Claude
Anthropic's Claude AI assistant API for natural language processing and conversation.
Reference-quality API operations across every facet — a rich contract, published governance, transparent operations, and machine-readable commercial terms.
API Evangelist profiles Claude the way a machine reads it — 177 machine-readable artifacts across 9 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 — Claude scores 73.6/100 (exemplar), with a separate agent-readiness read of 60/100 (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.
Kin Score
How this is scored →scored 2026-07-27 · rubric v0.5
How we profile Claude
Each block below is one kind of artifact we hold for Claude. 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 9
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.
Claude Message Batches API
API for asynchronously processing large volumes of message requests at reduced cost with 50 percent discount.
Claude Models API
API for listing and retrieving metadata about available Claude models including capabilities and context windows.
Claude Files API
API for uploading and managing files to reference in Claude API requests without re-uploading content each time.
Claude Admin API
API for programmatically managing organization resources including members workspaces API keys and invites.
Claude Usage and Cost API
API for tracking token consumption and costs across your organization with breakdowns by model workspace and service tier.
Claude Text Completions API
Legacy API for generating text completions - deprecated in favor of the Messages API.
Claude Message Batches API
Create and manage asynchronous message batches
Claude Messages API
Create messages and count tokens
Claude Models API
List and retrieve available Claude models
Scroll within the panel for all 9 ·
Postman Collections 1
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.
Claude Messages API
POSTMANOpen Collections 1
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).
Claude Messages API
OPEN COLLECTIONArazzo Workflows 8
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.
Claude Analyze Document From URL
Count tokens for a URL-referenced document, then ask Claude a question about it.
ARAZZOClaude Batch Process and Retrieve Results
Submit a message batch, poll until it ends, then retrieve the JSONL results.
ARAZZOClaude Cancel and Delete Batch
Submit a batch, request cancellation, poll until it ends, then delete it.
ARAZZOClaude Count Tokens Then Create Message
Pre-flight a prompt through token counting before sending it to the Messages API.
ARAZZOClaude Find Latest Batch Results
List recent message batches, inspect the most recent one, and retrieve its results if it has ended.
ARAZZOClaude Multi-Turn Conversation
Send a first user turn, then continue the conversation with a follow-up that includes the assistant's reply.
ARAZZOClaude Select Model and Create Message
Discover an available Claude model, confirm its metadata, then generate a message with it.
ARAZZOClaude Tool Use Round Trip
Offer the model a tool, capture its tool_use request, then return a tool_result for a final answer.
ARAZZOScroll within the panel for all 8 ·
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 SERVERPricing 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.
Claude Plans Pricing
PLANSRate 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.
Claude 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.
Claude 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.
Multi-Turn Conversations
Maintain context across multiple message exchanges for natural dialogue interactions.
Tool Use
Enable Claude to call external tools and functions to perform actions and retrieve data.
Vision
Process and analyze images alongside text for multimodal understanding.
Extended Thinking
Allow Claude to reason step-by-step for complex tasks with visible thinking process.
Streaming Responses
Receive responses in real-time via server-sent events for responsive user experiences.
Message Batches
Process large volumes of requests asynchronously at 50 percent reduced cost.
Token Counting
Pre-calculate token usage for messages including tools, images, and documents.
Scroll within the panel for all 7 ·
Semantic Vocabularies 2
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.
Claude Context
JSON-LDClaude Messages 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.
Claude API Rules
SPECTRALClaude API Rules
SPECTRALJSON Schema 65
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.
BatchRequestItem
JSON SCHEMACacheControl
JSON SCHEMAContentBlock
JSON SCHEMAContentBlockParam
JSON SCHEMACountTokensRequest
JSON SCHEMACreateMessageBatchRequest
JSON SCHEMACreateMessageRequest
JSON SCHEMADeletedMessageBatch
JSON SCHEMADocumentBlockParam
JSON SCHEMAError
JSON SCHEMAImageBlockParam
JSON SCHEMAClaude Message
JSON SCHEMAMessageBatch
JSON SCHEMAMessageBatchList
JSON SCHEMAMessageBatchResult
JSON SCHEMAMessageParam
JSON SCHEMABatchRequestItem
JSON SCHEMACacheControl
JSON SCHEMAContentBlockParam
JSON SCHEMAContentBlock
JSON SCHEMACountTokensRequest
JSON SCHEMACreateMessageBatchRequest
JSON SCHEMACreateMessageRequest
JSON SCHEMADeletedMessageBatch
JSON SCHEMADocumentBlockParam
JSON SCHEMAError
JSON SCHEMAImageBlockParam
JSON SCHEMAMessageBatchList
JSON SCHEMAMessageBatchResult
JSON SCHEMAMessageBatch
JSON SCHEMAMessageParam
JSON SCHEMAMessage
JSON SCHEMAMetadata
JSON SCHEMAModelInfo
JSON SCHEMAModelList
JSON SCHEMAOutputConfig
JSON SCHEMATextBlockParam
JSON SCHEMATextBlock
JSON SCHEMAThinkingBlockParam
JSON SCHEMAThinkingBlock
JSON SCHEMAThinkingConfig
JSON SCHEMATokenCount
JSON SCHEMAToolChoice
JSON SCHEMAToolResultBlockParam
JSON SCHEMATool
JSON SCHEMAToolUseBlockParam
JSON SCHEMAToolUseBlock
JSON SCHEMAUsage
JSON SCHEMAMetadata
JSON SCHEMAModelInfo
JSON SCHEMAModelList
JSON SCHEMAOutputConfig
JSON SCHEMATextBlock
JSON SCHEMATextBlockParam
JSON SCHEMAThinkingBlock
JSON SCHEMAThinkingBlockParam
JSON SCHEMAThinkingConfig
JSON SCHEMATokenCount
JSON SCHEMATool
JSON SCHEMAClaude Tool Use
JSON SCHEMAToolChoice
JSON SCHEMAToolResultBlockParam
JSON SCHEMAToolUseBlock
JSON SCHEMAToolUseBlockParam
JSON SCHEMAUsage
JSON SCHEMAScroll within the panel for all 65 ·
JSON Structure 33
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.
Claude Messages Batch Request Item Structure
JSON STRUCTUREClaude Messages Cache Control Structure
JSON STRUCTUREClaude Messages Content Block Param Structure
JSON STRUCTUREClaude Messages Content Block Structure
JSON STRUCTUREClaude Messages Count Tokens Request Structure
JSON STRUCTUREClaude Messages Create Message Batch Request Structure
JSON STRUCTUREClaude Messages Create Message Request Structure
JSON STRUCTUREClaude Messages Deleted Message Batch Structure
JSON STRUCTUREClaude Messages Document Block Param Structure
JSON STRUCTUREClaude Messages Error Structure
JSON STRUCTUREClaude Messages Image Block Param Structure
JSON STRUCTUREClaude Messages Message Batch List Structure
JSON STRUCTUREClaude Messages Message Batch Result Structure
JSON STRUCTUREClaude Messages Message Batch Structure
JSON STRUCTUREClaude Messages Message Param Structure
JSON STRUCTUREClaude Messages Message Structure
JSON STRUCTUREClaude Messages Metadata Structure
JSON STRUCTUREClaude Messages Model Info Structure
JSON STRUCTUREClaude Messages Model List Structure
JSON STRUCTUREClaude Messages Output Config Structure
JSON STRUCTUREClaude Messages Text Block Param Structure
JSON STRUCTUREClaude Messages Text Block Structure
JSON STRUCTUREClaude Messages Thinking Block Param Structure
JSON STRUCTUREClaude Messages Thinking Block Structure
JSON STRUCTUREClaude Messages Thinking Config Structure
JSON STRUCTUREClaude Messages Token Count Structure
JSON STRUCTUREClaude Messages Tool Choice Structure
JSON STRUCTUREClaude Messages Tool Result Block Param Structure
JSON STRUCTUREClaude Messages Tool Structure
JSON STRUCTUREClaude Messages Tool Use Block Param Structure
JSON STRUCTUREClaude Messages Tool Use Block Structure
JSON STRUCTUREClaude Messages Usage Structure
JSON STRUCTUREClaude Structure
JSON STRUCTUREScroll within the panel for all 33 ·
Examples 32
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.
Claude Messages Tool Example
EXAMPLEScroll within the panel for all 32 ·
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.
AI-Powered Chat Applications
Build conversational interfaces with context-aware responses and tool integration.
Content Generation
Generate, edit, and transform text content for marketing, documentation, and creative writing.
Code Assistance
Use Claude for code generation, review, debugging, and technical documentation.
Document Analysis
Extract information, summarize, and answer questions about documents and images.
Batch Processing
Process large datasets of prompts efficiently using the Message Batches API.
Integrations 4
Pre-built integrations with other platforms tell you where this provider already fits in a stack.
Pre-built integrations with other platforms and tools.
Amazon Bedrock
Access Claude models through AWS Bedrock for enterprise deployment with AWS infrastructure.
Google Cloud Vertex AI
Use Claude on Google Cloud through Vertex AI integration.
LangChain
Integrate Claude into LangChain pipelines for advanced AI application development.
MCP Protocol
Connect Claude to external data sources and tools via the Model Context Protocol.
Resources
Every other property we hold for Claude — 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 2
Portal, sign-up, and the first successful call
Documentation 1
Reference material describing how the API behaves
Agent Surfaces 2
MCP servers, agent skills, and machine-readable catalogs
Design & Contract 10
Pagination, idempotency, versioning, errors, and events
Scroll within the panel for all 10 ·
Build 2
SDKs, sample code, and the tooling you integrate with
Access & Security 4
Authentication, authorization, and security posture
Operate 4
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
← All providers · Data indexed from github.com/api-evangelist/claude · machine-readable index on apis.io