All models

ClaudeAnthropicClosed weights

Claude Haiku 4.5.

Claude Haiku 4.5 is the compact Claude model for real-time and high-volume applications where speed and latency count. It supports extended thinking with adjustable reasoning depth and tool calls for code, shell, web search and computer use.

Get started → Providers and prices

base_url="https://api.noirdoc.de/v1" model="claude-haiku-4-5"

  • Data centres in the EU
  • § 203 confidentiality
  • Zero retention
  • List prices

Details.

Where the model runs, which rules apply and what it can do.

  1. Data centres in the EU Google Vertex Contracting party: Google Cloud EMEA Limited · based in Dublin, Ireland
§ 203 German Criminal Code (StGB)
Confidentiality agreed with Google Vertex
Weights
Closed weights
Features
Tools, Vision, Reasoning and JSON
See how this looks in your account →
Map: Claude Haiku 4.5 runs in data centres in the EU (Google Vertex).

Providers.

We offer Claude Haiku 4.5 through these providers.

Provider § 203 model=
€ · 1M tokens Input Cache Read Cache Write Output
Anthropic EU EU data residency via Google Vertex
§ 203 agreed
claude-haiku-4-5
Input 1.00 Cache Read 0.10 Cache Write 1.25 Output 5.00

More models.

Anthropic develops the Claude models in the Opus, Sonnet and Haiku tiers. They are known for long-running agents and code.

All Claude models →
Model
€ · 1M tokens Input Cache Read Cache Write Output
Claude Opus 5.5 Tools Vision Reasoning JSON Opus-class Claude model for demanding reasoning — long-running agents, code review and multi-step changes across large codebases. Anthropic Logo Anthropic · EU
Input 3.93 Cache Read 0.20 Cache Write 4.92 Output 19.67
Claude Sonnet 5.5 Tools Vision Reasoning JSON Sonnet-class Claude model for well-defined everyday work — features, bug fixes, documents, presentations and spreadsheets. Anthropic Logo Anthropic · EU
Input 1.97 Cache Read 0.20 Cache Write 4.46 Output 9.83

Get started.

Test selected models right away with €5 starter credit — every model from the first top-up. If you have questions first, talk to our sales team.

Sign in →
python · openai sdk api.noirdoc.de/v1 
import os
from openai import OpenAI

client = OpenAI(
    # one line, that's all
    base_url="https://api.noirdoc.de/v1",
    api_key=os.environ["NOIRDOC_API_KEY"],
)

response = client.chat.completions.create(
    model="claude-haiku-4-5",  # provider & model
    messages=[{"role": "user", "content": "Hello"}],
)