SAIA Plattform

curl -i -X POST \
  --url https://chat-ai.academiccloud.de/v1/chat/completions \
  --header 'Accept: application/json' \
  --header 'Authorization: Bearer <api_key>' \
  --header 'Content-Type: application/json'\
  --data '{
  "model": "meta-llama-3.1-8b-instruct",
  "messages":[{"role":"system","content":"You are an assistant."},{"role":"user","content":"What is the weather today?"}],
  "max_tokens": 7,
  "temperature": 0.5,
  "top_p": 0.5
}'

curl -X POST \
  --url https://chat-ai.academiccloud.de/v1/models \
  --header 'Accept: application/json' \
  --header 'Authorization: Bearer <api_key>' \
  --header 'Content-Type: application/json'

curl -i -N -X POST \
  --url https://chat-ai.academiccloud.de/v1/chat/completions \
  --header 'Accept: application/json' \
  --header 'Authorization: Bearer <api_key>' \
  --header 'Content-Type: application/json'\
  --data '{
  "model": "meta-llama-3.1-8b-instruct",
  "messages": [{"role":"system","content":"You are a helpful assistant"},{"role":"user","content":"How tall is the Eiffel tower?"},{"role":"assistant","content":"The Eiffel Tower stands at a height of 324 meters (1,063 feet) above ground level. However, if you include the radio antenna on top, the total height is 330 meters (1,083 feet)."},{"role":"user","content":"Are there restaurants?"}],
  "temperature": 0
}'

from openai import OpenAI

# API-Konfiguration
api_key = '<api_key>' # Ersetzen Sie dies durch Ihren API-Schlüssel
base_url = "https://chat-ai.academiccloud.de/v1"
model = "meta-llama-3.1-8b-instruct" # Wählen Sie ein verfügbares Modell

# Starten des OpenAI-Clients
client = OpenAI(
    api_key=api_key,
    base_url=base_url
)

# Abrufen der Antwort
chat_completion = client.chat.completions.create(
    messages=[
        {"role": "system", "content": "You are a helpful assistant"},
        {"role": "user", "content": "How tall is the Eiffel tower?"},
        {"role": "assistant", "content": "The Eiffel Tower stands at a height of 324 meters (1,063 feet) above ground level. However, if you include the radio antenna on top, the total height is 330 meters (1,083 feet)."},
        {"role": "user", "content": "Are there restaurants?"}
    ],
    model=model,
)

# Vollständige Antwort als JSON ausgeben
print(chat_completion) # Sie können den Antworttext aus dem JSON-Objekt extrahieren

from openai import OpenAI

# API-Konfiguration
api_key = '<api_key>' # Ersetzen Sie dies durch Ihren API-Schlüssel
base_url = "https://chat-ai.academiccloud.de/v1"
model = "meta-llama-3.1-8b-instruct" # Wählen Sie ein verfügbares Modell

# Starten des OpenAI-Clients
client = OpenAI(
    api_key=api_key,
    base_url=base_url
)

# Stream starten
stream = client.chat.completions.create(
    messages=[
        {
            "role": "user",
            "content": "Name the capital city of each country on earth, and describe its main attraction",
        }
    ],
    model=model,
    stream=True
)

# Antwort ausgeben
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")

import base64
from openai import OpenAI

# API-Konfiguration
api_key = '<api_key>' # Ersetzen Sie dies durch Ihren API-Schlüssel
base_url = "https://chat-ai.academiccloud.de/v1"
model = "internvl3.5-30b-a3b" # Wählen Sie ein verfügbares Modell

# Starten des OpenAI-Clients
client = OpenAI(
    api_key=api_key,
    base_url=base_url,
)

# Funktion zum Codieren des Bildes
def encode_image(image_path):
  with open(image_path, "rb") as image_file:
    return base64.b64encode(image_file.read()).decode('utf-8')

# Pfad zu Ihrem Bild
image_path = "test-image.png"

# Abrufen der Base64-Zeichenkette
base64_image = encode_image(image_path)

response = client.chat.completions.create(
  model=model,
  messages=[
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "What is in this image?",
        },
        {
          "type": "image_url",
          "image_url": {
            "url": f"data:image/jpeg;base64,{base64_image}"
          },
        },
      ],
    }
  ],
)
print(response.choices[0])

curl -i -N -X POST \
  --url https://chat-ai.academiccloud.de/v1/images/generations \
  --header 'Accept: application/json' \
  --header 'Authorization: Bearer <key>' \
  --header 'Content-Type: application/json' \
  --data '{
    "prompt": "flower",
    "response_format": "b64_json",
    "model": "flux",
    "size": "1024x1024",
    "n": 1,
    "quality": "standard"
}'

curl https://chat-ai.academiccloud.de/v1/images/edits/ \
 -H "Authorization: Bearer <key>" \
 -H "Content-Type: multipart/form-data" \
 -H "inference-service: image-edit-2511" \
 -F "prompt=make style to Van-Gogh" \
 -F "image=@./<img.png or jpg>" \
 -o "edited_output.png"

curl -i 'https://saia.gwdg.de/v1/audio/<translations or transcriptions>' \
  --header 'Accept: /' \
  --header 'Authorization: Bearer <key>' \
  -H "Content-Type: multipart/form-data"\
  -F model="whisper-large-v2" \
  -F "file=@./<voice.wav, mp4, mp3 or flac>" \
  -F response_format=<vtt or text or srt>

curl https://chat-ai.academiccloud.de/v1/embeddings \
  -H "Authorization: Bearer <api_key>" \
  -H "Content-Type: application/json" \
  -d '{
    "input": "The food was delicious and the waiter...",
    "model": "e5-mistral-7b-instruct",
    "encoding_format": "float"
  }'

curl -i -X POST \
  --url https://chat-ai.academiccloud.de/v1/chat/completions \
  --header 'Accept: application/json' \
  --header 'Authorization: Bearer <api_key>' \
  --header 'Content-Type: application/json'\
  --header 'inference-service: saia-openai-gateway'\
  --data '{
    "model": "qwen3-30b-a3b-instruct-2507",
    "messages":[{"role":"system","content":"You are an assistant."},{"role":"user","content":"What is Chat-Ai?"}],
    "enable-tools": true,
    "arcana" : {
      "id": "<the Arcana ID>"
    },
    "temperature": 0.0,
    "top_p": 0.05
  }'

https://chat-ai.academiccloud.de/v1/documents

curl -X POST "https://chat-ai.academiccloud.de/v1/documents/convert" \
    -H "accept: application/json" \
    -H 'Authorization: Bearer <api_key>' \
    -H "Content-Type: multipart/form-data" \
    -F "document=@/path/to/your/file.pdf"

{
  "response_type": "MARKDOWN",
  "filename": "example_document",
  "images": [
    {
      "type": "picture",
      "filename": "image1.png",
      "image": "data:image/png;base64, xxxxxxx..."
    },
    {
      "type": "table",
      "filename": "table1.png",
      "image": "data:image/png;base64, xxxxxxx..."
    }
  ],
  "markdown": "#Your Markdown File",
}

curl -X POST "https://chat-ai.academiccloud.de/v1/documents/convert" \
    -H "accept: application/json" \
    -H 'Authorization: Bearer <api_key>' \
    -H "Content-Type: multipart/form-data" \
    -F "document=@/path/to/your/file.pdf" \
    | jq -r '.markdown' \
    > output.md

https://chat-ai.academiccloud.de/v1/documents/convert?response_type=json&extract_tables_as_images=false&image_resolution_scale=4

{
  "response_type": "HTML",
  "filename": "example_document",
  "images": [
    ...
  ],
  "html": "#Your HTML data",
}

curl -i -H "Authorization: Bearer <your-API-Key>" \
     -H "Content-Type: application/json" \
     https://saia.gwdg.de/v1/chat/completions

HTTP/2 400
content-type: application/json
content-length: 43
x-ratelimit-limit-minute: 1000
x-ratelimit-limit-hour: 10000
x-ratelimit-limit-day: 50002
x-ratelimit-remaining-minute: 999
x-ratelimit-remaining-hour: 9999
x-ratelimit-remaining-day: 50001
ratelimit-limit: 1000
ratelimit-remaining: 999
ratelimit-reset: 1
date: Mon, 20 Oct 2025 10:13:58 GMT
server: uvicorn
via: kong/3.6.1

@article{doosthosseini_saia_2026,
    title = {{SAIA}: a seamless {Slurm}-native solution for {HPC}-based services},
    volume = {82},
    issn = {1573-0484},
    url = {https://doi.org/10.1007/s11227-026-08508-3},
    doi = {10.1007/s11227-026-08508-3},
    number = {7},
    journal = {The Journal of Supercomputing},
    author = {Doosthosseini, Ali and Decker, Jonathan and Nolte, Hendrik and Kunkel, Julian},
    month = may,
    year = {2026},
    pages = {403},
}