Writing and content decision
Blainy
A capable technical user can build a useful, smaller replacement (search, citations, LLM writing, PDF chat) in a multi-week effort using existing APIs and open-source projects, though they will lack Blainy’s established brand, polish, and any proprietary data.
Visit website↗$12/mo
$144/yr
Read off the official pricing page.
$100one-off170 h to build
$50/mo6 h/mo upkeep
On cash alone, building overtakes the subscription at 5 seats.
No open-source build does this yet
Nothing published replaces this one, so a replacement starts from an empty file. Here is what it would have to cover.
What a replacement has to do
- Index/lookup academic papers, generate in-text citations in common styles, produce AI autocomplete/writing via an LLM, chat-with-PDF (PDF ingestion + embedding), web editor UI with saving to a database
What it still won’t have
- Large established user base and brand-recognition
- Production polish, design and UX refinements
- Priority customer support and trust signals
- Any proprietary datasets, telemetry, or training used by the vendor
What remains hard
- Brand trust
Blainy — The world’s #1 research paper writer - Blainy
First-year cost
Keep paying
Paying is—cheaper in year one.
On cash alone, building overtakes the subscription at 5 seats.
Money you would actually spend
Time you would spend
—
What you would spend
What we assumed
The verdict above measures whether you could build it. This one is only about money.
Runnable build prompt
Build a minimal self-hosted research-paper assistant using Next.js (React) for the web front end, PostgreSQL for user/docs storage, a vector DB (Pinecone or Milvus) for embeddings, and OpenAI (or compatible) for LLM calls. Implement: 1) paper search using CrossRef/arXiv/Semantic Scholar APIs and an ingestion pipeline that stores metadata; 2) citation formatting module supporting APA, MLA, IEEE, Harvard; 3) LLM endpoints for autocomplete, paraphrase and outline generation with token accounting and rate-limits; 4) PDF ingestion (extract text, chunk, embed) and a conversational PDF chat endpoint; 5) rich-text editor to create/save/export documents (PDF/Word) and basic account/session management. Out of scope: training custom LLMs, large-scale multi-tenant infra, automated grant/grade claims. Include error handling, input validation, unit tests for core logic, and a docker-compose deployment manifest.
How we checked
How the score was reached
- Partly verdict base52
- 2 cited sources+1
- Price verified on pricing page+3
- 3/3 assessment runs agreed+4
- Evidence score60
The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.
How scoring works →Cited sources · 2
Every page the run actually retrieved.
- official productBlainy — The world’s #1 research paper writer - Blainy
- official docsProduct Description Generator - Blainy
Integrity checks
What held up, and what did not.
