
JSON SCHEMACreateRepoRequest
JSON SCHEMAHugging Face Dataset
JSON SCHEMAError
JSON SCHEMAParquetResponse
JSON SCHEMARowsResponse
JSON SCHEMASearchResponse
JSON SCHEMASizeResponse
JSON SCHEMASplitsResponse
JSON SCHEMAStatisticsResponse
JSON SCHEMAValidityResponse
JSON SCHEMADatasetInfo
JSON SCHEMADatasetSummary
JSON SCHEMAEmbeddingRequest
JSON SCHEMAEmbeddingResponse
JSON SCHEMAEndpoint
JSON SCHEMAEndpointMetrics
JSON SCHEMAError
JSON SCHEMAErrorResponse
JSON SCHEMAFeatureExtractionRequest
JSON SCHEMAFillMaskRequest
JSON SCHEMAFillMaskResponse
JSON SCHEMAGenerateRequest
JSON SCHEMAGenerateResponse
JSON SCHEMACreateRepoRequest
JSON SCHEMADatasetInfo
JSON SCHEMADatasetSummary
JSON SCHEMAError
JSON SCHEMAModelInfo
JSON SCHEMAModelSummary
JSON SCHEMARepoUrl
JSON SCHEMASpaceInfo
JSON SCHEMASpaceSummary
JSON SCHEMAUserInfo
JSON SCHEMAImageGenerationRequest
JSON SCHEMAImageGenerationResponse
JSON SCHEMAClassificationResult
JSON SCHEMAHugging Face Inference Endpoint
JSON SCHEMACreateEndpointRequest
JSON SCHEMAEndpointMetrics
JSON SCHEMAEndpoint
JSON SCHEMAError
JSON SCHEMAProvider
JSON SCHEMAUpdateEndpointRequest
JSON SCHEMAError
JSON SCHEMAFeatureExtractionRequest
JSON SCHEMAFillMaskRequest
JSON SCHEMAFillMaskResponse
JSON SCHEMAInferenceRequest
JSON SCHEMAInferenceResponse
JSON SCHEMAModelLoadingResponse
JSON SCHEMAObjectDetectionResult
JSON SCHEMAChatCompletionRequest
JSON SCHEMAChatCompletionResponse
JSON SCHEMAChatCompletionStreamResponse
JSON SCHEMACompletionRequest
JSON SCHEMACompletionResponse
JSON SCHEMACompletionStreamResponse
JSON SCHEMAEmbeddingRequest
JSON SCHEMAEmbeddingResponse
JSON SCHEMAError
JSON SCHEMAImageGenerationRequest
JSON SCHEMAImageGenerationResponse
JSON SCHEMAUsage
JSON SCHEMAQuestionAnsweringRequest
JSON SCHEMAQuestionAnsweringResponse
JSON SCHEMASentenceSimilarityRequest
JSON SCHEMASpeechRecognitionResponse
JSON SCHEMASummarizationRequest
JSON SCHEMASummarizationResponse
JSON SCHEMATextClassificationRequest
JSON SCHEMATextGenerationRequest
JSON SCHEMATextGenerationResponse
JSON SCHEMATextToImageRequest
JSON SCHEMATranslationRequest
JSON SCHEMATranslationResponse
JSON SCHEMAZeroShotClassificationRequest
JSON SCHEMAZeroShotClassificationResponse
JSON SCHEMAInferenceRequest
JSON SCHEMAInferenceResponse
JSON SCHEMAInfo
JSON SCHEMAHugging Face Model
JSON SCHEMAModelInfo
JSON SCHEMAModelLoadingResponse
JSON SCHEMAModelSummary
JSON SCHEMAObjectDetectionResult
JSON SCHEMAParquetResponse
JSON SCHEMAProvider
JSON SCHEMAQuestionAnsweringRequest
JSON SCHEMAQuestionAnsweringResponse
JSON SCHEMARepoUrl
JSON SCHEMARowsResponse
JSON SCHEMASearchResponse
JSON SCHEMASentenceSimilarityRequest
JSON SCHEMASizeResponse
JSON SCHEMAHugging Face Space
JSON SCHEMASpaceInfo
JSON SCHEMASpaceSummary
JSON SCHEMASpeechRecognitionResponse
JSON SCHEMASplitsResponse
JSON SCHEMAStatisticsResponse
JSON SCHEMAStreamResponse
JSON SCHEMASummarizationRequest
JSON SCHEMASummarizationResponse
JSON SCHEMAChatCompletionRequest
JSON SCHEMAChatCompletionResponse
JSON SCHEMAChatCompletionStreamResponse
JSON SCHEMACompletionRequest
JSON SCHEMACompletionResponse
JSON SCHEMACompletionStreamResponse
JSON SCHEMAErrorResponse
JSON SCHEMAGenerateRequest
JSON SCHEMAGenerateResponse
JSON SCHEMAInfo
JSON SCHEMAStreamResponse
JSON SCHEMAUsage
JSON SCHEMATextClassificationRequest
JSON SCHEMATextGenerationRequest
JSON SCHEMATextGenerationResponse
JSON SCHEMATextToImageRequest
JSON SCHEMATranslationRequest
JSON SCHEMATranslationResponse
JSON SCHEMAUpdateEndpointRequest
JSON SCHEMAUsage
JSON SCHEMAHugging Face User
JSON SCHEMAUserInfo
JSON SCHEMAValidityResponse
JSON SCHEMAZeroShotClassificationRequest
JSON SCHEMAZeroShotClassificationResponse
JSON SCHEMAScroll within the panel for all 136 ·
JSON Structure 72
JSON Structure captures the data shapes in a form built for tooling — a complement to JSON Schema that keeps the model machine-legible.
JSON Structure definitions describing this provider's data shapes.
Hugging Face Dataset Viewer Error Structure
JSON STRUCTUREHugging Face Dataset Viewer Parquet Response Structure
JSON STRUCTUREHugging Face Dataset Viewer Rows Response Structure
JSON STRUCTUREHugging Face Dataset Viewer Search Response Structure
JSON STRUCTUREHugging Face Dataset Viewer Size Response Structure
JSON STRUCTUREHugging Face Dataset Viewer Splits Response Structure
JSON STRUCTUREHugging Face Dataset Viewer Validity Response Structure
JSON STRUCTUREHugging Face Hub Create Repo Request Structure
JSON STRUCTUREHugging Face Hub Dataset Info Structure
JSON STRUCTUREHugging Face Hub Dataset Summary Structure
JSON STRUCTUREHugging Face Hub Error Structure
JSON STRUCTUREHugging Face Hub Model Info Structure
JSON STRUCTUREHugging Face Hub Model Summary Structure
JSON STRUCTUREHugging Face Hub Repo Url Structure
JSON STRUCTUREHugging Face Hub Space Info Structure
JSON STRUCTUREHugging Face Hub Space Summary Structure
JSON STRUCTUREHugging Face Hub User Info Structure
JSON STRUCTUREHugging Face Inference Classification Result Structure
JSON STRUCTUREHugging Face Inference Endpoints Endpoint Structure
JSON STRUCTUREHugging Face Inference Endpoints Error Structure
JSON STRUCTUREHugging Face Inference Endpoints Provider Structure
JSON STRUCTUREHugging Face Inference Error Structure
JSON STRUCTUREHugging Face Inference Fill Mask Request Structure
JSON STRUCTUREHugging Face Inference Fill Mask Response Structure
JSON STRUCTUREHugging Face Inference Inference Request Structure
JSON STRUCTUREHugging Face Inference Inference Response Structure
JSON STRUCTUREHugging Face Inference Model Loading Response Structure
JSON STRUCTUREHugging Face Inference Object Detection Result Structure
JSON STRUCTUREHugging Face Inference Providers Error Structure
JSON STRUCTUREHugging Face Inference Providers Usage Structure
JSON STRUCTUREHugging Face Inference Summarization Request Structure
JSON STRUCTUREHugging Face Inference Summarization Response Structure
JSON STRUCTUREHugging Face Inference Text Generation Request Structure
JSON STRUCTUREHugging Face Inference Text To Image Request Structure
JSON STRUCTUREHugging Face Inference Translation Request Structure
JSON STRUCTUREHugging Face Inference Translation Response Structure
JSON STRUCTUREHugging Face Structure
JSON STRUCTUREHugging Face Text Generation Inference Info Structure
JSON STRUCTUREHugging Face Text Generation Inference Usage Structure
JSON STRUCTUREScroll within the panel for all 72 ·
Examples 135
Real request and response payloads are what turn a spec from abstract into obvious — and they're one of the twelve things an agent needs to call an API correctly on the first try.
Example request and response payloads for these APIs.
Hugging Face Getinfo Example
EXAMPLEHugging Face Getrows Example
EXAMPLEHugging Face Isvalid Example
EXAMPLEHugging Face Whoami Example
EXAMPLEScroll within the panel for all 135 ·
Security Posture 3
Authentication, domain security, vulnerability disclosure, and trust-center signals — the evidence that a provider takes security seriously enough to document it. We profile it because you can't govern what you can't see.
Authentication, domain security, vulnerability disclosure, and trust-center signals.
Agentic Access 1
An x-agentic-access contract marks which operations are safe for an agent to run on its own and which need a human in the loop. It is the difference between an API an agent can use and one it can use safely.
Recommended x-agentic-access execution contracts for AI agents.
Use Cases 5
What developers actually build with this provider — captured so the catalogue answers 'what is this for', not just 'what does this expose'.
What developers build with this provider.
ML Model Prototyping
Rapidly prototype AI applications by running inference on pre-trained models without infrastructure setup.
Production ML Deployment
Deploy and scale ML models for production workloads with dedicated endpoints and autoscaling.
Dataset Curation
Explore, validate, and curate ML datasets programmatically for training pipeline automation.
AI Application Development
Build AI-powered applications using unified inference APIs with multi-provider routing.
Model Benchmarking
Compare model performance across providers and hardware configurations for optimization.
Resources
Every other property we hold for Hugging Face — documentation, portals, status pages, policies, and corporate surface — grouped by the job it does, following the integrator's arc from getting started to running in production.
Get Started 4
Portal, sign-up, and the first successful call
Documentation 6
Reference material describing how the API behaves
Agent Surfaces 3
MCP servers, agent skills, and machine-readable catalogs
Design & Contract 15
Pagination, idempotency, versioning, errors, and events
Scroll within the panel for all 15 ·
Build 4
SDKs, sample code, and the tooling you integrate with
Access & Security 3
Authentication, authorization, and security posture
Learn 1
Tutorials, courses, talks, and written guidance
Operate 6
Status, limits, changes, and where to get help
Commercial 3
Pricing, plans, and the legal terms of use
Company 2
The organization behind the API
Other 1
Properties that don't map to a standard resource type
← All providers · Data indexed from github.com/api-evangelist/hugging-face · machine-readable index on apis.io