# Anthrophic Claude API Docs

## Kurzbeschreibung
**Anthropic** offers current LLMs via the Claude API for language processing, reasoning, coding, agentic workflows, tool use, and document-centric tasks. According to the official model overview, all current Claude models support text and image input, text output, multilingual capabilities, and vision. For direct API access, Anthropic refers users to the Messages API; in addition, there are Managed Agents for longer-running tasks.

## Claim
LLM “highly performant, trustworthy, and intelligent AI platform”

## Geeignet für
- API Integration
- Automation / Workflows
- Education
- Data Analysis
- Data Extraction / Document Analysis
- Customer Service & Chatbots
- Programming / Software Development
- Research
- Writing & Editing
- Texts / Content
- Knowledge Management / Internal Search

## Kernfunktionen
- Document Analysis
- Function Calling
- AI Agents
- LLM API
- Multimodal AI
- Programming
- Reasoning Model
- Language Model
- Text Generation

## Preismodell
- **free:** Anthropic documents that new users receive a small amount of free credits to test the API. However, this is not a classic permanent free plan in the SaaS sense, but rather a trial credit.
- **other:** **Token-based Claude API** Billing by model family such as Opus, Sonnet, and Haiku, as well as input, output, cache-write, and cache-read tokens.


**Prompt Caching** Reuse of large prompts, system instructions, or document contexts to reduce costs and latency.
**Batch API** Asynchronous processing of large request volumes with a reduced billing model.


**Long Context / 1M Context** Available for certain current models; suitable for very large documents, codebases, and analysis contexts.


**Data Residency / Third-Party Platforms** Claude is also available via AWS Bedrock, Google Vertex AI, and Microsoft Foundry; regional pricing and data handling depend on the respective platform.

## DSGVO und Datenschutz
**Gesamteinschätzung:** Conditional

**Overall assessment of hosting & data: **

The Claude API is a managed cloud API service for language, reasoning, analysis, coding, vision, tool use, structured outputs, prompt caching, batch processing, and long contexts. On-premises hosting of Claude models is not publicly documented as a standard option; however, Claude models are also available via AWS Bedrock, Google Vertex AI, and Microsoft Foundry, enabling regional cloud architectures depending on the platform. Positives include strong model quality, long context windows, API features for tools and agents, 30-day standard deletion for API inputs/outputs, no training on commercial data by default, and ZDR options. Critical concerns remain around US storage for the 1P Claude API, global standard routing logic, feature dependencies, and potentially longer retention in safety/policy cases. 


**Conclusion: **

Claude is very well suited for demanding text, analysis, coding, and agent workflows; for EU-regulated data, DPA, ZDR, storage/routing questions, and, if applicable, Bedrock/Vertex/Foundry deployment should be reviewed.


[Privacy Policy](https://www.anthropic.com/legal/privacy) [Usage Policy](https://www.anthropic.com/legal/aup)

**Anthropic** provides a DPA with SCCs for commercial/API customers; according to the Privacy Center, this is automatically incorporated into the Commercial Terms. 


For commercial services, Anthropic generally acts as a Processor on behalf of the customer according to the Privacy Center, and according to the Commercial Terms, Anthropic may not use Customer Content from the services for model training. In addition, according to the Privacy Center, inputs/outputs from commercial products such as the Anthropic API are not used for training by default, except, for example, in cases of explicit feedback/opt-in. 


Also **positive** is the documented standard retention: for API users, inputs/outputs are deleted within 30 days according to the Privacy Center, unless, for example, the Files API, a different agreement, or ZDR applies. At the same time, the Privacy Policy mentions transfers to the USA or outside the EEA/UK for controller-side processing and refers to Adequacy Decisions or Standard Contractual Clauses. 


For the direct **Claude API**, ZDR-capable features are also documented; the API documentation mentions Data Residency/inference geo-steering, though publicly, in the direct API context, mainly global or US-only. Broader regional routing/residency options are described primarily for AWS Bedrock, Vertex AI, and Microsoft Foundry. There is also a public subprocessor list as well as Trust Center artifacts for, among other things, SOC 2 and ISO 27001. 


This means **Claude** is well documented for GDPR scenarios, but not automatically fully handled “out of the box” in every setup; especially with regard to data localization, tool usage, retention, and platform choice, the specific use case should be reviewed.


[Privacy Policy](https://www.anthropic.com/legal/privacy) [Usage Policy](https://www.anthropic.com/legal/aup)

## Hosting und Daten
- **On-Prem / lokales Hosting:** unknown
- **Private Cloud / Rechenzentrum:** unknown
- **EU SaaS / Managed:** unknown
- **Hybrid:** teilweise / indirekt
- **AVV / DPA:** abgedeckt
- **Kein Training auf Kundendaten:** abgedeckt
- **Open-Source / Transparenz-Pfad:** teilweise / indirekt

## Standort
**Land:** USA

**Taxonomie:** USA

Anthropic, PBC, 548 Market Street, PMB 90375, San Francisco, CA 94104, USA

## Vorteile
- Very strong position in coding, agentic workflows, computer use, document understanding, and long contexts.
- Clear tiering by price/performance: Opus for maximum quality, Sonnet as the productive standard, Haiku for speed and volume.
- Strong business/privacy positioning: DPA, SCCs, Zero Data Retention for suitable APIs, documented retention rules.
- Useful API features such as prompt caching, batch, tools, structured control, and service tiers.

## Nachteile
- The directly most powerful model (Opus 4.7) is more expensive than necessary for many everyday workloads; Sonnet 4.6 or Haiku 4.5 is often more economical.
- The model portfolio is smaller than that of some competitors, but due to active and older snapshots that remain available, it still requires explanation.
- For strict regional requirements, the direct Claude API (1P) is publicly geared mainly toward global or US-only inference geo-control; broader regional options are available primarily on partner platforms such as Bedrock and Vertex.
- In the Commercial Terms, Anthropic explicitly states that factual statements in outputs should be independently verified before use.

## Quellen
- Offizielle Website: https://platform.claude.com/docs/it/about-claude/pricing

## Letzter Datenstand
2026-04-16

## Originalseite
https://kifox.ai/en/ki-tools/anthrophic-claude-api-docs-en/