Anthropic
Anthropic is an AI safety company and the creator of the Claude family of large language models (Opus, Sonnet, Haiku, and the Fable/Mythos frontier line). The Claude Developer Platform exposes them through a single REST API at api.anthropic.com: the Messages API for text, vision, tool use, thinking, streaming and structured outputs; Message Batches for asynchronous work at half price; Files, Token Counting, Models, and experimental Prompt Tools; Managed Agents with sessions, environments, memory stores, vaults and scheduled deployments; a Skills API; and an Admin API for organizations, workspaces, members, invites and API keys. Authentication is x-api-key with a required anthropic-version date header and dated anthropic-beta opt-ins. Anthropic also authors two of the open standards the agent ecosystem runs on — the Model Context Protocol and the Agent Skills specification — and ships Claude Code, the terminal agentic coding tool, which doubles as a first-party stdio MCP server.
Reference-quality API operations across every facet — a rich contract, published governance, transparent operations, and machine-readable commercial terms.
API Evangelist profiles Anthropic the way a machine reads it — 136 machine-readable artifacts across 6 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 — Anthropic scores 77.8/100 (exemplar), with a separate agent-readiness read of 38/100 (agent ready). 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. Every facet and dimension name is a link: it opens that measurement's page on APIs.io, where the rating runs across the whole catalog — the exact checks that feed it, how every profiled provider distributes on it, and who is at the top of it.
Kin Score
How this is scored →scored 2026-09-10 · rubric v0.20.0
Put this on your own site. The badge is drawn live from Anthropic's current Kin Score — paste it once and it updates itself every time the score is recomputed. It follows your visitor's light or dark setting, and it links back here so anyone who sees it can read the full breakdown.
<!-- Kin Score · API Evangelist -->
<a href="https://providers.apievangelist.com/providers/anthropic/"
title="Anthropic on API Evangelist — API profile and Kin Score">
<img src="https://apis.io/badge/anthropic.svg"
alt="Anthropic Kin Score — API readiness rating by API Evangelist" width="150" height="150" loading="lazy">
</a>[](https://providers.apievangelist.com/providers/anthropic/)<!-- Kin Score · API Evangelist -->
<a href="https://providers.apievangelist.com/providers/anthropic/"
title="Anthropic on API Evangelist — API profile and Kin Score">
<img src="https://apis.io/badge/anthropic/card.svg"
alt="Anthropic Kin Score — API readiness rating by API Evangelist" width="340" height="120" loading="lazy">
</a>More shapes, themes and sizes → · Score as JSON · How badges work
How we profile Anthropic
Each block below is one kind of artifact we hold for Anthropic. 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 43
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.
Anthropic Messages API
Send a structured list of input messages with text and/or image content, and the model will generate the next message in the conversation. The Messages API supports text, images...
Anthropic Models API
List and inspect Claude models including Opus 4.7, Sonnet 4.6, and Haiku 4.5. The response includes max_input_tokens, max_tokens, and a capabilities object for every model so cl...
Anthropic Files API
The Files API lets you upload and manage files for reuse across Messages, Batches, code execution, and Managed Agents without re-uploading content. 500 MB request limit; support...
Anthropic Skills API
Create and manage custom Agent Skills. Skills are filesystem-based directories of instructions, scripts, and resources that Claude loads on demand via progressive disclosure. Wo...
Anthropic Agents API
Reusable, versioned agent configurations
Anthropic Api Keys API
Monitor and manage API keys
Anthropic Cost API
Service-level cost reporting
Anthropic Environments API
Container configuration for agent sessions
Anthropic Events API
User messages and tool results sent to a session
Anthropic Organization API
Retrieve organization information and settings
Anthropic Organization Invites API
Create and manage organization invitations
Anthropic Organization Members API
Manage organization members and their roles
Anthropic Prompt Generation API
APIs for generating well-written prompts for specified tasks
Anthropic Prompt Improvement API
APIs for enhancing existing prompts with feedback
Anthropic Prompt Templatization API
APIs for converting prompts into reusable templates with variables
Anthropic Sessions API
Stateful agent execution instances
Anthropic Usage API
Token usage and consumption reporting
Anthropic Workspace Members API
Manage workspace membership and roles
Anthropic Workspaces API
Create and manage workspaces within an organization
Anthropic Agents?beta=true API
The Agents?beta=true API from Anthropic — 1 operation(s) for agents?beta=true.
Anthropic Anthropic API
The Anthropic API API from Anthropic — 0 operation(s) for anthropic api.
Anthropic Complete API
The Complete API from Anthropic — 1 operation(s) for complete.
Anthropic Deployment Runs API
The Deployment Runs API from Anthropic — 1 operation(s) for deployment runs.
Anthropic Deployment Runs?beta=true API
The Deployment Runs?beta=true API from Anthropic — 1 operation(s) for deployment runs?beta=true.
Anthropic Deployments API
The Deployments API from Anthropic — 5 operation(s) for deployments.
Anthropic Deployments?beta=true API
The Deployments?beta=true API from Anthropic — 1 operation(s) for deployments?beta=true.
Anthropic Dreams API
The Dreams API from Anthropic — 3 operation(s) for dreams.
Anthropic Dreams?beta=true API
The Dreams?beta=true API from Anthropic — 1 operation(s) for dreams?beta=true.
Anthropic Environments?beta=true API
The Environments?beta=true API from Anthropic — 1 operation(s) for environments?beta=true.
Anthropic Files?beta=true API
The Files?beta=true API from Anthropic — 1 operation(s) for files?beta=true.
Anthropic Memory Stores API
The Memory Stores API from Anthropic — 7 operation(s) for memory stores.
Anthropic Memory Stores?beta=true API
The Memory Stores?beta=true API from Anthropic — 1 operation(s) for memory stores?beta=true.
Anthropic Messages?beta=true API
The Messages?beta=true API from Anthropic — 1 operation(s) for messages?beta=true.
Anthropic Models?beta=true API
The Models?beta=true API from Anthropic — 1 operation(s) for models?beta=true.
Anthropic Organizations API
The Organizations API from Anthropic — 43 operation(s) for organizations.
Anthropic Sessions?beta=true API
The Sessions?beta=true API from Anthropic — 1 operation(s) for sessions?beta=true.
Anthropic Skills?beta=true API
The Skills?beta=true API from Anthropic — 1 operation(s) for skills?beta=true.
Anthropic Tunnels API
The Tunnels API from Anthropic — 7 operation(s) for tunnels.
Anthropic Tunnels?beta=true API
The Tunnels?beta=true API from Anthropic — 1 operation(s) for tunnels?beta=true.
Anthropic User Profiles API
The User Profiles API from Anthropic — 2 operation(s) for user profiles.
Anthropic User Profiles?beta=true API
The User Profiles?beta=true API from Anthropic — 1 operation(s) for user profiles?beta=true.
Anthropic Vaults API
The Vaults API from Anthropic — 6 operation(s) for vaults.
Anthropic Vaults?beta=true API
The Vaults?beta=true API from Anthropic — 1 operation(s) for vaults?beta=true.
Scroll within the panel for all 43 ·
Postman Collections 11
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.
Anthropic Admin API
POSTMANAnthropic Files API
POSTMANAnthropic Managed Agents API
POSTMANAnthropic Messages API
POSTMANAnthropic Models API
POSTMANAnthropic Prompt Tools API
POSTMANAnthropic Skills API
POSTMANAnthropic Token Counting API
POSTMANAnthropic Usage and Cost API
POSTMANScroll within the panel for all 11 ·
Open Collections 29
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).
API Collection
OPEN COLLECTIONAnthropic Admin API
OPEN COLLECTIONAnthropic Admin Agents API
OPEN COLLECTIONAnthropic Admin Agents Api Keys API
OPEN COLLECTIONAnthropic Admin Agents Claude Code Analytics API
OPEN COLLECTIONAnthropic Admin Agents Cost API
OPEN COLLECTIONAnthropic Admin Agents Environments API
OPEN COLLECTIONAnthropic Admin Agents Events API
OPEN COLLECTIONAnthropic Admin Agents Files API
OPEN COLLECTIONAnthropic Managed Agents API
OPEN COLLECTIONAnthropic Admin Agents Message Batches API
OPEN COLLECTIONAnthropic Admin Agents Messages API
OPEN COLLECTIONAnthropic Admin Agents Models API
OPEN COLLECTIONAnthropic Admin Agents Organization API
OPEN COLLECTIONAnthropic Admin Agents Organization Invites API
OPEN COLLECTIONAnthropic Admin Agents Organization Members API
OPEN COLLECTIONAnthropic Admin Agents Prompt Generation API
OPEN COLLECTIONAnthropic Admin Agents Prompt Improvement API
OPEN COLLECTIONAnthropic Admin Agents Prompt Templatization API
OPEN COLLECTIONAnthropic Prompt Tools API
OPEN COLLECTIONAnthropic Admin Agents Sessions API
OPEN COLLECTIONAnthropic Admin Agents Skill Versions API
OPEN COLLECTIONAnthropic Admin Agents Skills API
OPEN COLLECTIONAnthropic Admin Agents Token Counting API
OPEN COLLECTIONAnthropic Admin Agents Tokens API
OPEN COLLECTIONAnthropic Admin Agents Usage API
OPEN COLLECTIONAnthropic Usage and Cost API
OPEN COLLECTIONAnthropic Admin Agents Workspace Members API
OPEN COLLECTIONAnthropic Admin Agents Workspaces API
OPEN COLLECTIONScroll within the panel for all 29 ·
Arazzo Workflows 11
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.
Anthropic Cancel a Message Batch and Confirm
Create a batch, request cancellation, then poll until it leaves the canceling state.
ARAZZOAnthropic Create Batch, Poll, and Retrieve Results
Submit a message batch, poll until processing ends, then fetch the JSONL results.
ARAZZOAnthropic Count Tokens Then Create Message
Estimate input token usage for a prompt, then send the message only when it fits a budget.
ARAZZOAnthropic Create Workspace and Add a Member
Create a workspace, add a user to it, then confirm the member appears in the roster.
ARAZZOAnthropic Discover a Model and Send a Message
List available models, confirm a chosen model exists, then create a message with it.
ARAZZOAnthropic Invite an Org Member and Confirm
Send an organization invite, then read it back and branch on whether it is still pending.
ARAZZOAnthropic List Batches and Fetch Latest Results
List message batches, inspect the most recent one, and pull its results if it has ended.
ARAZZOAnthropic Onboard an Org Member into a Workspace
Find an org member by email, create a workspace, and add that member to it.
ARAZZOAnthropic Provision and Promote a Workspace Member
Create a workspace, add a member as a developer, then promote them to workspace admin.
ARAZZOAnthropic Upload, List, and Clean Up a File
Upload a file, confirm it appears in the file list, then delete it to clean up.
ARAZZOAnthropic Upload, Verify, and Download a File
Upload a file, read back its metadata, and download its content when it is downloadable.
ARAZZOScroll within the panel for all 11 ·
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.
Anthropic GraphQL Schema
This GraphQL schema is a conceptual representation of the Anthropic Claude API derived from the REST API surface. The Anthropic API provides access to Claude large language mode...
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 things the Kin Score reads for access clarity — renamed from commercial clarity in rubric 0.12, because a free statutory interface has access terms and no commercial ones.
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.
Anthropic 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.
Anthropic Finops
FINOPSFeatures 26
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.
Scroll within the panel for all 26 ·
Event Specifications 2
Not every API is request/response. AsyncAPI describes the event-driven and streaming side — the webhooks and channels — so the asynchronous half of the interface is documented the same way the synchronous half is.
AsyncAPI definitions for this provider's event-driven and streaming APIs.
Anthropic Messages Streaming API
AsyncAPI specification modeling the Server-Sent Events (SSE) stream produced by Anthropic's Messages API when `"stream": true` is set on a POST to `/v1/messages`. Transport: HTT...
ASYNCAPIAnthropic Webhooks
ASYNCAPISemantic Vocabularies 1
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.
Anthropic Context
JSON-LDSpectral 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.
Anthropic API Rules
SPECTRALAnthropic API Rules
SPECTRALJSON Schema 2
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.
Anthropic Message
JSON SCHEMAAnthropic Tool Use
JSON SCHEMASecurity Posture 4
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.
Anthropic Trust Center
SOC 2 Type I, SOC 2 Type II, ISO 27001:2022, ISO/IEC 42001:2023, HIPAA
SECURITYAgentic 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.
Resources
Every other property we hold for Anthropic — 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 10
Portal, sign-up, and the first successful call
Scroll within the panel for all 10 ·
Documentation 33
Reference material describing how the API behaves
Scroll within the panel for all 33 ·
Agent Surfaces 6
MCP servers, agent skills, and machine-readable catalogs
Design & Contract 19
Pagination, idempotency, versioning, errors, and events
Scroll within the panel for all 19 ·
Build 24
SDKs, sample code, and the tooling you integrate with
Scroll within the panel for all 24 ·
Access & Security 8
Authentication, authorization, and security posture
Scroll within the panel for all 8 ·
Learn 3
Tutorials, courses, talks, and written guidance
Operate 9
Status, limits, changes, and where to get help
Scroll within the panel for all 9 ·
Commercial 7
Pricing, plans, and the legal terms of use
Scroll within the panel for all 7 ·
Company 4
The organization behind the API
Other 16
Properties that don't map to a standard resource type
Scroll within the panel for all 16 ·
← All providers · Data indexed from github.com/api-evangelist/anthropic · machine-readable index on apis.io
This is an independent, third-party profile of Anthropic, published by API Evangelist. We do not operate, host, resell, or support these APIs, and we are not affiliated with or endorsed by the company unless stated above. Everything here is built from publicly available information — the company's own site, developer portal, documentation, public repositories, and the specifications it publishes for public use. Nothing is obtained by breaching a system, defeating an access control, or using credentials.
The Kin Score and Agent Readiness rating are independently calculated assessments of a company's public API artifacts, scored against a published rubric. They are not certifications, endorsements, security assessments, or audits.
Corrections, re-scores, and removal are free — no partnership or purchase required, and you do not need to justify the request. A removed company is recorded as unrated, never scored zero for having asked. Acknowledgement within one business day; removal within two.
info@apievangelist.com
·
Read the full data-sourcing policy →
On a security or compliance team? Put security in the subject line and
you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.