JSON-Schema: deutsche Rechnung extrahieren
JSON Schema, um eine deutsche Rechnung mit einem LLM zu extrahieren: Rechnungssteller, USt-IdNr., Nummer, Datum, Positionen, Netto, USt und Brutto.
Extrahiere die Rechnungsdaten. Beträge sind Zahlen in Euro, ohne Währungszeichen. Fehlt eine Angabe, erfinde sie nicht.
JSON Schema
{
"type": "object",
"required": [
"rechnungssteller",
"rechnungsdatum",
"brutto"
],
"properties": {
"netto": {
"type": "number"
},
"brutto": {
"type": "number"
},
"ust_idnr": {
"type": "string",
"description": "Umsatzsteuer-Identifikationsnummer (DE…)"
},
"ust_satz": {
"type": "number",
"description": "Umsatzsteuersatz in Prozent (19 oder 7)"
},
"positionen": {
"type": "array",
"items": {
"type": "object",
"required": [
"bezeichnung",
"netto"
],
"properties": {
"menge": {
"type": "number"
},
"netto": {
"type": "number"
},
"bezeichnung": {
"type": "string"
}
}
}
},
"ust_betrag": {
"type": "number"
},
"rechnungsdatum": {
"type": "string",
"format": "date",
"description": "Ausstellungsdatum (JJJJ-MM-TT)"
},
"rechnungsnummer": {
"type": "string"
},
"rechnungssteller": {
"type": "string"
}
}
}Output example
{
"rechnungssteller": "Druckerei Weber GmbH",
"ust_idnr": "DE123456789",
"rechnungsnummer": "RE-2026-0412",
"rechnungsdatum": "2026-09-15",
"positionen": [
{
"bezeichnung": "Visitenkarten x500",
"menge": 1,
"netto": 80.0
},
{
"bezeichnung": "Flyer DIN A5 x1000",
"menge": 1,
"netto": 120.0
}
],
"netto": 200.0,
"ust_satz": 19,
"ust_betrag": 38.0,
"brutto": 238.0
}Estimated cost
Input tokens per call : ≈ 610
| Model | Per call | Per 1,000 calls |
|---|---|---|
| Mistral Large · Mistral AI | €0.00027 | €0.27 |
| DeepSeek Flash · DeepSeek | €0.00016 | €0.16 |
| DeepSeek V4 Pro · DeepSeek | €0.00071 | €0.71 |
| GPT-6 Luna · OpenAI | €0.00005 | €0.05 |
| GPT-6 Sol · OpenAI | €0.00107 | €1.07 |
| Claude Sonnet 5.5 · Anthropic | €0.00107 | €1.07 |
| Claude Opus 5.5 · Anthropic | €0.00215 | €2.15 |
| Self-hosted open-source model (Ollama, vLLM) | €0 in API fees (server cost only) | |
Input cost only, excluding the model's answer. Providers' public standard prices (Mistral AI, DeepSeek, OpenAI, Anthropic) converted from USD to euros at the ECB rate of September 29, 2026. Estimate: 1 token ≈ 3.6 characters.
Common to all 3 regions
Created by the author, no outside source.
Commercial use allowed · credit the author · changes allowed.
Text or data only: no access to files, network or commands.
Hosted in France (Scaleway, Paris). No transfer outside the EU.
European Union · 5/5
No personal data.
No training data: no summary required.
United States · 5/5
No personal data.
No training data: no documentation to publish.
China · 5/5
No personal data.
No training data; AI-generated content published in China must be labelled (2025).
Indicative summary as of 30/09/2026, not a legal certification. Method and sources →
Statistics
Likes : 0 · Comments : 0
Click a counter to show or hide it, hover the chart for details. One view per visitor per day, bots excluded; counting started on 30 September 2026.
- Identifier
- contextetech--deutsche-rechnung-extrahieren
- Type
- Output schemas
- File
- deutsche-rechnung-extrahieren.schema.json
- Format
- JSON (application/json)
- Size
- 1,141 bytes (1.1 KB)
- Encoding
- UTF-8
- Estimated tokens
- ≈ 316
- Language
- German
- License
- MIT
- Commercial use
- Allowed
- Personal data
- None
- Version
- 1.0
- Published on
- October 3, 2026 at 5:20 AM
- Updated on
- October 3, 2026 at 5:20 AM
- Storage
- in database
- Uses
- 0
- Likes
- 0
deutsche-rechnung-extrahieren.schema.json
{
"type": "object",
"required": [
"rechnungssteller",
"rechnungsdatum",
"brutto"
],
"properties": {
"netto": {
"type": "number"
},
"brutto": {
"type": "number"
},
"ust_idnr": {
"type": "string",
"description": "Umsatzsteuer-Identifikationsnummer (DE…)"
},
"ust_satz": {
"type": "number",
"description": "Umsatzsteuersatz in Prozent (19 oder 7)"
},
"positionen": {
"type": "array",
"items": {
"type": "object",
"required": [
"bezeichnung",
"netto"
],
"properties": {
"menge": {
"type": "number"
},
"netto": {
"type": "number"
},
"bezeichnung": {
"type": "string"
}
}
}
},
"ust_betrag": {
"type": "number"
},
"rechnungsdatum": {
"type": "string",
"format": "date",
"description": "Ausstellungsdatum (JJJJ-MM-TT)"
},
"rechnungsnummer": {
"type": "string"
},
"rechnungssteller": {
"type": "string"
}
}
}Anthropic API (Python)
import json, anthropic
schema = json.load(open("deutsche-rechnung-extrahieren.schema.json"))
client = anthropic.Anthropic()
resp = client.messages.create(model="claude-sonnet-5", max_tokens=1024,
tools=[{"name": "extraire", "description": "Renvoie les données extraites", "input_schema": schema}],
tool_choice={"type": "tool", "name": "extraire"},
messages=[{"role": "user", "content": "your input here"}])
print(resp.content[0].input)OpenAI format (response_format)
{
"type": "json_schema",
"json_schema": {
"name": "deutsche-rechnung-extrahieren",
"schema": {
"type": "object",
"required": [
"rechnungssteller",
"rechnungsdatum",
"brutto"
],
"properties": {
"netto": {
"type": "number"
},
"brutto": {
"type": "number"
},
"ust_idnr": {
"type": "string",
"description": "Umsatzsteuer-Identifikationsnummer (DE…)"
},
"ust_satz": {
"type": "number",
"description": "Umsatzsteuersatz in Prozent (19 oder 7)"
},
"positionen": {
"type": "array",
"items": {
"type": "object",
"required": [
"bezeichnung",
"netto"
],
"properties": {
"menge": {
"type": "number"
},
"netto": {
"type": "number"
},
"bezeichnung": {
"type": "string"
}
}
}
},
"ust_betrag": {
"type": "number"
},
"rechnungsdatum": {
"type": "string",
"format": "date",
"description": "Ausstellungsdatum (JJJJ-MM-TT)"
},
"rechnungsnummer": {
"type": "string"
},
"rechnungssteller": {
"type": "string"
}
}
},
"strict": true
}
}
Community
No comments yet. Share your feedback, it will help the next person.