https://vo.rs/tags/api-gateway/Latest from the Api-Gateway desk at vo.rs.Hugo -- gohugo.ioenThis work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.Tue, 09 Sep 2025 10:00:00 +0000https://vo.rs/story/litellm-one-api-gateway-for-every-model/<p>Somewhere around my fourth self-hosted model backend, I noticed every one of my scripts had a slightly different way of talking to it. The <a href="https://vo.rs/story/local-ai-on-your-own-metal-running-llms-with-ollama/">Ollama</a> box used its native API for one script and the OpenAI-compat shim for another. The <a href="https://vo.rs/story/vllm-serving-local-models-fast-enough-to-use/">vLLM</a> server took a different base URL and a different model-name format. And two of my tools still called out to a cloud provider directly whenever the local box was overloaded, with their own hard-coded API key sitting in a config file I kept forgetting was there. None of this was hard, individually. Collectively, it was the kind of accumulated friction that means you stop experimenting because switching backends is annoying.</p>Tue, 09 Sep 2025 10:00:00 +0000