infr.ad · ads pay, you code free
Free LLM API. Ads in your terminal pay for it.
What it does
A free, OpenAI-compatible LLM API. No credit card, no billing, no trial. Every so often a response ends with a small ASCII block from a sponsor. Forty columns, plain text, nothing to block. That is the whole business model. You never see one in an agent turn — requests with tools, structured output, or a long system prompt are exempt, so aider, Cursor and Continue behave normally. Three models. Two env vars and any OpenAI client works. Sign in with GitHub, get a key in a minute.
Developers stopped visiting websites. They are in Cursor, VS Code and the terminal. infr.ad puts your brand inside the answers they are already reading.
Every place you used to buy their attention is emptying out. They ask a model now and never open the tab. That question has a Stack Overflow page with millions of views. Today it is answered without anyone opening a tab. Two decades of developer attention, answered now before anyone opens a tab. Those visits are not coming back. Below the fold, collapsed sidebar, behind the blocker this audience installs first. All of it counts as delivered. Printing an impression costs a network nothing. Everyone in the chain is paid by the number they report. The attention did not disappear. It moved somewhere nobody is selling. No script, no iframe, no third-party domain. Nothing for a blocker to match…from infr.ad
Does the same job
all alternatives →
OpenLIT's Zero-code LLM ObservabilityOct 2025 · ▲136Trace LLM requests + costs with OpenTelemetry monitoring
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com