A deterministic research pipeline with full cost transparency. CLI for individuals, REST API for teams and heavy workloads. Every claim cited, every source linked.
CLI for individuals · Hosted API for teams · Public research published openly
Tokens remaining
412
of 500 pre-paid
Jobs this month
47
14 Deep, 28 Standard, 5 Light
URLs fetched
1,962
avg 41.7 per job
Avg spend / job
$1.18
verified cites 99.4%
Token spend · last 8 weeks
Recent research
98%
Extraction Success
1000+
URLs per Job
$1
Starting Price
4 min
Avg. Turnaround
Agent-Native Research
Deep Water is MCP-enabled. An agent can commission research, read the report, act on it, and commission follow-up research — all without you in the loop.
01 — Instruct
You tell the agent what to build or fix. No further hand-holding needed.
02 — Research
The agent calls Deep Water via MCP. Hundreds of sources researched, best practices surfaced, edge cases flagged.
03 — Build
Armed with a grounded report, the agent writes code, opens PRs, and runs tests. It can loop back to research if anything is unclear.
Self-improving software
Instead of hallucinating library APIs or copying stale Stack Overflow answers, the agent reads current documentation, compares implementation patterns across dozens of sources, and applies verified best practices. The result isn’t just faster — it’s grounded.
MCP-native
Any MCP-compatible agent can call Deep Water directly — no wrapper code, no custom integration.
Runs overnight
Commission research, implement, clarify, and test — all while you sleep. Check the PR in the morning.
Iterates until confident
The agent can commission as many clarifying research runs as it needs. Each one costs only compute.
The Pipeline
Not a chatbot wrapper. A deterministic research pipeline that runs extractors locally and only calls frontier models when it matters.
Your query is decomposed into 3–12 targeted sub-questions with explicit facets, priorities, and retrieval strategies. No wasted searches.
Up to 500 URLs searched, fetched, and extracted with Readability + Trafilatura. Reflection loop refines queries between rounds.
Frontier model (GPT-5, Claude Sonnet) called once with evidence cards only. You pay for one expensive call, not hundreds.
Every claim is checked against its source span. Unsupported assertions are flagged in the final report — no silent hallucinations.
Pick Your Path
Same engine. Same pricing. Different shapes, depending on whether you’re one person with a terminal or a team shipping research into production.
Best for personal use
The fastest way to run deep research from your terminal. Zero install ceremony — npm i -g @unlikeotherai/deepwater, paste your key, done. Great for ad-hoc questions, side projects, research before a purchase, editor integrations, cron-driven briefings.
Best for production & heavy volume
The same engine, exposed as a REST API built for scale. Webhooks instead of polling, per-project billing, bring-your-own-model-keys, higher rate limits, SLA. This is the path if research is a product feature, a backend workflow, or a recurring internal process.
Both paths hit the same engine, the same pricing, the same cost caps. The only difference is how the work enters and how the result comes out.
Why Deep Water
We ran three real research queries side by side. Here's what came back.
Research query
“Latest approved treatments for triple-negative breast cancer”
Research query
“Compare REST vs GraphQL vs gRPC for high-throughput microservices”
Research query
“Market size and growth drivers for solid-state batteries 2024–2030”
Try It Now
Set your depth and quality, type your question, and we’ll get started. No hallucinations. Every claim cited.
Sign in required · Prepaid credit — top up any time · No subscription needed
Built For
If you're paying analysts to Google, or hitting ChatGPT Pro deep-research caps, this is built for you.
Series A–C startups, 5–10 person teams
Running 50–200 deep research queries a month — competitor analysis, market sizing, user sentiment. Currently burning $5K–20K/mo in analyst hours or hitting ChatGPT Pro caps.
You replace
2–5 analyst seats + $200/seat ChatGPT Pro
Small funds, 3–5 analysts, deals on 48-hour cycles
300–800 due-diligence queries per month. Speed is the edge: your analyst processes 20 URLs in 3 hours, Deep Water processes 500 in 4 minutes. Incognito mode keeps deal flow private.
You replace
60% of junior analyst research time
Agencies billing $5K–50K per engagement
Cut per-report research cost by 80–90%. Deep Water produces a sourced first draft — your analysts refine and client-face. Same billable hours, higher margin.
You replace
$500–2,000 research cost per report
Fortune 1000 market intelligence groups
Gartner and Forrester take 3–4 weeks and $100K–500K/year. Deep Water delivers the first-pass competitive landscape in 4 minutes. Use them together, not instead.
You replace
3-week research cycles
Founders shipping research features inside their own apps
Need a deep-research backend you can call from your own product? Forget building your own scope/gather/verify pipeline. REST API, webhook callbacks, bring-your-own keys in minutes.
You replace
3–6 months of infra engineering
Researchers, think tanks, policy analysts
A 40-hour literature review takes 4. Triage 500 sources, find the 20 that matter, then read deeply. Every claim cited so you can walk the bibliography yourself.
You replace
Weeks of manual search & synthesis
Your Data, Your Rules
Choose how your research is stored. Download reports anytime. Go incognito when you need to.
Past research is stored in your account. Download reports as Markdown, PDF, or JSON whenever you need them.
Run research without storing anything on our servers. Report delivered once, then permanently deleted. Full privacy.
You pay compute cost only — no markup on public research. Full breakdown on every job: URLs fetched, models used, cost incurred.
Pricing
No subscription required. Public research costs you nothing beyond compute. Privacy is the only add-on.
You pay for the compute only — tokens and search calls at cost, nothing more. Your completed research is published in the public archive so anyone can read it. No subscription, no seat fees, credit never expires.
Get startedKeep your research off the public archive. Everything you commission stays private to your account. This is what keeps the free archive running — we don’t mark up public research at all.
Add privacy planIf you're running non-commercial research at a medical or pharma university, an ecological programme, or any initiative aimed squarely at human benefit, we'll run your jobs at cost during launch. No margin. No upsell. Just infrastructure you couldn't otherwise afford.
Medical and pharma university research, ecological and climate studies, public-health work, and other non-profit programmes with a clear human-benefit thesis. Must be non-commercial.
Reach out with a short description of the programme, the institution, and what you're trying to answer. We review everything individually and assign custom terms — there's no self-serve path for at-cost access.
This is a launch-only programme. If it works we'll bring it back in later cohorts, but we can't commit to it indefinitely. If you need predictable access, apply now.
research@deepwater.live · Individual review · Terms assigned on approval
Sign up and run your first job in minutes. Public research published openly — private archive from £50 / €55 / $65 per month.
Pay as you go · Public research free to read · REST API + CLI included