browserfoundry.mdtext/markdown · 129 lines · 6,227 bytes · 0 scripts needed/llms.txt
1# browserfoundry
2
3> Search, research and data APIs for AI agents, behind one key.
4> A Keirolabs product.
5
6- base_url: https://api.keirolabs.cloud
7- auth: `Authorization: Bearer keiro_...`
8- mcp_server: https://keirolabs.space/mcp
9- get_a_key: https://platform.keirolabs.cloud/register
10- free_tier: 750 credits once at signup, no credit card
11- docs: https://platform.keirolabs.cloud/docs
12
13## Search APIs
14
15Live results, cited answers and deep research from one index of the open web.
16
17| endpoint | does | credits | latency |
18|-----------------------------|-------------------------------------------|---------|-----------|
19| POST /api/v2/search/lite | the cheapest search, for high volume | 1 (paid: 0.0375) | ~1s |
20| POST /api/v2/search/fast | ranked results | 1 (paid: 0.5) | ~1s |
21| POST /api/v2/search/content | results + full page markdown | 3 (paid: 1.5) | ~3s |
22| POST /api/v2/search/google | Google's own results as JSON | 2 | ~3s |
23| POST /api/v2/answer | a cited answer in one call | 2 (paid: 1) | ~2-5s |
24| POST /api/v2/deep | every top page read, ranked by evidence | 2 | ~7s |
25| POST /api/v2/agentic | multi-step research on hard questions | 20 | 30s-3min |
26
27## Data APIs
28
29Clean, structured content from any page, one URL or ten thousand at a time.
30
31| endpoint | does | credits |
32|-----------------------------|-------------------------------------------|----------------|
33| POST /api/v2/extract | any URL to markdown, or JSON from a schema | 2 |
34| POST /api/v2/embeddings | pages and PDFs to vectors for RAG | 3 per URL |
35| POST /api/v2/search/batch | up to 75 queries per async job | 0.5 per query (free on Startup) |
36
37## Quickstart
38
39```bash
40curl -X POST https://api.keirolabs.cloud/api/v2/search/fast \
41 -H "Authorization: Bearer $KEIRO_API_KEY" \
42 -H "Content-Type: application/json" \
43 -d '{"query":"latest open source LLMs","maxResults":5}'
44```
45
46## Response shape: /search/fast
47
48```json
49{
50 "results": [
51 { "title": "…", "url": "https://…", "snippet": "…", "score": 0.97, "published_date": "…" }
52 ],
53 "total_results": 5,
54 "latency_ms": 942,
55 "credits_used": 1
56}
57```
58
59## Benchmarks
60
61| benchmark | keiro | next best |
62|-----------------------------------|--------|------------------|
63| SimpleQA (deep search) | 96.5% | Exa 95.47% |
64| FinanceBench (accuracy) | 78% | Valyu 73% |
65| AIMultiple Agentic '26 (/20) | 15.20 | Brave 14.89 |
66| Datacircle best web search API | #1, 64.0 | Context.dev 60.7 |
67
68### Deep search on SimpleQA
69
70193 of 200 SimpleQA questions had the answer in deep's response (96.5%); 188 in the
71~900-token evidence alone (94.0%). Every response carries answer_status
72(found / weak / not_found); found was right 97.3% of the time. 2 credits per call:
73$1.78 per 1,000 on Startup, $5.33 on Essential. Median latency 7.5 s.
74
75| provider | SimpleQA | per 1,000 |
76|----------------------|----------|-----------|
77| browserfoundry deep | 96.5% | $1.78 |
78| Exa (full page) | 95.47% | ~$17 |
79| Parallel (advanced) | 95.33% | $5 |
80| You.com (Highlights) | 95.17% | $5 |
81| Brave AI Grounding | 94.1% F1 | $4+tokens |
82| Linkup (fast) | 94% F1 | $5 |
83| Tavily | 93.3% | $8 |
84| Perplexity Search | 85.92% | $5 |
85
86Best published run per provider; harnesses differ, so gaps under ~1 point are ties.
87Harness and results: https://github.com/Keirolabs-API/deep-search-benchmark
88Release: https://www.browserfoundry.cloud/blog/deep-search-update
89
90## Works with
91
92Claude Code, Cursor, Codex, Windsurf, OpenCode, Ollama, LangChain, LangGraph,
93Vercel AI SDK, CrewAI, n8n, Zapier. One API key and one MCP server.
94
95## Pricing
96
97| plan | monthly | yearly | credits / month | rate limit |
98|---|---|---|---|---|
99| Pay as you go | packs from $10 | no subscription | 750 free at signup, then 1,500-20,000 per pack | 15 req/min, 60 at 1,000+ credits |
100| Essential | $29.99 | $300/yr, save $59.88 | 11,250 | 60 req/min on lite search |
101| Pro | $49.99 | $504/yr, save $95.88 | 33,750 | 300 req/min on lite search |
102| Startup | $99.99 | $996/yr, save $203.88 | 112,500 | 600 req/min on lite search |
103
104/search/lite costs 0.0375 credit per request on paid plans ($0.10 per 1,000 on Essential), 1 on Free.
105Paid plans pay half on fast, content and answer. Batch is free on Startup.
106Zero data retention: send "zdr": true on any paid plan; queries, URLs and results are not stored. https://docs.keirolabs.cloud/zdr
107Pay as you go: credit packs from $10, no subscription. Credits last 12 months from the latest top-up; the first top-up adds 1,000 bonus credits. All plans: https://keirolabs.cloud/pricing
108
109## Data policy
110
111- never sold: queries and customer data are not sold, shared, or brokered
112- never leaves the platform: processed in-region on our own infrastructure
113- never trained on: your queries don't train models, ours or anyone's
114- pinned to your region: one X-Region header keeps data in EU, US, or APAC
115
116## Blog (each post also as markdown at /blog/<slug>.md)
117
118- [Google Custom Search API is shutting down: what to use instead](https://www.browserfoundry.cloud/blog/google-custom-search-api-alternative.md)
119- [DuckDuckGo search API: free, limits, and what to use instead](https://www.browserfoundry.cloud/blog/duckduckgo-search-api.md)
120- [URL to markdown for LLMs: 7 ways compared](https://www.browserfoundry.cloud/blog/url-to-markdown-for-llm.md)
121- [What web search costs in the OpenAI, Claude, Gemini and Perplexity APIs](https://www.browserfoundry.cloud/blog/llm-web-search-api-pricing.md)
122- [Browserbase pricing explained, and cheaper cloud browsers](https://www.browserfoundry.cloud/blog/browserbase-pricing-alternatives.md)
123
124## Links
125
126- docs: https://platform.keirolabs.cloud/docs
127- status: https://keirolabs.cloud/status
128- blog: https://keirolabs.cloud/blog
129- contact: team@keirolabs.cloud
browserfoundry · by Keirolabs

Every Web API
Your Agent Needs.

Search, extraction and research behind one key. Forged by Keirolabs for agents that work on the live web.

Start FreeRead the docs750 free credits at signup · no credit card
Datacircle's ranking of the best web search API providers

Trusted by engineers from

  • RBS International
  • Stack Overflow
  • Supabase
  • Qdrant
  • Replicate
  • Modal
  • Resend
  • Turso
The call

What You Send.
What You Get Back.

Pick an API, pick a language. One key and one shape of request across all of them.

200 OK · 942 ms · 1 credit
Request
curl -X POST https://api.keirolabs.cloud/api/v2/search/fast \
  -H "Authorization: Bearer $KEIRO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query":"Latest open source LLMs","maxResults":5}'
Responsesample values, real shape
{
  "query": "Latest open source LLMs",
  "results": [
    {
      "title": "…",
      "url": "https://…",
      "snippet": "…",
      "score": 0.97,
      "published_date": "2026-09-28T09:12:00Z"
    },
    { "title": "…", "url": "https://…", "score": 0.94 },
    { "title": "…", "url": "https://…", "score": 0.91 }
  ],
  "total_results": 5,
  "latency_ms": 942,
  "credits_used": 1
}
Latency
~1s
Cost
1 credit
Plans
Free and up
Returns
ranked sources + scores
Deep search

The Most Accurate
Web Search API.

Gaugamela, 331 BC. Alexander didn't fight the whole line.
He drove one wedge straight through its centre.

The web is mostly noise. Deep search doesn't hand you ten links into it. It goes straight for the fact, reads every page to the end, and comes back with the proof.

SimpleQA accuracybest published run per provider · %
  1. Keiro deep search96.5
  2. Exa95.47
  3. Parallel95.33
  4. you.com95.17
  5. Brave94.1
  6. Linkup94.0
  7. Tavily93.3
  8. Perplexity85.92

Oct 2026. Ours checks that the answer is in what we return; most others grade a reader model's answer, and Brave and Linkup report F1. Harnesses differ, so read gaps under a point as ties.

96.5%
of SimpleQA answered193 of 200 questions
~900
tokens of evidence94.0% of answers inside them
97.3%
right when it says foundanswer_status on every call
$1.78
per 1,000 requests2 credits on Startup
What we believe

The web is the largest thing humanity has ever written. Until now, only humans could read it.

That is ending. Soon most of its readers will be machines, acting for people, at a speed no person could.

They will need all of it: live, clean, and true enough to act on. We are building the way in.

The foundry

One Key.
Every Way onto the Web.

01 / 03 — Point at anything.

Search APIs

Live results, cited answers and deep research from one index of the open web.

02 / 03 — Reach in and read.

Research APIs

When ten links aren't enough: pages read, evidence ranked, answers cited.

03 / 03 — Bring it all back.

Data APIs

Clean, structured content from any page, one URL or ten thousand at a time.

Works with your stack

Plugs into
Every Agent You Run.

One API key and one MCP server. The same spark reaches every tool on the ring.

one key · one MCP server

Benchmarks

Don't Take Our Word.
Take the Numbers.

Public benchmarks, on the kinds of requests agents actually make.

FinanceBench · Patronus 150-question split · accuracy
Financial document QA: FinanceBench · Patronus 150-question split · accuracy
Keiro78%
Valyu73%
Parallel67%
Exa63%
Google55%

The live web,
Finally Working for You.

Stop babysitting proxies and headless fleets. browserfoundry fetches, renders and cleans every page on our side.

Endpoints · credits per request
  • Fast search/search/fast0.5
  • Search + content/search/content1.5
  • Answer/answer1
  • Research/agentic20
Your data

Your Data Never
Becomes the Product.

What you search is yours. The whole policy, in four lines.

  • Never soldWe don't sell, share, or broker your queries or customer data. Ever.
  • Never leaves the platformRequests are processed in-region on our own infrastructure. No third-party data pipelines.
  • Never trained onYour queries don't train models. Not ours, not anyone's.
  • Pinned to your regionOne X-Region header keeps your data in the EU, the US, or APAC.
Pricing

Simple Pricing,
no Surprises.

Pay in credits for what you actually call. Start free and move up when your agents do.

Pay as you go
$0 to start750 free credits · then packs from $10

No subscription. Start free, top up when you need more.

1,500–20,000
credits per pack
12 months
before credits expire
  • 15 req/min, 60 at 1,000+ credits
  • 750 free credits at signup
  • Packs from $10, credits last 12 months
  • +1,000 bonus credits on your first top-up
  • Every endpoint at standard rates
Start Free
Pro
$49.99/mobilled monthly · $42/mo if yearly

More power, more speed, more control.

33,750
credits / month
900,000
searches on /search/lite
  • 300 req/min on lite search
  • Priority queue (2x)
  • Webhook integrations
  • Priority support
Go Pro
Startup
$99.99/mobilled monthly · $83/mo if yearly

Built for teams that need scale.

112,500
credits / month
3,000,000
searches on /search/lite
  • 600 req/min on lite search
  • Batch · free and unlimited
  • Priority infrastructure
  • Dedicated account manager
Go Startup

Not sure which one? Run your numbers and compare every plan →

Start with browserfoundry

Ready to Give Your
Agent the Web?

Start free today. 750 credits at signup, no credit card, first result in under two minutes.

Start for Free