- Base URL:
https://api.vlm.run/v1 - Authentication:
Authorization: Bearer <VLMRUN_API_KEY> - Agents Supported:
vlmrun-orion-2: Our second-generation visual agent. It adds code execution, and is faster, cheaper, and more capable, with high reliability and repeatability.vlmrun-orion-1: Our first visual agent (November 2025). It sees, reasons, and acts with detection, segmentation, and specialized document OCR VLMs.
- Variants:
fast,auto, andpro, for examplevlmrun-orion-2:auto.
Need OCR, VQA, or detection models?
Call them through the Gateway: one OpenAI-compatible API and one key for every visual model. This reference covers the Orion agents.
Chat Completions & Agent Executions
Use the Chat Completions endpoint for interactive multi-modal conversations, or the Agent Executions endpoint for batch execution workflows.Next steps
Orion Introduction
What the agents are, and which one to pick.
Chat Completions
Send a multi-modal conversation to an agent.
Execute Agent
Run a saved agent on a file and poll for the result.
Upload File
Upload media once and reuse it by file ID.
Skills
Reusable, domain-specific skills for your agents.
Gateway
OCR, VQA, detection, and segmentation models behind one API.
Legacy API
Looking for thevlm-1 API? Click here.