Bohrium
AI-for-science research hub with citation-traceable search across 170M+ papers, a Deep Research literature writer, knowledge bases, and scientific computing tools.
Updated 2026-06-27
Overview
Bohrium is an AI-for-science research platform from DP Technology that combines semantic academic search across a corpus of 170M+ papers with an AI literature-review writer, personal knowledge bases, scholar profiles, and a set of scientific computing tools. It's built for working researchers — grad students, postdocs, and faculty — who need to move from a question to a sourced synthesis without losing the thread back to the underlying papers.
The differentiator Bohrium leans on hardest is citation traceability. Where general-purpose chatbots and many "research assistants" paraphrase or hallucinate references, Bohrium ties its Deep Research output back to real, locatable papers, which is the difference between a draft you can cite and one you have to re-verify line by line. It sits in the same lane as Elicit, Consensus, SciSpace, and NotebookLM, but adds a scientific-computing angle that reflects its roots — DP Technology is an established player in the DeepModeling open-source ecosystem and collaborates with the Beijing Institute for AI for Science.
The company reports 300,000+ researchers across 100+ universities using the platform. That traction, plus a live, fully operational app (chat, knowledge bases, agents, and tools, also mirrored at bohrium.dp.tech), puts it well past the vaporware stage. The main caveats are typical for this category: domain coverage skews toward the physical and life sciences where DP Technology is strongest, and the AI-written reviews still need expert review before they go anywhere near a submission.
Key features
Citation-Traceable Search
Semantic search over a corpus of 170M+ papers where every answer traces back to a real, locatable source — the key guard against the fabricated references that plague general chatbots.
Deep Research Writer
An AI literature-review and Deep Research mode that drafts structured, sourced syntheses from the question you pose, rather than a loose summary you have to re-check.
Knowledge Bases
Build personal collections of papers and notes the assistant can reason over, so research context persists across sessions instead of starting cold each time.
Scientific Computing Tools
A set of computing utilities reflecting DP Technology's DeepModeling roots, extending the platform beyond literature into the actual scientific workflow.
Pricing
Free tier: Yes — a free tier with daily credits (~1,500 reported) covers core search and basic literature review.
| Plan | Price | What's included |
|---|---|---|
| Free | $0 | Daily credits (~1,500 reported) covering core academic search and basic literature review |
| Pro | From ~$15/mo | Heavier Deep Research and AI Mentor usage; check website for current tiers and limits |
| Student / Institutional | Custom | Discounted student and institutional access — contact for details |
Daily credits (~1,500 reported) covering core academic search and basic literature review
Heavier Deep Research and AI Mentor usage; check website for current tiers and limits
Discounted student and institutional access — contact for details
Pros & cons
Pros
- ✓Citation traceability to real papers — output you can actually cite, not hallucinated references
- ✓Searches a large 170M+ paper corpus with semantic, not just keyword, matching
- ✓Combines literature review, knowledge bases, and scientific computing in one platform
- ✓Usable free tier with daily credits, plus student and institutional pricing
- ✓Backed by DP Technology, an established AI-for-science firm with real research traction
Cons
- ×Coverage skews toward physical and life sciences where DP Technology is strongest
- ×AI-generated reviews still require expert verification before any serious use
- ×Crowded category — overlaps heavily with Elicit, Consensus, and SciSpace
- ×Pricing tiers and credit limits are not always clearly documented; verify on the site
How it compares
| Tool | Best for | Pricing | Score |
|---|---|---|---|
| Bohrium | — | Free tier (daily credits) + Pro from ~$15/mo | 8/10 |
| Perplexity AI vs Perplexity AI → | — | Freemium | 9.4/10 |
| NotebookLM vs NotebookLM → | — | Free | 9.1/10 |
| Phind vs Phind → | — | Free tier + Pro subscription for advanced models | 8.7/10 |
Compare head-to-head
Related reading
Gov and Big Labs Get Frontier AI First. We Don't.
The most capable AI now reaches a few labs and the government first, then trickles to the public in guardrailed form. Why that precedent matters.
GPT-5.6 Sol, Terra, Luna: OpenAI's Limited Preview
OpenAI's GPT-5.6 family ships as a gated preview after a US government request. Here's what Sol, Terra, and Luna actually are.
GPT-5.6 Sol vs GPT-5.5: What the Benchmarks Say
OpenAI previewed GPT-5.6 Sol on June 26. Here's how its reported benchmarks stack up against GPT-5.5 — and what to trust.
Ready to try Bohrium?
Head to the official site to start with Bohrium — pricing and plans are listed above.
Visit Bohrium