Skip to main content
An OpenAI-compatible API for visual AI: OCR, VQA, document extraction, and text detection, all behind one base URL and one Authorization header. See Introduction for the full rationale.
General-purpose routers are built for text and carry lots of LLMs, but only a small slice of visual workloads. The VLM Run Gateway is built for OCR and VQA, and exposes each supported model through the same chat.completions shape so switching models is a one-line change.
Yes. Pass a PDF as a document_url content part and the Gateway decodes it, fans out per-page inference, and returns concatenated markdown or streamed page blocks through the same chat completions response. See Flexible Document OCR for the full walkthrough, including the method and document_dpi knobs for tuning cost, latency, and accuracy per request.
Yes, behind the same base URL and API key as chat completions. See Embeddings and Audio Transcriptions for request schemas, or Models for the models that back each endpoint.
The Gateway is free during the alpha, subject to per-tier rate limits. Formal pricing (per-request and per-page) is coming; until then, watch usage.cost on chat completion responses for a per-request cost signal. See Pricing and Rate Limits.
Not to start. Every endpoint accepts anonymous access today, rate limited per IP. Authenticate with an API key from app.vlm.run to get usage attributed to your account instead of a shared IP bucket, which matters once you’re building something you plan to run in production. See Authentication.
The Gateway is in alpha: free, rate-limited, and the model catalog is intentionally small. It already returns a live model catalog, per-request usage.cost for metering, x-request-id for tracing, and sanitized error responses. Authenticate with an API key if you’re building something you plan to run in production, since alpha limits are subject to change.
Use qwen/qwen3.5-0.8b for VQA and paddleocr/pp-ocrv6 for OCR or text detection. zai-org/glm-ocr and rednote-hilab/dots.mocr are markdown-output OCR alternatives when you want reading-order page output. Within pp-ocrv6, start with method: "ocr" for full OCR, or method: "detect" when you only need bounding polygons. For documents, treat model, method, and document_dpi as one tunable unit: start with the cheapest combination that clears your accuracy bar on your own data, and only pay for more where it actually moves the numbers.

Introduction

Why the VLM Run Gateway exists and what it’s built to help you do.

Models

Full catalog with availability, methods, and accepted inputs.

Methods

Per-model method reference and request parameters.

Quickstart

First requests for VQA and document OCR.