client.gateway

pip install "vlmrun[openai]"

from vlmrun.client import VLMRun

client = VLMRun(api_key="<VLMRUN_API_KEY>")

response = client.gateway.completions.create(
    model="paddleocr/pp-ocrv6",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "document_url",
                    "document_url": {
                        "url": "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/finance.sec-filings/tsla-8k.pdf"
                    },
                }
            ],
        }
    ],
    extra_body={"method": "ocr", "document_dpi": 96},
)

print(response.choices[0].message.content)

response = client.gateway.completions.create(
    model="qwen/qwen3.5-0.8b",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What is happening in this image?"},
                {"type": "image_url", "image_url": {"url": "https://example.com/image.jpg"}},
            ],
        }
    ],
)

print(response.choices[0].message.content)

stream = client.gateway.completions.create(
    model="zai-org/glm-ocr",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "document_url", "document_url": {"url": "https://example.com/doc.pdf"}},
            ],
        }
    ],
    stream=True,
)

for chunk in stream:
    delta = chunk.choices[0].delta.content
    if delta:
        print(delta, end="", flush=True)

response = client.gateway.embeddings.create(
    model="qwen/qwen3-vl-embedding-2b",
    input=[[{"type": "image_url", "image_url": {"url": "data:image/jpeg;base64,..."}}]],
)

print(len(response.data[0].embedding))

with open("clip.mp3", "rb") as fh:
    response = client.gateway.transcriptions.create(
        model="nvidia/parakeet-tdt-0.6b-v3",
        file=fh,
    )

print(response.text)

for model in client.gateway.models():
    print(model.id)

pip install "vlmrun[typesafe]"

result = client.gateway.systemone.decide(
    state="Invoice #44 was charged twice, I need this fixed today",
    questions=[
        {"id": "is_urgent", "type": "noul", "instructions": "Is this time-sensitive?"},
        {"id": "department", "type": "choice", "options": ["billing", "technical", "sales"]},
    ],
    images=["invoice-page.jpg"],  # optional: up to 8 images, or document="invoice.pdf"
)

result.nouls["is_urgent"].noul          # 0.91
result.choices["department"].choice     # "billing"

from vlmrun.common.video import VideoReader

with client.gateway.systemone.stream(
    questions=[{"id": "is_open", "type": "noul", "instructions": "Is the door open?"}],
    state="Is the door open?",
) as stream, VideoReader("door.mp4") as video:
    for decision in stream.map(video.frames(fps=2)):
        print(decision.timestamp_s, decision.response.nouls["is_open"].noul)

if client.gateway.health():
    print("Gateway is healthy")

export VLMRUN_GATEWAY_BASE_URL="https://gateway.vlm.run/v1"