Models
SauerkrautLM-decision API
Hosted access to the SauerkrautLM decision models through the VAGO API. Send text and images with typed questions, get calibrated probabilities back.
The SauerkrautLM-decision API gives hosted access to VAGO's decision models at api.sauerkrautlm.de. You send an input (the state), optional images and one or more typed questions; the API returns one structured answer per question as probabilities, with zero generated tokens. To run the open-weight model yourself instead, see SauerkrautLM-decision.
No GPU to manage
VAGO hosts and scales the models. You call one endpoint.
Text and images
Evaluate text, JSON and images together in the same request.
Pay for input only
Billed per million input tokens. Output is always zero tokens and free.
Models
Choose the hosted model with the model field. Both models share the same endpoint, question types and response format.
| Model | Inputs | Description |
|---|---|---|
sauerkrautlm-decision-small | Text, images | Default hosted model. Fast and low-cost for high-volume routing and classification. TODO: placeholder ID |
sauerkrautlm-decision-large | Text, images | Larger model for harder or more nuanced decisions. TODO: placeholder ID |
The examples below use sauerkrautlm-decision-small. Switch to sauerkrautlm-decision-large for harder decisions.
Pricing
You pay only for input tokens. Output is always zero tokens and is not billed. Each question is billed for its own text plus all images in the request.
| Model | Price per 1M input tokens | Output |
|---|---|---|
sauerkrautlm-decision-small | €0.10 (TODO: placeholder price) | Free |
sauerkrautlm-decision-large | €0.40 (TODO: placeholder price) | Free |
TODO: link to the VAGO pricing page and any free credits.
Setup
- Sign in to the VAGO console at console.sauerkrautlm.de.
- Create an API key. TODO: menu path. Keys start with
vago_. - Store the key in an environment variable:
export VAGO_API_KEY="vago_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"Your first call
A request has these fields:
| Field | Description |
|---|---|
model | Which hosted decision model to use. |
state | The input to evaluate: plain text, or a JSON object with structured fields. |
questions | Named questions. Each has a type (noul, choice or score), instructions, and for Choice and Score, criteria. |
images | Optional. Images to evaluate with the state. See Image inputs. |
Endpoint: POST https://api.sauerkrautlm.de/v1/systemone
curl -s https://api.sauerkrautlm.de/v1/systemone \
-H "Authorization: Bearer $VAGO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "sauerkrautlm-decision-small",
"state": "Ich warte seit drei Wochen auf meine Bestellung und niemand antwortet auf meine E-Mails.",
"questions": {
"is_complaint": {
"type": "noul",
"instructions": "Is this message a complaint?"
}
}
}'import os
import requests
response = requests.post(
"https://api.sauerkrautlm.de/v1/systemone",
headers={"Authorization": f"Bearer {os.environ['VAGO_API_KEY']}"},
json={
"model": "sauerkrautlm-decision-small",
"state": "Ich warte seit drei Wochen auf meine Bestellung und niemand antwortet auf meine E-Mails.",
"questions": {
"is_complaint": {
"type": "noul",
"instructions": "Is this message a complaint?",
}
},
},
timeout=30,
)
response.raise_for_status()
result = response.json()
print(result["answers"]["is_complaint"]["noul"])Response:
{
"model": "sauerkrautlm-decision-small",
"answers": {
"is_complaint": {
"type": "noul",
"noul": 0.97
}
},
"usage": {
"input_tokens": 61,
"output_tokens": 0
}
}The numbers above are illustrative, not measured.
answers.<name>: one answer per question, keyed by the question name.usage.input_tokens: total input tokens for all questions, including image tokens.usage.output_tokens: always0. Decision models do not generate tokens.
Question types
Type noul. Returns one probability between 0 and 1 that the answer is "yes". Threshold it, use it as a weight, or pass it on.
"is_harmful": {
"type": "noul",
"instructions": "Does this message contain threatening or abusive content?"
}Answer:
"is_harmful": { "type": "noul", "noul": 0.98 }Type choice. Picks one option and returns the probability of every option plus a confidence value, so you can spot close calls.
"intent": {
"type": "choice",
"instructions": "What is this customer inquiry mainly about?",
"criteria": {
"billing": "Charges, invoices, refunds, payment methods",
"technical": "Bugs or how-to questions about the product",
"shipping": "Order status, delivery, address changes"
}
}Answer:
"intent": {
"type": "choice",
"choice": "billing",
"probabilities": { "billing": 0.95, "technical": 0.03, "shipping": 0.02 },
"confidence": 0.93
}Type score. Places the input on an ordered scale you define, from level 0 upward, and returns the probability-weighted position, the distribution per level, and a legend mapping each level to your criteria.
"urgency": {
"type": "score",
"instructions": "How urgent is this support request?",
"criteria": [
"Can wait: no business impact",
"Handle today: minor, non-blocking issue",
"Blocking: customers or revenue affected now"
]
}Answer:
"urgency": {
"type": "score",
"score": 1.9,
"confidence": 0.9,
"probabilities": { "0": 0.02, "1": 0.06, "2": 0.92 },
"legend": {
"0": "Can wait: no business impact",
"1": "Handle today: minor, non-blocking issue",
"2": "Blocking: customers or revenue affected now"
}
}All answer values on this page are illustrative.
Combining questions
Ask a Yes/No, a Choice and a Score question in the same request to classify, route and prioritise one input in a single round trip:
answers = result["answers"]
is_bug = answers["is_bug"]["noul"] > 0.7
team = answers["team"]["choice"]
urgency = answers["urgency"]["score"]
if is_bug and urgency > 1.5:
print(f"Escalate to {team} on-call")
elif answers["team"]["confidence"] < 0.5:
print("Routing unclear: send to triage")
else:
print(f"Queue in {team}")Thresholds here are examples. Tune them on your own data.
Image inputs
Both hosted models accept images. Add an images array next to model, state and questions; question types and the response format stay the same. Every question sees every image, in the order given, so refer to images by position ("the first image", "the second image").
Each image is either a Base64 data URL or an object with content_type and base64. Remote image URLs are not accepted: download and encode the file first.
IMAGE_BASE64=$(base64 < board.jpg | tr -d '\r\n')
curl -s https://api.sauerkrautlm.de/v1/systemone \
-H "Authorization: Bearer $VAGO_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<JSON
{
"model": "sauerkrautlm-decision-small",
"state": "Kamerabild einer Leiterplatte aus der Fertigungslinie.",
"images": ["data:image/jpeg;base64,$IMAGE_BASE64"],
"questions": {
"defect": {
"type": "noul",
"instructions": "Does this circuit board have a visible defect?"
}
}
}
JSONimport base64
import os
import requests
with open("board.jpg", "rb") as f:
image = base64.b64encode(f.read()).decode("ascii")
response = requests.post(
"https://api.sauerkrautlm.de/v1/systemone",
headers={"Authorization": f"Bearer {os.environ['VAGO_API_KEY']}"},
json={
"model": "sauerkrautlm-decision-small",
"state": "Kamerabild einer Leiterplatte aus der Fertigungslinie.",
"images": [{"content_type": "image/jpeg", "base64": image}],
"questions": {
"defect": {
"type": "noul",
"instructions": "Does this circuit board have a visible defect?",
}
},
},
timeout=60,
)
response.raise_for_status()
print(response.json()["answers"]["defect"]["noul"])Image tokens count toward usage.input_tokens and are billed at the model's input rate, once per question. TODO: image token formula, supported formats, maximum images per request and maximum request size.
Errors and limits
TODO: error response format and status codes, rate limits, maximum request size and maximum number of questions per request.