# Serve Published articles for Serve. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## OpenRouter provider fallbacks can cause inconsistent model behavior DevFeed: [OpenRouter provider fallbacks can cause inconsistent model behavior]() Original publisher: [Read original article]() Author: Simon Willison Published: 2026-09-11T22:49:18Z Content type: opinion Language: en Sources: [Simon Willison's Weblog]() Topics: [API](), [Large Language Model](), [Software]() Tags: [ai](), [ai-2-236](), [api](), [cost](), [generative-ai](), [generative-ai-1-982](), [llms](), [llms-1-948](), [model](), [models](), [news](), [openrouter](), [openrouter-32](), [providers](), [reasoning](), [serve]() ### AI overview OpenRouter's automatic provider fallbacks can produce inconsistent behavior for the same model because providers use different serving software, optimizations, and settings. The article notes differences in vision support and reasoning-effort handling, and points to provider.only and /endpoints for controlling or inspecting routing. ### Source excerpt So you want to use OpenRouter? One of OpenRouter's selling points is that it "handles fallbacks automatically and picks the most cost-effective option for each request", so you can call a single API endpoint for a model and get routed to the best available backend provider. Mohamed Moustafa points out a whole set of ways that this can cause you problems. Different providers run different serving software with different optimizations and settings, which means that the same OpenRouter endpoint can serve model requests that behave in different ways. Some providers even lack vision capability for vision models, and the way the reasoning effort option is processed can differ as well. Thankfully you can control which provider is routed to using the provider.only option. The /endpoints method returns the list of available providers for a specific model ID. Via Hacker News Tags: ai, generative-ai, llms, openrouter ## OpenAPI Documentation for Spin Apps with Rust DevFeed: [OpenAPI Documentation for Spin Apps with Rust]() Original publisher: [Read original article]() Author: Thorsten Hans Published: 2025-08-19T12:00:00Z Content type: tutorial Language: en Sources: [Fermyon - Experience the next wave of cloud computing.]() Topics: [Documentation](), [OpenAPI Specification](), [Rust]() Tags: [documentation](), [how-to](), [learn](), [openapi](), [rust](), [serve]() ### AI overview A tutorial on creating, customizing, and serving OpenAPI documentation within Spin applications written in Rust. ### Source excerpt Learn how to create, customize and serve OpenAPI Documentation from within Spin apps written in Rust ## Gophercon Latam 2025 - Serving TUIs over SSH using Go ✨ DevFeed: [Gophercon Latam 2025 - Serving TUIs over SSH using Go ✨]() Original publisher: [Read original article]() Author: Carlos Alexandro Becker Published: 2025-05-05T00:00:00Z Content type: article Language: en Sources: [Carlos Becker]() Topics: [ssh](), [Go](), [Text-based user interface](), [Sequences]() Tags: [2025](), [ansi](), [build](), [code](), [event](), [go](), [how-to](), [interviews](), [introduction](), [photos](), [repository](), [sequences](), [serve](), [ssh](), [talk](), [video]() ### AI overview A recap of a Gophercon Latam 2025 talk covering terminal history, ANSI escape sequences, SSH, and how to build and serve a text-based user interface using Bubble Tea and Wish. ### Source excerpt My talk at Gophercon Latam 2025, showing a brief history of terminals, an introduction to ANSI escape sequences, a briefer introduction to SSH, and finally, how to build and serve a TUI using Bubble Tea and Wish. ## Funnel and Serve: Tailscale Explained DevFeed: [Funnel and Serve: Tailscale Explained]() Original publisher: [Read original article]() Author: Alex Kretzschmar Published: 2023-11-09T00:00:00Z Content type: tutorial Language: en Sources: [Tailscale Community]() Topics: [tailscale](), [Internet]() Tags: [demo](), [funnel](), [local](), [serve](), [tailnet](), [tailscale](), [video](), [vs-code]() ### AI overview A demo video explains how to access local services over a Tailscale tailnet or the public internet using Funnel and Serve. ### Source excerpt Accessing your local services over your tailnet or the public internet is one command away, as Alex demonstrates in a new demo video. ## Funnel-y enough: Release Recap November 2023 DevFeed: [Funnel-y enough: Release Recap November 2023]() Original publisher: [Read original article]() Author: Parker Higgins Published: 2023-11-02T00:00:00Z Content type: release Language: en Sources: [Tailscale Community]() Topics: [tailscale]() Tags: [funnel](), [release](), [release-recap](), [serve](), [taildrop](), [tailscale](), [updates]() ### AI overview A November 2023 Tailscale release recap covering updates to Serve and Funnel, Taildrop, and automatic updates. ### Source excerpt Big updates to Serve and Funnel, Taildrop, and auto-updates in the latest Tailscale release. ## Remote control with Code: Release Recap September 2023 DevFeed: [Remote control with Code: Release Recap September 2023]() Original publisher: [Read original article]() Author: Parker Higgins Published: 2023-09-01T00:00:00Z Content type: release Language: en Sources: [Tailscale Community]() Topics: [VS Code Extension](), [vs-code]() Tags: [beta](), [extension](), [funnel](), [release](), [release-recap](), [serve](), [tailnet-lock](), [vs-code]() ### AI overview Tailscale's September 2023 release recap covers remote editing with its VS Code extension, improved onboarding for Serve and Funnel, and tailnet lock entering beta. ### Source excerpt Remote editing with our VS Code extension, smoother onramps to Serve and Funnel, and tailnet lock in beta in this month's Release Recap. ## Serving it plain: Release Recap August 2023 DevFeed: [Serving it plain: Release Recap August 2023]() Original publisher: [Read original article]() Author: Parker Higgins Published: 2023-08-01T00:00:00Z Content type: release Language: en Sources: [Tailscale Community]() Topics: [tailscale](), [HTTP](), [iOS]() Tags: [headers](), [http](), [identity](), [ios](), [redesign](), [release](), [release-recap](), [serve](), [tailscale](), [tailscale-serve]() ### AI overview Tailscale's August 2023 Release Recap covers Tailscale Serve over plain HTTP, identity headers, and an iOS redesign. ### Source excerpt Tailscale Serve over plain HTTP, identity headers, and an iOS redesign in this month's Release Recap. ## Tapping into Tailscale's identity headers with Serve DevFeed: [Tapping into Tailscale's identity headers with Serve]() Original publisher: [Read original article]() Author: Parker Higgins, Sonia Appasamy Published: 2023-07-20T00:00:00Z Content type: tutorial Language: en Sources: [Tailscale Community]() Topics: [tailscale](), [proxy]() Tags: [content](), [flask](), [funnel](), [headers](), [identity](), [proxy](), [python](), [serve](), [tailscale](), [tailscale-serve]() ### AI overview This tutorial explains how to use identity headers from Tailscale Serve when proxying requests, allowing an application to change the content it serves. ### Source excerpt When you use Tailscale serve to proxy requests, you can use its identity headers to change what content you serve.