Anthropic logo

Anthropic

Anthropic is an AI safety company and creator of the Claude family of large language models (Opus, Sonnet, Haiku). The Claude API provides access to Claude models for text generation, vision, tool use, extended thinking, batch processing, and agentic workflows including managed agents, skills, memory, compaction, and computer use. Anthropic also publishes the open Model Context Protocol (MCP) for standardized AI tool integration and ships Claude Code, the terminal-based agentic coding tool.

11 APIs 26 Features
AIArtificial IntelligenceClaudeFoundation ModelsLarge Language ModelsMachine LearningMCPAgents

APIs

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 Message Batches API

Send a batch of Message creation requests at 50% off both input and output tokens. Batches can take up to 24 hours to complete. Supports up to 300k output tokens per request on ...

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 Admin API

Programmatically manage administrative resources including organization info, members, invites, workspaces, workspace members, and API keys. Requires an Admin API key (sk-ant-ad...

Anthropic Prompts API

Prompt tools API for generating, improving, and templatizing prompts. Backs the Console Prompt Generator and integrates into the Workbench prompt authoring workflow.

Anthropic Token Counting API

Count the number of tokens in a Message, including tools, images, and documents, without creating it. The Token Count API accepts the same structured list of inputs as Messages ...

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 Usage and Cost API

Programmatically access your organization's API usage and cost data with the Usage & Cost Admin API. The Usage API tracks token consumption with breakdowns by model, workspace, ...

Anthropic Claude Code Analytics API

Daily aggregated user-level Claude Code productivity metrics — sessions, lines of code, commits, pull requests, tool actions, and estimated costs by model — via /v1/organization...

Anthropic Managed Agents API

Claude Managed Agents — a fully managed agent harness for running Claude as an autonomous agent with secure sandboxing, built-in tools (bash, file ops, web search/fetch, MCP), S...

Features

Claude Opus 4.7 — most capable generally available model for complex reasoning and agentic coding
Claude Sonnet 4.6 — balanced model combining speed and intelligence with 1M context window
Claude Haiku 4.5 — fastest model with near-frontier intelligence
Messages API with text, vision, tool use, extended thinking, streaming, structured outputs
Prompt caching with automatic and manual breakpoints, 5-minute and 1-hour TTLs, cache reads at 10% of input price
Server-side compaction API for effectively infinite conversations on Opus 4.6/4.7 and Sonnet 4.6
Memory tool (client-side) for cross-conversation persistence with ZDR support
Message Batches API with 50% discount on both input and output tokens
Files API for upload-once / reuse-many content across Messages and Managed Agents
Agent Skills API (beta) — packaged domain expertise with progressive disclosure
Claude Managed Agents (beta) — Agents, Sessions, Environments with SSE streaming and managed sandboxes
Web Search tool ($10/1,000 searches) and Web Fetch tool (free)
Code Execution tool — Python + Bash + filesystem in sandbox; 1,550 free container-hours/month
Computer Use tool for browser and desktop automation (beta)
Advisor tool (beta) for pairing executor and high-intelligence advisor models
Tool Search tool and Programmatic Tool Calling
Token-bucket rate limiting with cache-aware ITPM (cache reads excluded on most models)
Five usage tiers (Tier 1-4 plus Monthly Invoicing) with automatic advancement
Usage & Cost Admin API and Claude Code Analytics Admin API for FinOps reporting
Rate Limits API for programmatic limit inspection
Workload Identity Federation for short-lived bearer tokens
Data residency controls (US-only inference at 1.1x pricing for models after Feb 2026)
Available via Claude API, Claude Platform on AWS, Microsoft Foundry, AWS Bedrock, and Google Vertex AI
{"Official SDKs"=>"Python, TypeScript, Java, Go, Ruby, C#, PHP plus the `ant` CLI"}
Claude Code (terminal agent) and Claude Code GitHub Action
Open MCP specification stewardship via modelcontextprotocol.io

Event Specifications

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...

ASYNCAPI

Semantic Vocabularies

Anthropic Context

0 classes · 18 properties

JSON-LD

Resources

🔗
PostmanWorkspace
PostmanWorkspace
🔗
ArazzoWorkflows
ArazzoWorkflows
🔗
LinkedIn
LinkedIn
🔗
Documentation
Documentation
🌐
Portal
Portal
🔗
Documentation
Documentation
🟢
StatusPage
StatusPage
📄
ChangeLog
ChangeLog
🔗
Documentation
Documentation
🔗
RateLimits
RateLimits
🔗
Tiers
Tiers
🔗
Errors
Errors
🔗
Documentation
Documentation
🔗
Versioning
Versioning
🔗
Regions
Regions
💬
Support
Support
🔗
Plans
Plans
💰
Pricing
Pricing
🌐
Portal
Portal
🚀
GettingStarted
GettingStarted
🔗
Glossary
Glossary
🔗
Documentation
Documentation
📜
PrivacyPolicy
PrivacyPolicy
📜
PrivacyPolicy
PrivacyPolicy
🟢
StatusPage
StatusPage
📰
Blog
Blog
📰
Blog
Blog
📝
SignUp
SignUp
📝
SignUp
SignUp
🔗
Sandbox
Sandbox
🔗
Documentation
Documentation
🔗
TrustCenter
TrustCenter
📜
TermsOfService
TermsOfService
🔗
Documentation
Documentation
🔗
Documentation
Documentation
🔗
Documentation
Documentation
👥
GitHubOrganization
GitHubOrganization
📦
SDK
SDK
📦
SDK
SDK
📦
SDK
SDK
📦
SDK
SDK
📦
SDK
SDK
📦
SDK
SDK
📦
SDK
SDK
📦
SDK
SDK
🔧
Tool
Tool
🔧
Tool
Tool
🔧
Tool
Tool
💻
CodeExamples
CodeExamples
🔗
Courses
Courses
🔗
Courses
Courses
🔗
Plugins
Plugins
💻
CodeExamples
CodeExamples
💻
CodeExamples
CodeExamples
🔗
Plugins
Plugins
🎓
Training
Training
🔗
Forum
Forum
🔗
Documentation
Documentation
🔗
Documentation
Documentation
🔗
Documentation
Documentation
🔗
Documentation
Documentation
🔗
Documentation
Documentation
🔗
Documentation
Documentation
🔗
Documentation
Documentation
🔗
Documentation
Documentation
🔗
Documentation
Documentation
🔗
Documentation
Documentation
🔗
Documentation
Documentation
🔗
Documentation
Documentation
🔗
Documentation
Documentation
🔗
Documentation
Documentation
🔗
Documentation
Documentation
🔗
Documentation
Documentation
🔗
Documentation
Documentation
🔗
Documentation
Documentation
🔗
Models
Models
📦
SDK
SDK
📦
SDK
SDK
🔗
Documentation
Documentation
👥
GitHubOrganization
GitHubOrganization
🔗
Documentation
Documentation
🔗
Documentation
Documentation
🌐
Portal
Portal
🔗
Documentation
Documentation
🔗
Documentation
Documentation
🚀
GettingStarted
GettingStarted
🔗
Plans
Plans
🔗
RateLimits
RateLimits
🔗
FinOps
FinOps

Sources

Raw ↑
aid: anthropic
url: https://raw.githubusercontent.com/api-evangelist/anthropic/refs/heads/main/apis.yml
apis:
  - aid: anthropic:anthropic-messages-api
    name: Anthropic Messages API
    tags:
      - AI
      - Artificial Intelligence
      - Messages
    humanURL: https://docs.anthropic.com/en/api/messages
    properties:
      - url: https://docs.anthropic.com/en/api/messages
        type: Documentation
      - url: https://docs.anthropic.com/en/api/messages-streaming
        type: Documentation
      - url: openapi/anthropic-messages-api-openapi.yml
        type: OpenAPI
      - url: asyncapi/anthropic-asyncapi.yml
        type: AsyncAPI
      - url: json-schema/anthropic-message-schema.json
        type: JSONSchema
      - url: json-schema/anthropic-tool-use-schema.json
        type: JSONSchema
      - url: json-ld/anthropic-context.jsonld
        type: JSONLD
    description: >-
      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, tool use, extended thinking, streaming,
      structured outputs, prompt caching, compaction, and the new advisor tool for pairing executor and
      higher-intelligence advisor models.
  - aid: anthropic:anthropic-models-api
    name: Anthropic Models API
    tags:
      - AI
      - Artificial Intelligence
      - Models
    humanURL: https://docs.anthropic.com/en/api/models-list
    properties:
      - url: https://docs.anthropic.com/en/api/models-list
        type: Documentation
      - url: openapi/anthropic-models-api-openapi.yml
        type: OpenAPI
    description: >-
      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 clients can discover model properties
      programmatically.
  - aid: anthropic:anthropic-message-batches-api
    name: Anthropic Message Batches API
    tags:
      - AI
      - Artificial Intelligence
      - Batches
      - Messages
    humanURL: https://docs.anthropic.com/en/api/creating-message-batches
    properties:
      - url: https://docs.anthropic.com/en/api/creating-message-batches
        type: Documentation
      - url: openapi/anthropic-message-batches-api-openapi.yml
        type: OpenAPI
    description: >-
      Send a batch of Message creation requests at 50% off both input and output tokens. Batches can take up to 24 hours
      to complete. Supports up to 300k output tokens per request on Opus 4.6/4.7 and Sonnet 4.6 with the
      output-300k-2026-03-24 beta header.
  - aid: anthropic:anthropic-files-api
    name: Anthropic Files API
    tags:
      - AI
      - Artificial Intelligence
      - Files
    humanURL: https://docs.anthropic.com/en/api/files-create
    properties:
      - url: https://docs.anthropic.com/en/api/files-create
        type: Documentation
      - url: openapi/anthropic-files-api-openapi.yml
        type: OpenAPI
    description: >-
      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; supports PDFs, images, Office documents, and plain
      text.
  - aid: anthropic:anthropic-admin-api
    name: Anthropic Admin API
    tags:
      - Administrative
      - AI
      - Artificial Intelligence
    humanURL: https://docs.anthropic.com/en/api/admin-api/users/get-user
    properties:
      - url: https://docs.anthropic.com/en/api/admin-api/users/get-user
        type: Documentation
      - url: openapi/anthropic-admin-api-openapi.yml
        type: OpenAPI
    description: >-
      Programmatically manage administrative resources including organization info, members, invites, workspaces,
      workspace members, and API keys. Requires an Admin API key (sk-ant-admin...).
  - aid: anthropic:anthropic-prompts-api
    name: Anthropic Prompts API
    tags:
      - AI
      - Artificial Intelligence
      - Prompts
    humanURL: https://docs.anthropic.com/en/api/prompt-tools-generate
    properties:
      - url: https://docs.anthropic.com/en/api/prompt-tools-generate
        type: Documentation
      - url: openapi/anthropic-prompts-api-openapi.yml
        type: OpenAPI
    description: >-
      Prompt tools API for generating, improving, and templatizing prompts. Backs the Console Prompt Generator and
      integrates into the Workbench prompt authoring workflow.
  - aid: anthropic:anthropic-token-counting-api
    name: Anthropic Token Counting API
    tags:
      - AI
      - Artificial Intelligence
      - Counting
      - Tokens
    humanURL: https://docs.anthropic.com/en/api/messages-count-tokens
    properties:
      - url: https://docs.anthropic.com/en/api/messages-count-tokens
        type: Documentation
      - url: openapi/anthropic-token-counting-api-openapi.yml
        type: OpenAPI
    description: >-
      Count the number of tokens in a Message, including tools, images, and documents, without creating it. The Token
      Count API accepts the same structured list of inputs as Messages including system prompts, tools, images, and
      PDFs. Free to use but subject to requests-per-minute rate limits.
  - aid: anthropic:anthropic-skills-api
    name: Anthropic Skills API
    tags:
      - Agents
      - AI
      - Artificial Intelligence
      - Skills
    humanURL: https://docs.anthropic.com/en/api/skills/create-skill
    properties:
      - url: https://docs.anthropic.com/en/api/skills/create-skill
        type: Documentation
      - url: openapi/anthropic-skills-api-openapi.yml
        type: OpenAPI
    description: >-
      Create and manage custom Agent Skills. Skills are filesystem-based directories of instructions, scripts, and
      resources that Claude loads on demand via progressive disclosure. Workspace-wide sharing. The Skills API is
      currently in beta and requires the skills-2025-10-02 beta header.
  - aid: anthropic:anthropic-usage-cost-api
    name: Anthropic Usage and Cost API
    tags:
      - Administration
      - AI
      - Artificial Intelligence
      - Cost
      - Usage
      - FinOps
    humanURL: https://docs.anthropic.com/en/api/usage-cost-api
    properties:
      - url: https://docs.anthropic.com/en/api/usage-cost-api
        type: Documentation
      - url: openapi/anthropic-usage-cost-api-openapi.yml
        type: OpenAPI
    description: >-
      Programmatically access your organization's API usage and cost data with the Usage & Cost Admin API. The Usage API
      tracks token consumption with breakdowns by model, workspace, and service tier via
      /v1/organizations/usage_report/messages. The Cost API retrieves service-level USD breakdowns via
      /v1/organizations/cost_report. Requires an Admin API key.
  - aid: anthropic:anthropic-claude-code-analytics-api
    name: Anthropic Claude Code Analytics API
    tags:
      - Administration
      - AI
      - Analytics
      - Artificial Intelligence
      - Claude Code
      - Productivity
    humanURL: https://docs.anthropic.com/en/api/claude-code-analytics-api
    properties:
      - url: https://docs.anthropic.com/en/api/claude-code-analytics-api
        type: Documentation
      - url: openapi/anthropic-claude-code-analytics-api-openapi.yml
        type: OpenAPI
    description: >-
      Daily aggregated user-level Claude Code productivity metrics — sessions, lines of code, commits, pull requests,
      tool actions, and estimated costs by model — via /v1/organizations/usage_report/claude_code. Requires an Admin API
      key.
  - aid: anthropic:anthropic-managed-agents-api
    name: Anthropic Managed Agents API
    tags:
      - Agents
      - AI
      - Artificial Intelligence
      - Beta
      - Managed Agents
      - Sessions
      - Environments
    humanURL: https://platform.claude.com/docs/en/managed-agents/overview
    properties:
      - url: https://platform.claude.com/docs/en/managed-agents/overview
        type: Documentation
      - url: https://platform.claude.com/docs/en/managed-agents/agent-setup
        type: Documentation
      - url: https://platform.claude.com/docs/en/managed-agents/sessions
        type: Documentation
      - url: https://platform.claude.com/docs/en/managed-agents/environments
        type: Documentation
      - url: openapi/anthropic-managed-agents-api-openapi.yml
        type: OpenAPI
    description: >-
      Claude Managed Agents — a fully managed agent harness for running Claude as an autonomous agent with secure
      sandboxing, built-in tools (bash, file ops, web search/fetch, MCP), SSE streaming, vault-managed OAuth
      credentials, multiagent sessions, and self-hosted sandbox option. Three resources — Agents, Sessions, Environments
      — plus event streaming. Currently in public beta under the managed-agents-2026-04-01 header.
name: Anthropic
tags:
  - AI
  - Artificial Intelligence
  - Claude
  - Foundation Models
  - Large Language Models
  - Machine Learning
  - MCP
  - Agents
kind: contract
image: https://kinlane-productions2.s3.amazonaws.com/apis-json/apis-json-logo.jpg
access: 3rd-Party
common:
  - type: PostmanWorkspace
    url: https://www.postman.com/kinlaneapi/anthropic/overview
  - type: ArazzoWorkflows
    url: arazzo/
    workflows:
      - url: arazzo/anthropic-batch-cancel-and-confirm-workflow.yml
        name: Anthropic Cancel a Message Batch and Confirm
        summary: Create a batch, request cancellation, then poll until it leaves the canceling state.
      - url: arazzo/anthropic-batch-create-poll-results-workflow.yml
        name: Anthropic Create Batch, Poll, and Retrieve Results
        summary: Submit a message batch, poll until processing ends, then fetch the JSONL results.
      - url: arazzo/anthropic-count-tokens-then-message-workflow.yml
        name: Anthropic Count Tokens Then Create Message
        summary: Estimate input token usage for a prompt, then send the message only when it fits a budget.
      - url: arazzo/anthropic-create-workspace-and-add-member-workflow.yml
        name: Anthropic Create Workspace and Add a Member
        summary: Create a workspace, add a user to it, then confirm the member appears in the roster.
      - url: arazzo/anthropic-discover-model-and-message-workflow.yml
        name: Anthropic Discover a Model and Send a Message
        summary: List available models, confirm a chosen model exists, then create a message with it.
      - url: arazzo/anthropic-invite-org-member-and-confirm-workflow.yml
        name: Anthropic Invite an Org Member and Confirm
        summary: Send an organization invite, then read it back and branch on whether it is still pending.
      - url: arazzo/anthropic-list-batches-and-fetch-latest-results-workflow.yml
        name: Anthropic List Batches and Fetch Latest Results
        summary: List message batches, inspect the most recent one, and pull its results if it has ended.
      - url: arazzo/anthropic-onboard-member-to-workspace-workflow.yml
        name: Anthropic Onboard an Org Member into a Workspace
        summary: Find an org member by email, create a workspace, and add that member to it.
      - url: arazzo/anthropic-provision-and-promote-workspace-member-workflow.yml
        name: Anthropic Provision and Promote a Workspace Member
        summary: Create a workspace, add a member as a developer, then promote them to workspace admin.
      - url: arazzo/anthropic-upload-list-and-cleanup-file-workflow.yml
        name: Anthropic Upload, List, and Clean Up a File
        summary: Upload a file, confirm it appears in the file list, then delete it to clean up.
      - url: arazzo/anthropic-upload-verify-download-file-workflow.yml
        name: Anthropic Upload, Verify, and Download a File
        summary: Upload a file, read back its metadata, and download its content when it is downloadable.
  - type: LinkedIn
    url: https://www.linkedin.com/company/anthropicresearch
  - url: https://github.com/anthropics/anthropic-quickstarts
    name: Quickstarts
    type: Documentation
  - url: https://platform.claude.com/docs/en/home
    name: Claude API Docs
    type: Portal
  - url: https://docs.anthropic.com/en/api/messages
    name: Messages - Anthropic
    type: Documentation
  - url: https://status.anthropic.com/
    name: Anthropic Status
    type: StatusPage
  - url: https://platform.claude.com/docs/en/release-notes/api
    name: Claude Platform Release Notes
    type: ChangeLog
  - url: https://platform.claude.com/login
    name: Claude Console
    type: Documentation
  - url: https://docs.anthropic.com/en/api/rate-limits
    name: Rate limits - Anthropic
    type: RateLimits
  - url: https://docs.anthropic.com/en/api/service-tiers
    name: Service tiers - Anthropic
    type: Tiers
  - url: https://docs.anthropic.com/en/api/errors
    name: Errors - Anthropic
    type: Errors
  - url: https://docs.anthropic.com/en/api/client-sdks
    name: Client SDKs - Anthropic
    type: Documentation
  - url: https://docs.anthropic.com/en/api/versioning
    name: Versions - Anthropic
    type: Versioning
  - url: https://docs.anthropic.com/en/api/supported-regions
    name: Supported regions - Anthropic
    type: Regions
  - url: https://docs.anthropic.com/en/api/getting-help
    name: Getting help - Anthropic
    type: Support
  - url: https://www.anthropic.com/pricing
    data:
      - id: free
        name: Free
        entries:
          - geo: US
            unit: 1
            label: User
            limit: 1
            price: Free
            metric: user
            timeFrame: month
            description: Usage based pricing.
        elements:
          - name: Chat on web, iOS, Android, and on your desktop
          - name: Generate code and visualize data
          - name: Write, edit, and create content
          - name: Analyze text and images
          - name: Ability to search the web
          - name: Unlock more from Claude with desktop extensions
        description: Try Claude
      - id: pro
        name: Pro
        entries:
          - geo: US
            unit: 1
            label: User
            limit: 1
            price: 20
            metric: user
            timeFrame: month
            description: Usage based pricing.
        elements:
          - name: More usage
          - name: Access Claude Code directly in your terminal
          - name: Access to unlimited Projects to organize chats and documents
          - name: Access to Research
          - name: Connect Google Workspace email, calendar, and docs
          - name: Connect your everyday tools in just a few clicks (with remote MCP servers)
          - name: Extended thinking for complex work
          - name: Ability to use more Claude models
        description: For everyday productivity.
      - id: max
        name: Max
        entries:
          - geo: US
            unit: 1
            label: User
            limit: 1
            price: 100
            metric: user
            timeFrame: month
            description: Usage based pricing.
        elements:
          - name: Choose 5x or 20x more usage per session than Pro
          - name: Higher output limits for all tasks
          - name: Early access to advanced Claude features
          - name: Priority access at high traffic times
        description: Get the most out of Claude.
      - id: team
        name: Team
        entries:
          - geo: US
            unit: 1
            label: User
            limit: 1
            price: 25
            metric: user
            timeFrame: month
            description: Usage based pricing.
        elements:
          - name: More usage
          - name: Central billing and administration
          - name: Early access to collaboration features
          - name: Claude Code available separately through Anthropic Console
        description: For collaboration across organizations
      - id: enterprise
        name: Enterprise
        entries:
          - geo: US
            unit: 1
            label: User
            limit: 1
            price: Call
            metric: user
            timeFrame: month
            description: For businesses operating at scale
        elements:
          - name: More usage
          - name: Enhanced context window
          - name: Single sign-on (SSO) and domain capture
          - name: Role-based access with fine grained permissioning
          - name: System for Cross-domain Identity Management (SCIM)
          - name: Audit logs
          - name: Google Docs cataloging
          - name: Claude Code available separately through Anthropic Console
        description: For collaboration across organizations
    name: Plans
    type: Plans
  - url: https://www.anthropic.com/pricing#api
    data:
      - id: claude-opus-4-7
        name: Claude Opus 4.7
        type: Latest
        entries:
          - geo: US
            unit: 1M
            label: Input
            price: 5
            metric: token
            timeFrame: usage
            description: Input token usage-based pricing.
          - geo: US
            unit: 1M
            label: Output
            price: 25
            metric: token
            timeFrame: usage
            description: Output token usage-based pricing.
          - geo: US
            unit: 1M
            label: Read Prompt Caching
            price: 0.5
            metric: token
            timeFrame: usage
            description: Read prompt caching for model.
          - geo: US
            unit: 1M
            label: Write Prompt Caching 5min
            price: 6.25
            metric: token
            timeFrame: usage
            description: Write prompt caching 5-minute TTL for model.
          - geo: US
            unit: 1M
            label: Write Prompt Caching 1hr
            price: 10
            metric: token
            timeFrame: usage
            description: Write prompt caching 1-hour TTL for model.
        description: >-
          Most capable generally available model for complex reasoning and agentic coding. 1M context window, 128k max
          output, new tokenizer.
      - id: claude-opus-4-6
        name: Claude Opus 4.6
        type: Legacy
        entries:
          - geo: US
            unit: 1M
            label: Input
            price: 5
            metric: token
            timeFrame: usage
          - geo: US
            unit: 1M
            label: Output
            price: 25
            metric: token
            timeFrame: usage
        description: Most capable Claude model from the previous generation with fast mode support and 1M context.
      - id: claude-sonnet-4-6
        name: Claude Sonnet 4.6
        type: Latest
        entries:
          - geo: US
            unit: 1M
            label: Prompts Input < 200K
            price: 3
            metric: token
            maximum: 200000
            timeFrame: usage
            description: Input token less than 200K token usage-based pricing.
          - geo: US
            unit: 1M
            label: Prompts Input > 200K
            price: 6
            metric: token
            minimum: 200000
            timeFrame: usage
            description: Input token greater than 200K token usage-based pricing.
          - geo: US
            unit: 1M
            label: Prompts Output < 200K
            price: 15
            metric: token
            maximum: 200000
            timeFrame: usage
            description: Output token less than 200k usage-based pricing.
          - geo: US
            unit: 1M
            label: Prompts Output > 200K
            price: 22.5
            metric: token
            minimum: 200000
            timeFrame: usage
            description: Output token greater than 200k usage-based pricing.
          - geo: US
            unit: 1M
            label: Read Prompt Caching < 200K
            price: 0.3
            metric: token
            maximum: 200000
            timeFrame: usage
            description: Read prompt caching for less than 200K tokens model.
          - geo: US
            unit: 1M
            label: Write Prompt Caching < 200K
            price: 3.75
            metric: token
            maximum: 200000
            timeFrame: usage
            description: Write prompt caching for less than 200K tokens model.
        description: High performance balanced model with 1M context window support.
      - id: claude-haiku-4-5
        name: Claude Haiku 4.5
        type: Latest
        entries:
          - geo: US
            unit: 1M
            label: Input
            price: 1
            metric: token
            timeFrame: usage
          - geo: US
            unit: 1M
            label: Output
            price: 5
            metric: token
            timeFrame: usage
          - geo: US
            unit: 1M
            label: Read Prompt Caching
            price: 0.1
            metric: token
            timeFrame: usage
          - geo: US
            unit: 1M
            label: Write Prompt Caching 5min
            price: 1.25
            metric: token
            timeFrame: usage
          - geo: US
            unit: 1M
            label: Write Prompt Caching 1hr
            price: 2
            metric: token
            timeFrame: usage
        description: Fastest, near-frontier model for real-time and high-volume workloads.
      - id: web-search
        name: Web Search
        type: Tools
        entries:
          - geo: US
            unit: 1K
            label: Searches
            price: 10
            metric: search
            timeFrame: usage
        description: Give Claude access to the latest information from the web.
      - id: code-execution
        name: Code Execution
        type: Tools
        entries:
          - geo: US
            unit: 1
            label: Per Hour Per Container
            price: 0.05
            metric: container
            timeFrame: hour
        description: >-
          Run Python/Bash in a sandboxed environment. Free when used with web search or web fetch; 1,550 free
          container-hours/month per organization for standalone use.
      - id: fast-mode
        name: Fast Mode
        type: Features
        entries:
          - geo: US
            unit: 1M
            label: Input
            price: 30
            metric: token
            timeFrame: usage
            description: Fast mode input token pricing for Opus 4.6/4.7.
          - geo: US
            unit: 1M
            label: Output
            price: 150
            metric: token
            timeFrame: usage
            description: Fast mode output token pricing for Opus 4.6/4.7.
        description: >-
          Significantly faster output for Claude Opus 4.6 and 4.7 at premium pricing (6x standard rates). Research
          preview.
      - id: web-fetch
        name: Web Fetch
        type: Tools
        entries:
          - geo: US
            unit: 1
            label: Requests
            price: 0
            metric: request
            timeFrame: usage
        description: Fetch web page content for Claude to process.
    name: Pricing
    type: Pricing
  - url: https://www.anthropic.com/api
    name: Build with Claude
    type: Portal
  - url: https://docs.anthropic.com/en/docs/get-started
    name: Get started with Claude
    type: GettingStarted
  - url: https://docs.anthropic.com/en/docs/about-claude/glossary
    name: Glossary
    type: Glossary
  - url: https://www.anthropic.com/legal/terms
    type: Documentation
  - url: https://www.anthropic.com/legal/privacy
    type: PrivacyPolicy
  - url: https://privacy.claude.com/
    type: PrivacyPolicy
  - url: https://status.anthropic.com
    type: StatusPage
  - url: https://www.anthropic.com/news
    type: Blog
  - url: https://www.anthropic.com/engineering
    type: Blog
  - url: https://console.anthropic.com/
    type: SignUp
  - url: https://platform.claude.com/
    name: Claude Console
    type: SignUp
  - url: https://platform.claude.com/workbench
    type: Sandbox
  - url: https://docs.anthropic.com/en/api/beta-headers
    type: Documentation
  - url: https://trust.anthropic.com/
    type: TrustCenter
  - url: https://www.anthropic.com/legal/aup
    type: TermsOfService
  - url: https://docs.anthropic.com/en/api/administration-api
    type: Documentation
  - url: https://docs.anthropic.com/en/api/usage-cost-api
    type: Documentation
  - url: https://docs.anthropic.com/en/api/claude-code-analytics-api
    type: Documentation
  - url: https://github.com/anthropics
    type: GitHubOrganization
  - url: https://github.com/anthropics/anthropic-sdk-python
    name: Python SDK
    type: SDK
  - url: https://github.com/anthropics/anthropic-sdk-typescript
    name: TypeScript SDK
    type: SDK
  - url: https://github.com/anthropics/anthropic-sdk-java
    name: Java SDK
    type: SDK
  - url: https://github.com/anthropics/anthropic-sdk-go
    name: Go SDK
    type: SDK
  - url: https://github.com/anthropics/anthropic-sdk-ruby
    name: Ruby SDK
    type: SDK
  - url: https://github.com/anthropics/anthropic-sdk-csharp
    name: C# SDK
    type: SDK
  - url: https://github.com/anthropics/anthropic-sdk-php
    name: PHP SDK
    type: SDK
  - url: https://github.com/anthropics/claude-agent-sdk-python
    name: Claude Agent SDK (Python)
    type: SDK
  - url: https://github.com/anthropics/claude-code
    name: Claude Code
    type: Tool
  - url: https://github.com/anthropics/claude-code-action
    name: Claude Code GitHub Action
    type: Tool
  - url: https://github.com/anthropics/skills
    name: Public Skills repository
    type: Tool
  - url: https://github.com/anthropics/claude-cookbooks
    name: Claude Cookbooks
    type: CodeExamples
  - url: https://github.com/anthropics/courses
    name: Anthropic Courses
    type: Courses
  - url: https://github.com/anthropics/prompt-eng-interactive-tutorial
    name: Prompt Engineering Interactive Tutorial
    type: Courses
  - url: https://github.com/anthropics/claude-plugins-official
    name: Official Claude Plugins
    type: Plugins
  - url: https://github.com/anthropics/financial-services
    name: Financial Services solutions
    type: CodeExamples
  - url: https://github.com/anthropics/claude-for-legal
    name: Claude for Legal
    type: CodeExamples
  - url: https://github.com/anthropics/knowledge-work-plugins
    name: Knowledge Work Plugins for Claude Cowork
    type: Plugins
  - url: https://www.anthropic.com/learn
    type: Training
  - url: https://discord.com/invite/6PPFFzqPDZ
    type: Forum
  - url: https://www.postman.com/postman/anthropic-apis/overview
    name: Postman Workspace
    type: Documentation
  - url: https://docs.anthropic.com/en/docs/build-with-claude/token-counting
    type: Documentation
  - url: https://docs.anthropic.com/en/docs/build-with-claude/data-residency
    type: Documentation
  - url: https://docs.anthropic.com/en/api/messages-streaming
    type: Documentation
  - url: https://docs.anthropic.com/en/docs/agents-and-tools/tool-use/overview
    type: Documentation
  - url: https://docs.anthropic.com/en/docs/agents-and-tools/computer-use
    type: Documentation
  - url: https://docs.anthropic.com/en/docs/build-with-claude/extended-thinking
    type: Documentation
  - url: https://docs.anthropic.com/en/docs/build-with-claude/citations
    type: Documentation
  - url: https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching
    type: Documentation
  - url: https://docs.anthropic.com/en/docs/build-with-claude/batch-processing
    type: Documentation
  - url: https://docs.anthropic.com/en/build-with-claude/compaction
    type: Documentation
  - url: https://docs.anthropic.com/en/agents-and-tools/agent-skills/overview
    type: Documentation
  - url: https://docs.anthropic.com/en/agents-and-tools/tool-use/memory-tool
    type: Documentation
  - url: https://docs.anthropic.com/en/api/openai-sdk
    type: Documentation
  - url: https://docs.anthropic.com/en/api/claude-on-amazon-bedrock
    type: Documentation
  - url: https://docs.anthropic.com/en/api/claude-on-vertex-ai
    type: Documentation
  - url: https://docs.anthropic.com/en/build-with-claude/claude-platform-on-aws
    type: Documentation
  - url: https://docs.anthropic.com/en/build-with-claude/claude-in-microsoft-foundry
    type: Documentation
  - url: https://docs.anthropic.com/en/docs/about-claude/models/all-models
    type: Models
  - url: https://docs.anthropic.com/en/docs/claude-code/sdk
    name: Claude Code SDK
    type: SDK
  - url: https://docs.anthropic.com/en/api/sdks/cli
    name: ant CLI
    type: SDK
  - url: https://modelcontextprotocol.io
    name: Model Context Protocol
    type: Documentation
  - url: https://github.com/modelcontextprotocol
    name: Model Context Protocol GitHub
    type: GitHubOrganization
  - url: https://docs.anthropic.com/en/docs/build-with-claude/structured-output
    type: Documentation
  - url: https://docs.anthropic.com/en/docs/build-with-claude/prompt-engineering/overview
    type: Documentation
  - type: Portal
    url: https://www.anthropic.com
  - type: Documentation
    url: https://docs.anthropic.com/
  - type: Documentation
    url: https://platform.claude.com/docs/
  - type: GettingStarted
    url: https://docs.anthropic.com/en/api/getting-started
  - url: https://plans/anthropic-plans-pricing.yml
    type: Plans
  - url: https://rate-limits/anthropic-rate-limits.yml
    type: RateLimits
  - url: https://finops/anthropic-finops.yml
    type: FinOps
  - type: Features
    data:
      - Claude Opus 4.7 — most capable generally available model for complex reasoning and agentic coding
      - Claude Sonnet 4.6 — balanced model combining speed and intelligence with 1M context window
      - Claude Haiku 4.5 — fastest model with near-frontier intelligence
      - Messages API with text, vision, tool use, extended thinking, streaming, structured outputs
      - >-
        Prompt caching with automatic and manual breakpoints, 5-minute and 1-hour TTLs, cache reads at 10% of input
        price
      - Server-side compaction API for effectively infinite conversations on Opus 4.6/4.7 and Sonnet 4.6
      - Memory tool (client-side) for cross-conversation persistence with ZDR support
      - Message Batches API with 50% discount on both input and output tokens
      - Files API for upload-once / reuse-many content across Messages and Managed Agents
      - Agent Skills API (beta) — packaged domain expertise with progressive disclosure
      - Claude Managed Agents (beta) — Agents, Sessions, Environments with SSE streaming and managed sandboxes
      - Web Search tool ($10/1,000 searches) and Web Fetch tool (free)
      - Code Execution tool — Python + Bash + filesystem in sandbox; 1,550 free container-hours/month
      - Computer Use tool for browser and desktop automation (beta)
      - Advisor tool (beta) for pairing executor and high-intelligence advisor models
      - Tool Search tool and Programmatic Tool Calling
      - Token-bucket rate limiting with cache-aware ITPM (cache reads excluded on most models)
      - Five usage tiers (Tier 1-4 plus Monthly Invoicing) with automatic advancement
      - Usage & Cost Admin API and Claude Code Analytics Admin API for FinOps reporting
      - Rate Limits API for programmatic limit inspection
      - Workload Identity Federation for short-lived bearer tokens
      - Data residency controls (US-only inference at 1.1x pricing for models after Feb 2026)
      - Available via Claude API, Claude Platform on AWS, Microsoft Foundry, AWS Bedrock, and Google Vertex AI
      - Official SDKs: Python, TypeScript, Java, Go, Ruby, C#, PHP plus the `ant` CLI
      - Claude Code (terminal agent) and Claude Code GitHub Action
      - Open MCP specification stewardship via modelcontextprotocol.io
    sources:
      - https://www.anthropic.com/pricing
      - https://platform.claude.com/docs/en/api/overview
      - https://platform.claude.com/docs/en/about-claude/models/all-models
      - https://platform.claude.com/docs/en/api/rate-limits
      - https://platform.claude.com/docs/en/release-notes/api
      - https://platform.claude.com/docs/en/managed-agents/overview
    updated: '2026-05-22'
created: '2025-08-14T00:00:00.000Z'
modified: '2026-05-29'
position: Consuming
description: >-
  Anthropic is an AI safety company and creator of the Claude family of large language models (Opus, Sonnet, Haiku). The
  Claude API provides access to Claude models for text generation, vision, tool use, extended thinking, batch
  processing, and agentic workflows including managed agents, skills, memory, compaction, and 

# --- truncated at 32 KB (32 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/anthropic/refs/heads/main/apis.yml