We're excited to introduce VLM Run Gateway - a new unified API for running open-weight VLMs, OCR VLMs and ViT-based vision models. Full model catalog
The motivation was mostly frustration when running these models in production and discovering all the details around serving VLMs, especially around visual accuracy.
A few footguns we kept running into:
quantized models served under the same name (this one still drives me nuts): providers often serve models with different quants, environments, vLLM/SGLang serving params with the same model-id. Vision is especially sensitive to this; some quants that look fine on text benchmarks noticeably hurt OCR/small-text/spatial accuracy.
video performance is varied: when we tested with popular routers on video-native VLMs, more than 80% of providers didn't support video inputs, and even fewer let you control FPS. If you care for time-resolution in videos, none of these providers work even if the models themselves are capable of it.
