<oembed><type>rich</type><version>1.0</version><title>Juraj wrote</title><author_name>Juraj (npub1m2…lr8p9)</author_name><author_url>https://nostr.now/npub1m2mvvpjugwdehtaskrcl7ksvdqnnhnjur9v6g9v266nss504q7mqvlr8p9</author_url><provider_name>njump</provider_name><provider_url>https://nostr.now</provider_url><html>The cheapest per-token inference...&#xA;&#xA;If you&#39;ve looked at nostr:nprofile1qy88wumn8ghj7mn0wvhxcmmv9uq32amnwvaz7tmjv4kxz7fwv3sk6atn9e5k7tcqyz9lv2dn65v6p79g8yqn0fz9cr4j7hetf28dwy23m6ycq50gqph3xdsqeaf  and want cheap AI inference paid in sats (without e-mail address and without KYC) but don&#39;t want to manually pick and babysit nodes, run routstrd locally.&#xA;&#xA;First the prices. I am monitoring prices and for most models, you can get somewhere between 53% and 66% of nostr:nprofile1qyxhwumn8ghj7mn0wvhxcmmvqy2hwumn8ghj7mn0wd68ytn00p68ytnyv4mz7qpq6g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hq62etsy  (also pay per query) price on Routstr. Yep, between half and two-thirds. Some models, such as Kimi K3 are often 36%. And PPQ is around 5% more expensive than OpenRouter. I do not know of a cheaper way to get per-token API inference right now (besides subscriptions, they are a different beast).&#xA;&#xA;Back to routstrd. It&#39;s a small daemon, not a node itself, that sits on your machine and exposes a normal OpenAI-compatible API on localhost:8008. Point your apps at it and it handles the rest.&#xA;&#xA;Under the hood it finds nodes by reading provider announcements off Nostr relays, verifying them and refreshing the list every 21 minutes, and it only trusts nodes that have a positive review from the Routstr team — anything unreviewed is disabled by default. For whatever model you&#39;re calling, it compares prices across all known nodes and routes to the cheapest one, and if a request fails it automatically fails over to the next cheapest instead of just erroring out.&#xA;&#xA;On payments, it defaults to a mode where it quietly exchanges a Cashu token for each node&#39;s own API key, holds onto it, and tops it up as the balance runs low — so it genuinely manages real provider API keys for you behind the scenes. You fund it with Lightning or a Cashu token, and your apps never touch the e-cash directly, they just get a local key from the daemon.&#xA;&#xA;Worth trying, just keep the wallet funded with small amounts you&#39;re comfortable topping up regularly rather than loading it with a lot of sats at once.&#xA;&#xA;Basic commands to get going:&#xA;&#xA;bun i -g routstrd&#xA;routstrd onboard&#xA;routstrd receive &lt;cashu-token&gt;      # fund with a Cashu token&#xA;routstrd receive 2100                # or top up 2100 sats via Lightning&#xA;routstrd start                       # starts the daemon on localhost:8008&#xA;routstrd clients add --claude-code   # or --pi-agent / --opencode&#xA;routstrd status&#xA;routstrd balance&#xA;&#xA;P.S.: I run price monitoring of Routstr nodes and I only count nodes that respond to API requests with completion - so these prices are representative of real prices that you can get, not only advertised prices.</html></oembed>