Skip to main content
The VLM Run API enables you to run production-ready multimodal models. Use it to ETL data from PDFs, generate images, summarize videos, and more.
  • Base URL: https://api.vlm.run/v1
  • Authentication: Authorization: Bearer <VLMRUN_API_KEY>
  • Models Supported: vlm-1
Access your API keys in our dashboard.

​
Example Request

from pathlib import Path
from vlmrun.client import VLMRun
from vlmrun.client.types import PredictionResponse

# Initialize the client
client = VLMRun(api_key="<VLMRUN_API_KEY>", base_url="https://api.vlm.run/v1")

# Process a document
response: PredictionResponse = client.document.generate(
    file=Path("path/to/document.pdf"),
    model="vlm-1",
    domain="document.markdown",
)