Bohrium
AI-for-science research hub pairing citation-traceable paper search with a Deep Research literature writer, knowledge bases, and scientific computing tools.
Updated 2026-08-10
Yes, within limits. Bohrium runs a free tier with paid plans above it.
Listed pricing: Free tier with daily credits; paid tiers — check website for current pricing.
Overview
Bohrium is an AI-for-science platform from DP Technology that runs semantic search over a large academic corpus, drafts sourced literature reviews through a Deep Research mode, and wraps both in personal knowledge bases, scholar profiles, and a set of scientific computing tools. The target user is a working researcher: grad students, postdocs, and faculty who need to get from a question to a synthesis without losing the thread back to the underlying papers.
Citation traceability is the pitch. Output links back to real, locatable sources instead of paraphrased or invented references, which is the difference between a draft you can cite and one you have to re-verify line by line. That mattered more in 2025 than it does now. Through 2026 the general assistants shipped deep-research modes that cite sources by default, and Elicit, Consensus, SciSpace, and NotebookLM all sit in the same lane. What Bohrium still has that they mostly don't is the computing side: DP Technology comes out of the DeepModeling open-source ecosystem and collaborates with the Beijing Institute for AI for Science, so the platform reaches past literature into the actual scientific workflow rather than stopping at the summary.
The company reports 300,000+ researchers across 100+ universities, and the app is fully operational (chat, knowledge bases, agents, tools, mirrored at bohrium.dp.tech). Two caveats worth knowing going in. Coverage skews toward the physical and life sciences where DP Technology is strongest, so a humanities or social-science literature search will feel thinner than the corpus size suggests. And the pricing page moves: the credit allowances and paid tiers have not held still, so confirm the current numbers before committing a lab budget to it.
Is Bohrium free?
Yes, within limits. Bohrium runs a free tier with paid plans above it.
What the free tier covers: Yes. A free tier with a daily credit allowance covers core search and basic literature review, which is enough to judge whether the corpus covers your field before paying.
Listed pricing: Free tier with daily credits; paid tiers — check website for current pricing.
Pricing verified . That is the date the plans were last re-checked against the vendor's own pages, not today's date. Confirm on the official site before you pay.
What the free tier leaves out
Read straight off the plan list below. Vendors move features between tiers, so check the current split before you pay.
- Paid tiers Check website for current pricing Higher Deep Research and agent usage limits. Tier names and prices are not stable enough to quote here; the pricing page is the only reliable source.
- Student / Institutional Custom Discounted student access and institutional licensing, arranged directly with the company.
Bohrium pricing
| Plan | Price | What's included |
|---|---|---|
| Free | $0 | Daily credit allowance covering core academic search and basic literature review. Credit amounts have changed since launch — confirm the current allowance on the site. |
| Paid tiers | Check website for current pricing | Higher Deep Research and agent usage limits. Tier names and prices are not stable enough to quote here; the pricing page is the only reliable source. |
| Student / Institutional | Custom | Discounted student access and institutional licensing, arranged directly with the company. |
Daily credit allowance covering core academic search and basic literature review. Credit amounts have changed since launch — confirm the current allowance on the site.
Higher Deep Research and agent usage limits. Tier names and prices are not stable enough to quote here; the pricing page is the only reliable source.
Discounted student access and institutional licensing, arranged directly with the company.
2 plans carry no published number: Paid tiers, recorded as “Check website for current pricing”; Student / Institutional, recorded as “Custom”. Nothing is estimated in its place. The vendor's own pricing page is the only source for those figures.
Pricing verified . That is the date the plans were last re-checked against the vendor's own pages, not today's date. Confirm on the official site before you pay.
Is Bohrium worth it?
Worth it for Physical and life science researchers, postdocs, and faculty who want citation-traceable literature synthesis sitting next to actual scientific computing tools, rather than a chatbot that stops at the summary.
You can test that on the free tier before paying anything. The recorded trade-offs are listed below, and any one of them can settle the question on its own.
The 7.5/10 AI Score is an editorial read of published capability, price and shipping pace. Nobody here has hands-on hours with Bohrium. How we verify.
Worth it if
The strengths recorded against this entry.
- Output links back to real, locatable papers rather than paraphrased or invented references
- Scientific computing tools and agents that general-purpose research assistants have no equivalent for
- Knowledge bases keep project context across sessions instead of restarting each chat
- Free tier with daily credits is generous enough to test corpus coverage in your field before paying
- Built by DP Technology, an established AI-for-science firm with real standing in the DeepModeling ecosystem
Not worth it if
Any one of these blocks your use case.
- Sourced literature synthesis is no longer rare — the frontier assistants' deep-research modes closed most of that gap during 2026
- Coverage skews to physical and life sciences; humanities and social-science searches feel thinner than the corpus size implies
- AI-drafted reviews still need expert verification, so the time saved is smaller than the demo suggests
- Pricing tiers and credit allowances have shifted since launch and are not clearly documented — verify before budgeting
What sets Bohrium apart
- Scientific computing tools and agents alongside literature search — Elicit, Consensus, and SciSpace stop at the papers
- Built on DP Technology's DeepModeling ecosystem, giving it genuine depth in computational chemistry and materials science
- Persistent knowledge bases the assistant reasons over across sessions, not per-chat uploads
- Citation traceability is real but no longer distinguishing — the frontier assistants' deep-research modes now match it
Key features
Citation-Traceable Search
Semantic rather than keyword search over a corpus the company puts at 170M+ papers, with answers tied back to locatable sources. The guard against fabricated references, though this is now table stakes rather than a differentiator.
Deep Research Writer
Drafts a structured, sourced literature synthesis from a posed question instead of a loose summary. Useful as a first pass over an unfamiliar subfield; still needs expert reading before it goes near a submission.
Knowledge Bases
Persistent collections of papers and notes the assistant reasons over, so a long-running project keeps its context across sessions instead of restarting cold every time you open a chat.
Scientific Computing Tools
Computing utilities and agents drawn from DP Technology's DeepModeling roots. This is the part general-purpose research assistants have no answer to, and the strongest reason to pick Bohrium over a frontier chatbot's deep-research mode.
How it compares
| Tool | Best for | Pricing | Score |
|---|---|---|---|
| Bohrium | Physical and life science researchers, postdocs, and faculty who want citation-traceable literature synthesis sitting next to actual scientific computing tools, rather than a chatbot that stops at the summary. | Free tier with daily credits; paid tiers — check website for current pricing | 7.5/10 |
| NotebookLM vs NotebookLM → | Students, academics and analysts who already have the documents they need and want them synthesized into cited answers, study guides and listenable overviews rather than searched for. | Free tier with caps + higher limits via Google AI Pro/Ultra — check website for current pricing | 8.7/10 |
| Perplexity AI vs Perplexity AI → | Analysts, journalists and consultants who need answers they can verify line by line, and who want one subscription spanning several frontier models plus an agentic browser instead of paying three vendors. | Free tier + Pro $20/mo; higher Max and Enterprise tiers above it | 8.6/10 |
| Inkling-Small vs Inkling-Small → | ML research teams and infrastructure-heavy engineering orgs that need audio-plus-vision reasoning over long documents running on weights they host themselves, because the data can't go to a hosted API. | Free open weights; Tinker hosted access — check website for current pricing | 8.5/10 |
Compare head-to-head
Comparison explorer Put Bohrium up against any three tools Opens with Bohrium already loaded. Add up to three more from the full index and read pricing, features, pros and cons in one table. →Related reading
Muse Glimmer and the 30B Open-Weights Ceiling
Meta released Muse Glimmer's 30B weights under Apache 2.0, landing in the same consumer-GPU size class as every other recent open model release.
OpenAI Astra's Cyber Pause and the Release Rules
OpenAI flagged Astra as critical on cybersecurity and paused non-essential work on it. What the hold covers and what nobody outside OpenAI can check.
ChatGPT Slider and Think Button: How to Use Both
OpenAI put reasoning depth under your control in ChatGPT. Which tier gets which control, which setting fits which task, and when to leave both alone.
Ready to try Bohrium?
Head to the official site to start with Bohrium — pricing and plans are listed above.
Visit Bohrium