Anthropic Claude

Anthropic Claude is a family of frontier large language models (Opus, Sonnet, Haiku) accessible via the Anthropic API for building AI assistants, agents, and integrations. The API supports streaming chat completions, tool use, vision, prompt caching, batch processing, the Files API, computer use, and the Model Context Protocol, with authentication via x-api-key headers and a base URL at api.anthropic.com.

Anthropic Claude publishes 4 APIs on the APIs.io network, including Message Batches API, Messages API, Models API, and 1 more. Tagged areas include Artificial Intelligence, Large Language Models, LLM, Generative AI, and Chat.

The Anthropic Claude catalog on APIs.io includes 1 event-driven AsyncAPI specification and 1 Spectral governance ruleset.

Anthropic Claude’s developer surface includes authentication, documentation, API reference, developer console, signup flow, pricing, support, and 23 more developer resources.

🌐 Visit website 📡 Source on GitHub

48.8/100 developing ▬ flat Agent 29/100 agent ready saas Full breakdown ↓
scored 2026-09-10 · rubric v0.20.0

1 APIs 1 MCP Servers

Artificial Intelligence Large Language Models LLM Generative AI Chat Agents Claude

Kin Score

Kin Score How this is scored →
scored 2026-09-10 · rubric v0.20.0

Composite quality — 48.8/100 · developing

Contract Quality 14.0 / 23

Developer Ergonomics 11.1 / 18

Access Clarity 8.0 / 18

Operational Transparency 4.0 / 12

Contract Governance 1.2 / 11

Discoverability 6.2 / 9

Create-or-Update Ergonomics 0.0 / 10

Agent readiness — 29/100 · agent ready

Machine-Readable Contract 18 / 18

Agentic Access Contract 10 / 10

Documented Reversibility 6 / 6

MCP Server 12 / 12

Machine-Readable Auth 10 / 10

Idempotency 0 / 9

Stable Error Semantics 8 / 8

Request/Response Examples 0 / 7

Rate-Limit Signaling 7 / 7

Typed Event Surface 6 / 6

Agent Skills 0 / 5

Well-Known Catalog 0 / 4

Consent & Bot Identity 0 / 3

A2A Agent Card 0 / 8

Dry-Run / Simulate Mode 0 / 4

Delegated User Identity 0 / 6

Protected Resource Metadata 0 / 5

Registration Without a Human 0 / 6

Agentic Commerce Well-Known Document 0 / 5

Create-or-Update Ergonomics applies to this provider. This API accepts writes, so it carries 10 points of the composite. It is scored from the published contracts themselves: whether a caller can create-or-update in one call, whether the write accepts a key the caller already holds, and whether the response says which branch ran. Without that, every write needs a search-and-branch in front of it, and the first time that check is skipped a duplicate record is created. Scored against the observed mean rather than raw — a provider at the catalog average is unchanged by this facet, not penalised by it.

Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. Every facet and dimension name above is a link: it opens that measurement's own page — what it means, the exact checks that feed it, how the whole catalog distributes on it, and the providers at the top of it. This rating is computed from github.com/api-evangelist/anthropic-claude: open an issue to ask a question, or submit a pull request to add artifacts. Submit an artifact on GitHub — free → Manage your own listing — the Influence plan, $499/mo →

APIs 4

Individual APIs this provider publishes, each with its own machine-readable definition.

Anthropic Claude Message Batches API

Submit and manage asynchronous Message Batches.

Anthropic Claude Messages API

Create messages with Claude models.

Anthropic Claude Models API

List and inspect available Claude models.

Anthropic Claude Token Counting API

Count tokens for a prospective Messages request.

Open Collections 6

Open, tool-agnostic API collections (OpenAPI-derived and Bruno).

API Collection

OPEN COLLECTION

Anthropic Claude Messages Message Batches API

OPEN COLLECTION

Anthropic Claude Message Batches Messages API

OPEN COLLECTION

Anthropic Claude Messages Message Batches Models API

OPEN COLLECTION

Anthropic Claude Messages Message Batches Token Counting API

OPEN COLLECTION

Anthropic Claude Messages API

OPEN COLLECTION

MCP Servers 1

Model Context Protocol servers that expose these APIs to AI agents.

MCP Server

MCP SERVER

Event Specifications 1

AsyncAPI definitions for this provider's event-driven and streaming APIs.

Anthropic Claude Messages Streaming API

AsyncAPI specification modeling the Server-Sent Events (SSE) stream produced by Anthropic's Claude Messages API when `"stream": true` is set on a POST to `/v1/messages`. Transpo...

ASYNCAPI

Spectral Rules 1

Spectral governance rulesets for linting and validating these APIs.

Anthropic Claude API Rules

6 rules · 1 errors 5 warnings

SPECTRAL

Security Posture 3

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Anthropic Claude Authentication

apiKey · 1 scheme

SECURITY

Anthropic Claude Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Anthropic Claude Vulnerability Disclosure

Hackerone · security.txt · contact published

SECURITY

Agentic Access 1

Recommended x-agentic-access execution contracts for AI agents.

Anthropic Claude Agentic Access

9 operations · 4 acting

AGENTIC

Resources

Get Started 2

Portal, sign-up, and the first successful call

Console

Console

Signup

Signup

Documentation 2

Reference material describing how the API behaves

Documentation

Documentation

APIReference

APIReference

Agent Surfaces 2

MCP servers, agent skills, and machine-readable catalogs

AgenticAccess

AgenticAccess

MCPServer

MCPServer

Design & Contract 2

Pagination, idempotency, versioning, errors, and events

ErrorCodes

ErrorCodes

Versioning

Versioning

Build 4

SDKs, sample code, and the tooling you integrate with

GitHubOrganization

Python SDK

TypeScript SDK

Claude Code

Access & Security 4

Authentication, authorization, and security posture

VulnerabilityDisclosure

VulnerabilityDisclosure

DomainSecurity

DomainSecurity

Authentication

Authentication

Authentication

Authentication

Learn 2

Tutorials, courses, talks, and written guidance

Cookbook

Cookbook

YouTube

YouTube

Operate 3

Status, limits, changes, and where to get help

RateLimits

RateLimits

StatusPage

StatusPage

Support

Support

Commercial 3

Pricing, plans, and the legal terms of use

Pricing

Pricing

PrivacyPolicy

PrivacyPolicy

TermsOfService

TermsOfService

Company 4

The organization behind the API

Website

Website

Blog

Blog

X (Twitter)

X (Twitter)

LinkedIn

Other 2

Properties that don't map to a standard resource type

Models

Models

ModelContextProtocol

ModelContextProtocol

Source (apis.yml)

aid: anthropic-claude
name: Anthropic Claude
description: Anthropic Claude is a family of frontier large language models (Opus, Sonnet, Haiku) accessible via the Anthropic
  API for building AI assistants, agents, and integrations. The API supports streaming chat completions, tool use, vision,
  prompt caching, batch processing, the Files API, computer use, and the Model Context Protocol, with authentication via x-api-key
  headers and a base URL at api.anthropic.com.
type: Index
deliveryModel:
  model: saas
  open_source: false
  commercial: true
  callable_host: true
  label: Hosted service · you call their endpoint
  confidence: high
  source:
  - openapi
  - pricing
  generated: '2026-08-28'
  method: derived
accessModel:
  pricing: unknown
  onboarding: unknown
  trial: false
  try_now: false
  public: false
  label: Unknown
  confidence: low
  source:
  - authentication
  - security
  generated: '2026-09-03'
  method: derived
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/anthropic-claude.png
tags:
- Artificial Intelligence
- Large Language Models
- LLM
- Generative AI
- Chat
- Agents
- Claude
url: https://raw.githubusercontent.com/api-evangelist/anthropic-claude/refs/heads/main/apis.yml
created: '2026-05-11'
modified: '2026-05-29'
specificationVersion: '0.23'
apis:
- aid: anthropic-claude:anthropic-claude-message-batches-api
  name: Anthropic Claude Message Batches API
  description: Submit and manage asynchronous Message Batches.
  humanURL: https://docs.anthropic.com/en/api/messages
  baseURL: https://api.anthropic.com
  tags:
  - Message Batches
  properties:
  - type: OpenAPI
    url: openapi/anthropic-claude-message-batches-api-openapi.yml
  - type: Documentation
    url: https://docs.anthropic.com/en/api/messages
  - type: APIReference
    url: https://docs.anthropic.com/en/api/getting-started
  - type: AsyncAPI
    url: asyncapi/anthropic-claude-asyncapi.yml
  - type: GettingStarted
    url: https://docs.anthropic.com/en/api/getting-started
- aid: anthropic-claude:anthropic-claude-messages-api
  name: Anthropic Claude Messages API
  description: Create messages with Claude models.
  humanURL: https://docs.anthropic.com/en/api/messages
  baseURL: https://api.anthropic.com
  tags:
  - Message
  tags_raw:
  - Messages
  properties:
  - type: OpenAPI
    url: openapi/anthropic-claude-messages-api-openapi.yml
  - type: Documentation
    url: https://docs.anthropic.com/en/api/messages
  - type: APIReference
    url: https://docs.anthropic.com/en/api/getting-started
  - type: AsyncAPI
    url: asyncapi/anthropic-claude-asyncapi.yml
  - type: GettingStarted
    url: https://docs.anthropic.com/en/api/getting-started
- aid: anthropic-claude:anthropic-claude-models-api
  name: Anthropic Claude Models API
  description: List and inspect available Claude models.
  humanURL: https://docs.anthropic.com/en/api/messages
  baseURL: https://api.anthropic.com
  tags:
  - Models
  properties:
  - type: OpenAPI
    url: openapi/anthropic-claude-models-api-openapi.yml
  - type: Documentation
    url: https://docs.anthropic.com/en/api/messages
  - type: APIReference
    url: https://docs.anthropic.com/en/api/getting-started
  - type: AsyncAPI
    url: asyncapi/anthropic-claude-asyncapi.yml
  - type: GettingStarted
    url: https://docs.anthropic.com/en/api/getting-started
- aid: anthropic-claude:anthropic-claude-token-counting-api
  name: Anthropic Claude Token Counting API
  description: Count tokens for a prospective Messages request.
  humanURL: https://docs.anthropic.com/en/api/messages
  baseURL: https://api.anthropic.com
  tags:
  - Token Counting
  properties:
  - type: OpenAPI
    url: openapi/anthropic-claude-token-counting-api-openapi.yml
  - type: Documentation
    url: https://docs.anthropic.com/en/api/messages
  - type: APIReference
    url: https://docs.anthropic.com/en/api/getting-started
  - type: AsyncAPI
    url: asyncapi/anthropic-claude-asyncapi.yml
  - type: GettingStarted
    url: https://docs.anthropic.com/en/api/getting-started
common:
- type: AgenticAccess
  url: agentic-access/anthropic-claude-agentic-access.yml
- type: VulnerabilityDisclosure
  url: security/anthropic-claude-vulnerability-disclosure.yml
- type: DomainSecurity
  url: security/anthropic-claude-domain-security.yml
- type: Authentication
  url: authentication/anthropic-claude-authentication.yml
- type: Website
  url: https://www.anthropic.com
- type: Documentation
  url: https://docs.anthropic.com
- type: APIReference
  url: https://docs.anthropic.com/en/api/getting-started
- type: Console
  url: https://console.anthropic.com
- type: Signup
  url: https://console.anthropic.com/login
- type: Pricing
  url: https://www.anthropic.com/pricing
- type: Models
  url: https://docs.anthropic.com/en/docs/about-claude/models
- type: Authentication
  url: https://docs.anthropic.com/en/api/getting-started
- type: RateLimits
  url: https://docs.anthropic.com/en/api/rate-limits
- type: ErrorCodes
  url: https://docs.anthropic.com/en/api/errors
- type: Versioning
  url: https://docs.anthropic.com/en/api/versioning
- type: StatusPage
  url: https://status.anthropic.com
- type: Support
  url: https://support.anthropic.com
- type: PrivacyPolicy
  url: https://www.anthropic.com/legal/privacy
- type: TermsOfService
  url: https://www.anthropic.com/legal/commercial-terms
- type: GitHubOrganization
  url: https://github.com/anthropics
- type: Python SDK
  url: https://github.com/anthropics/anthropic-sdk-python
- type: TypeScript SDK
  url: https://github.com/anthropics/anthropic-sdk-typescript
- type: Cookbook
  url: https://github.com/anthropics/anthropic-cookbook
- type: Claude Code
  url: https://www.anthropic.com/claude-code
- type: ModelContextProtocol
  url: https://modelcontextprotocol.io
- type: Blog
  url: https://www.anthropic.com/news
- type: X (Twitter)
  url: https://x.com/AnthropicAI
- type: LinkedIn
  url: https://www.linkedin.com/company/anthropicresearch
- type: YouTube
  url: https://www.youtube.com/@anthropic-ai
- name: MCP Server
  url: https://github.com/anthropics/claude-ai-mcp
  type: MCPServer
features:
- name: Frontier Models
  description: Access to Claude Opus, Sonnet, and Haiku families of large language models with industry-leading reasoning,
    coding, and agentic capabilities.
- name: Tool Use
  description: Define custom tools that Claude can invoke during conversations to call external APIs, query databases, or
    execute code.
- name: Vision
  description: Multi-modal input supports images alongside text for analysis, OCR, diagrams, and document understanding.
- name: Prompt Caching
  description: Cache large prompts (system instructions, documents, examples) to reduce cost and latency on subsequent requests.
- name: Streaming
  description: Server-sent events stream responses token-by-token for low-latency interactive experiences.
- name: Batch API
  description: Submit large batches of asynchronous requests at 50 percent discount with results delivered within 24 hours.
- name: Files API
  description: Upload and reference files for use across Messages, batches, and computer-use sessions.
- name: Computer Use
  description: Allow Claude to control a virtual computer (screenshots, mouse, keyboard) to complete multi-step tasks autonomously.
- name: Extended Thinking
  description: Enable extended reasoning steps for harder problems with transparent thinking traces.
useCases:
- name: AI Assistants and Chatbots
  description: Build conversational assistants for customer support, productivity, and knowledge work powered by Claude models.
- name: Coding Agents
  description: Power software engineering agents that read, edit, run, and test code across large repositories.
- name: Document Processing
  description: Extract, summarize, and analyze long documents using large context windows and vision capabilities.
- name: Content Generation
  description: Generate marketing copy, technical writing, translations, and creative content at scale.
- name: Agentic Workflows
  description: Orchestrate multi-step agent workflows using tool use, MCP servers, and computer use for end-to-end task automation.
integrations:
- name: Amazon Bedrock
  description: Access Claude models via the AWS Bedrock API
- name: Google Cloud Vertex AI
  description: Access Claude models via Google Cloud Vertex AI
- name: Model Context Protocol
  description: Open protocol for connecting Claude to external tools and data sources
- name: LangChain
  description: First-class LangChain integration for chains and agents
- name: LlamaIndex
  description: Use Claude as the LLM for RAG and indexing workflows
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com

Work with this as data

Every provider here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for providers

9 MCP tools reach this

find_providersBrowse and filter every provider in the catalog.
get_provider_artifactsEvery artifact this provider publishes, grouped by type.
get_provider_operationsEvery operation across all of their OpenAPIs — one call instead of parsing every spec.
get_provider_toolsEvery MCP tool they ship, with the operation each wraps.
get_provider_evidenceHow each part of their score was established. Free — the basis for a claim should not sit behind it.
get_provider_ratingPRO — composite, band, trend and facet scores.
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
resolveTurn a domain, URL or GitHub org into the provider it belongs to.
find_cohortsEvery scored population of providers in the catalog.

All 92 tools →

Call it yourself

curl for this page

This provider

curl "https://apis.io/api/v1/providers/anthropic-claude"

All providers

curl "https://apis.io/api/v1/providers?limit=25"

Every operation they expose

curl "https://apis.io/api/v1/providers/anthropic-claude/operations?limit=25"

How their score was established

curl "https://apis.io/api/v1/providers/anthropic-claude/evidence"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.