I run a production AI app for €60 a month. Here is the actual bill.
TailStoryBlogInside TailStoryInside TailStoryI run a production AI app for €60 a month. Here is the actual bill.Photo-to-structured-data, a RAG assistant with citations, voice logging and a recommendation engine — in 21 languages, on one VPS. So here are ours.TailStory is a pet health record.
- ▪TailStoryBlogInside TailStoryInside TailStoryI run a production AI app for €60 a month.
- ▪Here is the actual bill.Photo-to-structured-data, a RAG assistant with citations, voice logging and a recommendation engine — in 21 languages, on one VPS.
- ▪So here are ours.TailStory is a pet health record.
Hacker News (AI / LLM) files mainly under ai. We currently carry 6,025 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | TailStory |
| Canonical URL | https://tailstory-app.com/en/blog/what-production-ai-actually-costs |
| Publication time | Tue, 22 Sep 2026 16:55:49 +0000 |
| Retrieval time | 2026-09-22T17:08:53.225Z |
| Last seen | 2026-09-22T17:08:53.225Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | rL2E9Xxmo19h · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
TailStoryBlogInside TailStoryInside TailStoryI run a production AI app for €60 a month. Here is the actual bill.Photo-to-structured-data, a RAG assistant with citations, voice logging and a recommendation engine — in 21 languages, on one VPS. The real per-call costs, and why inference was never the expensive part.By TailStory team·22 September 2026·6 min readIn this articleThe bill, per operationInference is not the expensive partFour decisions that kept it cheapWhat we got wrongThe part that is not about moneyEvery time someone posts an AI side project, the same comment appears: nice, but what does it cost to run? Almost nobody answers with numbers. So here are ours.TailStory is a pet health record. A photo becomes a structured profile. A spoken sentence becomes several log entries.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at TailStory.
Discussion
0 commentsMore from TailStory
