Classify 6700 pages for $1 with a Jev-compatible VLM API

VLM Run launched a Jev-compatible vision-language model API in its gateway that classifies documents at $1 per 6,700+ pages, with the full 1,651-page OmniDocBench run costing 25 cents. The API reads pages as pixels without an OCR-to-LLM pipeline and returns one typed, calibrated decision per page at roughly 180ms p50 end-to-end latency. Sign-up and trial of the gateway are free.

You can now classify documents with open-weight VLMs at ultra-low cost with our @typesafeai https://twitter.com/typesafeai Jev-compatible API in the @vlmrun https://twitter.com/vlmrun gateway $1 buys you 6700+ pages, and the full 1,651-page OmniDocBench run cost 25 cents. It reads the page as pixels no OCR- LLM hacks and hands back one typed, calibrated decision per page - ~180ms p50 e2e. Jev really opened developers' eyes to re-thinking how we process data at the cost-pareto front. A week later we're bringing that to our APIs with vision as a first-class citizen. Try our gateway today - free to sign-up and try 00:00