Night exhibition · Worldwide · EnglishBuild Something Agents Want

Anthropic · agent Twin Score 94

Anthropic API capability matrix

Anthropic's API is the Messages API, tool use, prompt caching, and long context — the machine product behind Claude. Console and workbench help humans. Agents get clean JSON, streaming, and relatively honest limit documentation. Available also via AWS Bedrock and Google Vertex for enterprises who will not hold an Anthropic key. Twin Score on this directory is 72 for humans and 94 for agents, using the public rubric (interface, onboarding, human docs, collaboration, support, pricing fairness, accessibility, reliability versus API quality, MCP or tool surface, CLI, structured docs, machine auth, quotas, determinism, and skill packaging). Anthropic API is sold by Anthropic, founded 2021, headquartered in San Francisco, USA. Pricing in public materials: Usage-based tokens; batch discounts; Bedrock and Vertex as alternate bills. Machine capabilities we record: API excellent, MCP strong, CLI basic, docs excellent, auth API keys, cloud marketplaces. This page is editorial, not a star rating scraped from users.

Human72
Agent94

Updated 2026-08-01. Editorial, not a user-count rating.

Named editor: Edu Tor. Twin Score updated 2026-08-01. See methodology and the rubric. Meaning is in this HTML, not in any canvas.

API / MCP / CLI / docs / auth

MCP is strong. If that is none or basic, do not invent a server. Auth: API keys, cloud marketplaces.

Matrix

SurfaceLevel
APIexcellent
MCPstrong
CLIbasic
Docsexcellent
Webhooksstrong
AuthAPI keys, cloud marketplaces
SDKspython, typescript, http

SKILL.md · Human twin page · Official site