nchhaya commited on
Commit
d97ed3b
·
verified ·
1 Parent(s): ed8447c

Reposition HyperAPI page for enterprise documents; add agents, datasets, production results

Browse files
Files changed (2) hide show
  1. README.md +7 -15
  2. index.html +148 -131
README.md CHANGED
@@ -6,28 +6,20 @@ colorTo: indigo
6
  sdk: static
7
  pinned: true
8
  license: mit
9
- short_description: Document intelligence APIs for finance documents
10
  tags:
11
  - document-ai
12
  - ocr
13
- - invoice-extraction
14
  - document-parsing
15
- - finance
 
16
  - pii-redaction
 
 
17
  ---
18
 
19
  # HyperAPI by Hyperbots
20
 
21
- HyperAPI turns financial documents (invoices, receipts, bank statements, contracts and more) into validated JSON. It has five endpoints, and each can be called on its own:
22
 
23
- | Endpoint | What it does | Price |
24
- |---|---|---|
25
- | `POST /v1/parse` | OCR to text and markdown with layout, boxes and tables | from $0.001/page |
26
- | `POST /v1/extract` | Typed entities and line items, or your own JSON schema | $0.05/page |
27
- | `POST /v1/classify` | Document type with a confidence score | $0.05/page |
28
- | `POST /v1/split` | Splits bundled PDFs into separate documents | $0.05/page |
29
- | `POST /v1/redact` | Masks or de-identifies PII | $0.05/page |
30
-
31
- The free tier is 30 pages/month with no credit card. [Get a key](https://apis.hyperbots.com/dashboard/register) · [Docs](https://apis.hyperbots.com/docs) · [Python SDK](https://github.com/hyprbots/hyperapi-sdk) · [Sandbox](https://apis.hyperbots.com/sandbox)
32
-
33
- This Space is a static landing page. Open the **App** tab to see it.
 
6
  sdk: static
7
  pinned: true
8
  license: mit
9
+ short_description: Document intelligence APIs for enterprise documents
10
  tags:
11
  - document-ai
12
  - ocr
 
13
  - document-parsing
14
+ - key-information-extraction
15
+ - document-classification
16
  - pii-redaction
17
+ - mcp
18
+ - agents
19
  ---
20
 
21
  # HyperAPI by Hyperbots
22
 
23
+ One API to **parse, extract, classify, split and redact** any enterprise document. It returns schema-validated JSON with a confidence score and a source box for every field, and AI agents can call it over MCP. Open the **App** tab for the overview, quickstart, agent workflow, pricing and links to our ten open synthetic benchmarks.
24
 
25
+ [Get a free key](https://apis.hyperbots.com/dashboard/register) · [Sandbox](https://apis.hyperbots.com/sandbox) · [Docs](https://apis.hyperbots.com/docs) · [Python SDK](https://github.com/hyprbots/hyperapi-sdk) · [Datasets](https://huggingface.co/hyperbots-inc)
 
 
 
 
 
 
 
 
 
 
index.html CHANGED
@@ -3,48 +3,52 @@
3
  <head>
4
  <meta charset="utf-8">
5
  <meta name="viewport" content="width=device-width, initial-scale=1">
6
- <title>HyperAPI by Hyperbots: Document intelligence APIs for finance</title>
7
- <meta name="description" content="HyperAPI turns invoices, receipts, statements and contracts into validated JSON. Parse, Extract, Classify, Split and Redact endpoints with a free tier.">
8
  <style>
9
- :root{--ink:#0f172a;--muted:#475569;--line:#e2e8f0;--bg:#ffffff;--soft:#f8fafc;--brand:#2563eb;--brand2:#0ea5e9;--code:#0b1220;--codeink:#e2e8f0}
10
  *{box-sizing:border-box}
11
- html,body{margin:0;background:var(--bg);color:var(--ink);font:16px/1.6 -apple-system,BlinkMacSystemFont,"Segoe UI",Inter,Roboto,Helvetica,Arial,sans-serif}
12
  a{color:var(--brand);text-decoration:none}a:hover{text-decoration:underline}
13
- .wrap{max-width:1040px;margin:0 auto;padding:0 24px}
14
- header.hero{background:linear-gradient(135deg,#0b1220 0%,#13254a 55%,#0c3b6e 100%);color:#fff;padding:64px 0 56px}
15
  .badge{display:inline-block;font-size:12px;letter-spacing:.06em;text-transform:uppercase;background:rgba(255,255,255,.12);border:1px solid rgba(255,255,255,.25);padding:4px 10px;border-radius:999px}
16
- h1{font-size:44px;line-height:1.1;margin:18px 0 12px;letter-spacing:-.02em}
17
- .lede{font-size:19px;color:#cbd5e1;max-width:720px;margin:0 0 28px}
18
  .cta{display:flex;gap:12px;flex-wrap:wrap}
19
  .btn{display:inline-block;padding:11px 18px;border-radius:10px;font-weight:600;font-size:15px}
20
  .btn.primary{background:#fff;color:#0b1220}.btn.ghost{border:1px solid rgba(255,255,255,.4);color:#fff}
21
  .btn:hover{text-decoration:none;opacity:.92}
22
- .facts{display:flex;gap:28px;flex-wrap:wrap;margin-top:34px;color:#cbd5e1;font-size:14px}
23
- .facts b{display:block;color:#fff;font-size:20px}
24
- section{padding:56px 0;border-bottom:1px solid var(--line)}
25
  section.alt{background:var(--soft)}
26
  h2{font-size:28px;margin:0 0 8px;letter-spacing:-.01em}
27
- .sub{color:var(--muted);margin:0 0 28px}
28
- .grid{display:grid;grid-template-columns:repeat(auto-fit,minmax(190px,1fr));gap:16px}
29
  .card{border:1px solid var(--line);border-radius:14px;padding:18px;background:#fff}
30
  .card h3{margin:0 0 6px;font-size:17px}
31
  .card code{font-size:13px;color:var(--brand)}
32
  .card p{margin:8px 0 0;color:var(--muted);font-size:14.5px}
33
- .price{font-size:13px;color:#0f766e;font-weight:600;margin-top:10px}
 
 
34
  pre{background:var(--code);color:var(--codeink);padding:18px 20px;border-radius:12px;overflow:auto;font:13.5px/1.55 ui-monospace,SFMono-Regular,Menlo,Consolas,monospace;margin:0 0 18px}
35
  code{font-family:ui-monospace,SFMono-Regular,Menlo,Consolas,monospace}
36
  .c{color:#94a3b8}.k{color:#93c5fd}.s{color:#86efac}
37
- table{width:100%;border-collapse:collapse;font-size:15px;background:#fff;border:1px solid var(--line);border-radius:12px;overflow:hidden}
38
- th,td{text-align:left;padding:11px 14px;border-bottom:1px solid var(--line);vertical-align:top}
39
- th{background:var(--soft);font-weight:600;font-size:13.5px;color:var(--muted);text-transform:uppercase;letter-spacing:.04em}
40
  tr:last-child td{border-bottom:0}
41
- .steps{counter-reset:s;list-style:none;padding:0;margin:0 0 22px}
42
- .steps li{counter-increment:s;position:relative;padding:0 0 12px 40px}
43
- .steps li:before{content:counter(s);position:absolute;left:0;top:0;width:26px;height:26px;border-radius:50%;background:var(--brand);color:#fff;font-size:13px;font-weight:700;display:flex;align-items:center;justify-content:center}
44
  .note{border-left:3px solid var(--brand2);background:#f0f9ff;padding:12px 16px;border-radius:0 10px 10px 0;color:#0c4a6e;font-size:14.5px;margin:0 0 18px}
45
- .two{display:grid;grid-template-columns:1fr 1fr;gap:24px}
46
- @media(max-width:760px){.two{grid-template-columns:1fr}h1{font-size:34px}}
 
 
 
 
47
  ul.clean{padding-left:18px;margin:0}ul.clean li{margin:0 0 8px}
 
48
  footer{padding:36px 0 48px;color:var(--muted);font-size:14px}
49
  .links{display:flex;gap:18px;flex-wrap:wrap}
50
  </style>
@@ -54,159 +58,171 @@ footer{padding:36px 0 48px;color:var(--muted);font-size:14px}
54
  <header class="hero">
55
  <div class="wrap">
56
  <span class="badge">HyperAPI · by Hyperbots</span>
57
- <h1>Turn financial documents into validated JSON</h1>
58
- <p class="lede">HyperAPI is a set of document intelligence APIs for invoices, receipts, bank statements, contracts and other finance documents. You send a PDF or image and get back clean text, typed fields, a document type or redacted pages. It works from a backend service, a dashboard or an AI agent.</p>
59
  <div class="cta">
60
  <a class="btn primary" href="https://apis.hyperbots.com/dashboard/register" target="_blank" rel="noopener">Get a free API key</a>
 
61
  <a class="btn ghost" href="https://apis.hyperbots.com/docs" target="_blank" rel="noopener">Read the docs</a>
62
- <a class="btn ghost" href="https://apis.hyperbots.com/sandbox" target="_blank" rel="noopener">Try the sandbox</a>
63
  </div>
64
  <div class="facts">
65
- <div><b>5</b>core endpoints</div>
66
- <div><b>30 pages / mo</b>free, no credit card</div>
67
- <div><b>$0.001 / page</b>fast parse</div>
68
- <div><b>Python SDK</b>sync + async, MIT</div>
 
69
  </div>
70
  </div>
71
  </header>
72
 
73
  <section>
74
  <div class="wrap">
75
- <h2>Five endpoints. Call any of them on its own.</h2>
76
- <p class="sub">Each endpoint takes a <code>document_key</code> from a single upload, so you can chain them without uploading the file again.</p>
77
  <div class="grid">
78
- <div class="card"><h3>Parse</h3><code>POST /v1/parse</code><p>OCR to clean text and markdown with page geometry, line and word boxes, layout regions and table parsing. <code>advanced</code> mode adds per-page structured HTML and markdown.</p><div class="price">from $0.001 / page</div></div>
79
- <div class="card"><h3>Extract</h3><code>POST /v1/extract</code><p>Typed entities and line items from invoices and receipts. For any other document, pass your own JSON schema.</p><div class="price">$0.05 / page</div></div>
80
- <div class="card"><h3>Classify</h3><code>POST /v1/classify</code><p>Returns a document type with a confidence score and ranked candidates. You can add your own classes and descriptions.</p><div class="price">$0.05 / page</div></div>
81
- <div class="card"><h3>Split</h3><code>POST /v1/split</code><p>Breaks a bundled PDF into separate logical documents, with a page range, label and confidence for each.</p><div class="price">$0.05 / page</div></div>
82
- <div class="card"><h3>Redact</h3><code>POST /v1/redact</code><p>Covers PII with black boxes or replaces it with synthetic values. You can add your own entity types.</p><div class="price">$0.05 / page</div></div>
83
  </div>
 
84
  </div>
85
  </section>
86
 
87
- <section class="alt" id="quickstart">
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
88
  <div class="wrap">
89
  <h2>Quickstart</h2>
90
- <p class="sub">Python 3.9+. The official SDK installs from GitHub.</p>
91
- <ol class="steps">
92
- <li>Create a free account and generate a key at <a href="https://apis.hyperbots.com/dashboard/api-keys" target="_blank" rel="noopener">apis.hyperbots.com/dashboard/api-keys</a>. Keys that start with <code>hk_live_</code> are for production and keys that start with <code>hk_test_</code> are for testing.</li>
93
- <li>Install the SDK and set <code>HYPERAPI_KEY</code>.</li>
94
- <li>Parse and extract in a single call.</li>
95
- </ol>
96
- <pre><span class="c"># install (the package installs as hyperapi-sdk and imports as hyperapi)</span>
97
  pip install <span class="s">"hyperapi-sdk @ git+https://github.com/hyprbots/hyperapi-sdk.git"</span>
98
- export HYPERAPI_KEY=hk_test_...</pre>
99
  <pre><span class="k">from</span> hyperapi <span class="k">import</span> HyperAPIClient
100
 
101
- <span class="k">with</span> HyperAPIClient() <span class="k">as</span> client: <span class="c"># reads HYPERAPI_KEY</span>
102
- doc = client.process(<span class="s">"invoice.pdf"</span>) <span class="c"># parse + extract in one call</span>
103
- print(doc[<span class="s">"result"</span>])
104
-
105
- text = client.parse(<span class="s">"invoice.pdf"</span>) <span class="c"># OCR text + layout</span>
106
- kind = client.classify(<span class="s">"bundle.pdf"</span>) <span class="c"># document type + confidence</span>
107
- parts = client.split(<span class="s">"bundle.pdf"</span>) <span class="c"># page ranges per document</span>
108
- safe = client.redact(<span class="s">"statement.pdf"</span>, mode=<span class="s">"deidentify"</span>)</pre>
109
- <div class="note">Don't run <code>pip install hyperapi</code>. That name on PyPI belongs to an unrelated project. Use the GitHub install above.</div>
110
- <p>For FastAPI, aiohttp or agent loops, use <code>AsyncHyperAPIClient</code> and fan calls out with <code>asyncio.gather</code>. Every endpoint also has a <code>submit_*</code> variant that returns a job for bulk or long-running work. Batches are available through <code>create_batch_from_files</code>.</p>
 
111
  </div>
112
  </section>
113
 
114
- <section id="rest">
115
  <div class="wrap">
116
- <h2>REST, from any language</h2>
117
- <p class="sub">The flow has three steps: request an upload URL, PUT the bytes, then call any endpoint with the <code>document_key</code>. The key is valid for 24 hours.</p>
118
- <pre><span class="c"># 1. request a presigned upload URL</span>
119
- curl -X POST https://apis.hyperbots.com/v1/documents/upload \
120
- -H <span class="s">"X-API-Key: $HYPERAPI_KEY"</span> -H <span class="s">"Content-Type: application/json"</span> \
121
- -d <span class="s">'{"filename":"invoice.pdf","content_type":"application/pdf","content_length":184213}'</span>
122
- <span class="c"># -> {"document_key":"550e8400-...","upload_url":"https://...","expires_in":900}</span>
123
-
124
- <span class="c"># 2. upload the file to upload_url with an HTTP PUT (no API key needed)</span>
125
-
126
- <span class="c"># 3. extract structured fields</span>
127
- curl -X POST https://apis.hyperbots.com/v1/extract \
128
- -H <span class="s">"X-API-Key: $HYPERAPI_KEY"</span> \
129
- -F <span class="s">"document_key=550e8400-e29b-41d4-a716-446655440000"</span></pre>
130
- <div class="two">
131
- <pre>{
132
- <span class="s">"status"</span>: <span class="s">"success"</span>,
133
- <span class="s">"task"</span>: <span class="s">"extract"</span>,
134
- <span class="s">"model_used"</span>: <span class="s">"HyperLM"</span>,
135
- <span class="s">"result"</span>: {
136
- <span class="s">"entities"</span>: {
137
- <span class="s">"invoice_number"</span>: <span class="s">"INV-2024-0042"</span>,
138
- <span class="s">"date"</span>: <span class="s">"2024-01-15"</span>,
139
- <span class="s">"due_date"</span>: <span class="s">"2024-02-15"</span>,
140
- <span class="s">"vendor_name"</span>: <span class="s">"Acme Supplies Ltd"</span>,
141
- <span class="s">"total_amount"</span>: <span class="s">"1,250.00"</span>,
142
- <span class="s">"currency"</span>: <span class="s">"USD"</span>
143
- },
144
- <span class="s">"line_items"</span>: [ ... ]
145
- }
146
- }</pre>
147
- <pre><span class="c"># any document, your schema</span>
148
- curl -X POST \
149
- <span class="s">"https://apis.hyperbots.com/v1/extract?category=non_financial"</span> \
150
- -H <span class="s">"X-API-Key: $HYPERAPI_KEY"</span> \
151
- -F <span class="s">"document_key=..."</span> \
152
- -F <span class="s">'schema={"patient_name":null,"active":false}'</span>
153
 
154
- <span class="c"># dense tables and forms</span>
155
- <span class="c"># add ?parse_mode=advanced (Plus, Pro, Custom)</span>
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
156
 
157
- <span class="c"># process asynchronously and get a job id</span>
158
- -H <span class="s">"X-Async: true"</span></pre>
 
 
 
 
 
 
 
159
  </div>
160
  </div>
161
  </section>
162
 
163
- <section class="alt" id="pricing">
164
  <div class="wrap">
165
  <h2>Pricing</h2>
166
- <p class="sub">Start free. Paid plans charge overage to prepaid credits at the per-page rates shown above. Results are cached per document for 24 hours, and cached results are not billed.</p>
167
  <table>
168
  <tr><th>Plan</th><th>Price</th><th>Pages / month</th><th>Rate limit</th><th>Highlights</th></tr>
169
- <tr><td><b>Free</b></td><td>$0</td><td>30</td><td>1 req/min</td><td>All core APIs, fast parse, no credit card</td></tr>
170
- <tr><td><b>Starter</b></td><td>$1</td><td>300</td><td>10 req/min</td><td>Core APIs, email support</td></tr>
171
  <tr><td><b>Plus</b></td><td>$25</td><td>10,000</td><td>30 req/min</td><td>Advanced parse, team workspace with 3 seats</td></tr>
172
- <tr><td><b>Pro</b></td><td>$99</td><td>50,000</td><td>60 req/min</td><td>Priority routing, up to 10 seats, priority support</td></tr>
173
- <tr><td><b>Custom</b></td><td>Talk to us</td><td>Volume</td><td>Dedicated</td><td>BYOK, IP allowlist, human-in-the-loop review</td></tr>
174
  </table>
175
- <p style="margin-top:14px;color:var(--muted);font-size:14.5px">Current prices and promotions are on the <a href="https://apis.hyperbots.com/pricing" target="_blank" rel="noopener">pricing page</a>.</p>
176
  </div>
177
  </section>
178
 
179
- <section id="details">
180
  <div class="wrap two">
181
  <div>
182
- <h2>Inputs and limits</h2>
183
  <ul class="clean">
184
- <li>PDF, PNG, JPEG, WebP, TIFF and HEIC, plus Word, Excel, PowerPoint, CSV, TXT, RTF, JSON and XML.</li>
185
- <li>Uploads up to 50 MB (512 MiB for Custom async).</li>
186
- <li>Fast parse, Classify and Split have no page cap. Advanced parse and advanced Extract allow 60 pages (500 for Custom async). Redact allows 36 pages.</li>
187
- <li><code>GET /v1/limits</code> returns the limits that apply to your key.</li>
188
  </ul>
189
  </div>
190
  <div>
191
- <h2>Data handling</h2>
192
- <ul class="clean">
193
- <li>Files are processed in memory and deleted when a run completes, unless you turn on retention.</li>
194
- <li>Documents are not used for training.</li>
195
- <li>Redact can remove PII before any downstream model sees the document.</li>
196
- <li>Hyperbots is SOC 1 Type 2, SOC 2 Type 2 and ISO 27001 certified.</li>
197
- </ul>
198
- </div>
199
- </div>
200
- </section>
201
-
202
- <section class="alt" id="research">
203
- <div class="wrap">
204
- <h2>Research behind it</h2>
205
- <p class="sub">HyperAPI runs on Hyperbots' finance-specific models, including HyperLM and in-house vision-language models.</p>
206
- <div class="grid">
207
- <div class="card"><h3>DocuLite</h3><p>Adapting LLMs and VLMs to invoice extraction without human-annotated training data, using synthetic data generators (InvoicePy and TemplatePy). Accepted at the 4th Deployable AI Workshop, AAAI 2026.</p><p><a href="https://www.hyperbots.com/research/breaking-the-annotation-barrier-with-doculite" target="_blank" rel="noopener">Read the research →</a></p></div>
208
- <div class="card"><h3>Synthetic invoice dataset</h3><p>A synthetic invoice set with HTML, OCR-style text and gold labels in the Extract output format. Use it to benchmark HyperAPI or your own pipeline.</p><p><a href="https://huggingface.co/datasets/hyperbots-inc/synthetic-invoice-extraction" target="_blank" rel="noopener">Open the dataset →</a></p></div>
209
- <div class="card"><h3>Engineering blog</h3><p>Posts on deterministic extraction from financial PDFs, schema-as-contract, and classifying more than 1,400 bank statement templates.</p><p><a href="https://apis.hyperbots.com/blogs" target="_blank" rel="noopener">Read the blog →</a></p></div>
210
  </div>
211
  </div>
212
  </section>
@@ -217,12 +233,13 @@ curl -X POST \
217
  <a href="https://apis.hyperbots.com" target="_blank" rel="noopener">apis.hyperbots.com</a>
218
  <a href="https://apis.hyperbots.com/docs" target="_blank" rel="noopener">Docs</a>
219
  <a href="https://github.com/hyprbots/hyperapi-sdk" target="_blank" rel="noopener">Python SDK</a>
 
220
  <a href="https://apis.hyperbots.com/docs/status" target="_blank" rel="noopener">Status</a>
221
  <a href="https://huggingface.co/hyperbots-inc" target="_blank" rel="noopener">Hyperbots on Hugging Face</a>
222
- <a href="https://www.hyperbots.com" target="_blank" rel="noopener">hyperbots.com</a>
223
  <a href="mailto:hyperapi-support@hyperbots.com">hyperapi-support@hyperbots.com</a>
 
224
  </div>
225
- <p style="margin-top:16px">© 2026 Hyperbots Inc. HyperAPI is a product of Hyperbots Inc.</p>
226
  </div>
227
  </footer>
228
  </body>
 
3
  <head>
4
  <meta charset="utf-8">
5
  <meta name="viewport" content="width=device-width, initial-scale=1">
6
+ <title>HyperAPI by Hyperbots: document intelligence APIs for enterprise documents</title>
7
+ <meta name="description" content="One API to parse, extract, classify, split and redact any enterprise document. Schema-validated JSON with per-field confidence, an MCP server for agents, and a free tier.">
8
  <style>
9
+ :root{--ink:#0f172a;--muted:#475569;--line:#e2e8f0;--soft:#f8fafc;--brand:#2563eb;--brand2:#0ea5e9;--code:#0b1220;--codeink:#e2e8f0;--ok:#0f766e}
10
  *{box-sizing:border-box}
11
+ html,body{margin:0;background:#fff;color:var(--ink);font:16px/1.6 -apple-system,BlinkMacSystemFont,"Segoe UI",Inter,Roboto,Helvetica,Arial,sans-serif}
12
  a{color:var(--brand);text-decoration:none}a:hover{text-decoration:underline}
13
+ .wrap{max-width:1080px;margin:0 auto;padding:0 24px}
14
+ header.hero{background:linear-gradient(135deg,#0b1220 0%,#13254a 55%,#0c3b6e 100%);color:#fff;padding:60px 0 52px}
15
  .badge{display:inline-block;font-size:12px;letter-spacing:.06em;text-transform:uppercase;background:rgba(255,255,255,.12);border:1px solid rgba(255,255,255,.25);padding:4px 10px;border-radius:999px}
16
+ h1{font-size:44px;line-height:1.1;margin:18px 0 12px;letter-spacing:-.02em;max-width:900px}
17
+ .lede{font-size:19px;color:#cbd5e1;max-width:760px;margin:0 0 26px}
18
  .cta{display:flex;gap:12px;flex-wrap:wrap}
19
  .btn{display:inline-block;padding:11px 18px;border-radius:10px;font-weight:600;font-size:15px}
20
  .btn.primary{background:#fff;color:#0b1220}.btn.ghost{border:1px solid rgba(255,255,255,.4);color:#fff}
21
  .btn:hover{text-decoration:none;opacity:.92}
22
+ .facts{display:grid;grid-template-columns:repeat(auto-fit,minmax(150px,1fr));gap:18px;margin-top:34px;color:#cbd5e1;font-size:13.5px}
23
+ .facts b{display:block;color:#fff;font-size:24px;letter-spacing:-.01em}
24
+ section{padding:54px 0;border-bottom:1px solid var(--line)}
25
  section.alt{background:var(--soft)}
26
  h2{font-size:28px;margin:0 0 8px;letter-spacing:-.01em}
27
+ .sub{color:var(--muted);margin:0 0 26px;max-width:820px}
28
+ .grid{display:grid;grid-template-columns:repeat(auto-fit,minmax(200px,1fr));gap:16px}
29
  .card{border:1px solid var(--line);border-radius:14px;padding:18px;background:#fff}
30
  .card h3{margin:0 0 6px;font-size:17px}
31
  .card code{font-size:13px;color:var(--brand)}
32
  .card p{margin:8px 0 0;color:var(--muted);font-size:14.5px}
33
+ .meta{font-size:13px;color:var(--ok);font-weight:600;margin-top:10px}
34
+ .chips{display:flex;flex-wrap:wrap;gap:8px}
35
+ .chip{border:1px solid var(--line);background:#fff;border-radius:999px;padding:5px 12px;font-size:13.5px;color:#334155}
36
  pre{background:var(--code);color:var(--codeink);padding:18px 20px;border-radius:12px;overflow:auto;font:13.5px/1.55 ui-monospace,SFMono-Regular,Menlo,Consolas,monospace;margin:0 0 18px}
37
  code{font-family:ui-monospace,SFMono-Regular,Menlo,Consolas,monospace}
38
  .c{color:#94a3b8}.k{color:#93c5fd}.s{color:#86efac}
39
+ table{width:100%;border-collapse:collapse;font-size:15px;background:#fff;border:1px solid var(--line)}
40
+ th,td{text-align:left;padding:10px 14px;border-bottom:1px solid var(--line);vertical-align:top}
41
+ th{background:var(--soft);font-weight:600;font-size:13px;color:var(--muted);text-transform:uppercase;letter-spacing:.04em}
42
  tr:last-child td{border-bottom:0}
 
 
 
43
  .note{border-left:3px solid var(--brand2);background:#f0f9ff;padding:12px 16px;border-radius:0 10px 10px 0;color:#0c4a6e;font-size:14.5px;margin:0 0 18px}
44
+ .two{display:grid;grid-template-columns:1fr 1fr;gap:28px}
45
+ .flow{display:grid;grid-template-columns:repeat(auto-fit,minmax(150px,1fr));gap:10px;margin:18px 0}
46
+ .step{border:1px solid var(--line);border-radius:12px;padding:12px;background:#fff;font-size:14px}
47
+ .step b{display:block;font-size:12px;text-transform:uppercase;letter-spacing:.05em;color:var(--brand)}
48
+ .step.agent b{color:#7c3aed}
49
+ @media(max-width:780px){.two{grid-template-columns:1fr}h1{font-size:33px}}
50
  ul.clean{padding-left:18px;margin:0}ul.clean li{margin:0 0 8px}
51
+ .small{font-size:13px;color:var(--muted)}
52
  footer{padding:36px 0 48px;color:var(--muted);font-size:14px}
53
  .links{display:flex;gap:18px;flex-wrap:wrap}
54
  </style>
 
58
  <header class="hero">
59
  <div class="wrap">
60
  <span class="badge">HyperAPI · by Hyperbots</span>
61
+ <h1>Document intelligence APIs for enterprise documents</h1>
62
+ <p class="lede">One API to <b>parse, extract, classify, split and redact</b> any enterprise document: invoices and statements, POs and bills of lading, contracts and NDAs, KYC packs, HR files, claims, lab reports and email. It returns schema-validated JSON with a confidence score and a source box for every field. You call it from your own applications, and AI agents can call it over MCP.</p>
63
  <div class="cta">
64
  <a class="btn primary" href="https://apis.hyperbots.com/dashboard/register" target="_blank" rel="noopener">Get a free API key</a>
65
+ <a class="btn ghost" href="https://apis.hyperbots.com/sandbox" target="_blank" rel="noopener">Try the sandbox (no sign-up)</a>
66
  <a class="btn ghost" href="https://apis.hyperbots.com/docs" target="_blank" rel="noopener">Read the docs</a>
 
67
  </div>
68
  <div class="facts">
69
+ <div><b>99.8%</b>extraction accuracy (reported)</div>
70
+ <div><b>&lt; 2 s</b>average latency</div>
71
+ <div><b>99.9%</b>uptime SLA</div>
72
+ <div><b>35M+</b>real documents in training</div>
73
+ <div><b>100+</b>languages</div>
74
  </div>
75
  </div>
76
  </header>
77
 
78
  <section>
79
  <div class="wrap">
80
+ <h2>Five operations, one endpoint</h2>
81
+ <p class="sub">Upload a file once and get a <code>document_key</code>, valid for 24 hours. Then run any operation against it, in any order. Each operation reads the page, interprets layout and content, and returns structured output that's ready for the next system.</p>
82
  <div class="grid">
83
+ <div class="card"><h3>Parse</h3><code>POST /v1/parse</code><p>Layout-aware text and Markdown with reading order, tables, labeled regions and word boxes with fonts. Handles scans, photos, multi-column layouts and low-quality PDFs.</p><div class="meta">~1 s · from $0.001 / page</div></div>
84
+ <div class="card"><h3>Extract</h3><code>POST /v1/extract</code><p>Typed fields and any number of line items. Use the built-in financial format or send a JSON schema for any document type. The advanced extractor detects the type automatically.</p><div class="meta">~2 s · $0.05 / page</div></div>
85
+ <div class="card"><h3>Classify</h3><code>POST /v1/classify</code><p>Document type with a confidence score and ranked candidates. 67 types out of the box, flags types outside the set, and supports custom classes.</p><div class="meta">~0.8 s · $0.05 / page</div></div>
86
+ <div class="card"><h3>Split</h3><code>POST /v1/split</code><p>Finds where each document in a bundle starts and ends, from content rather than page counts. Trained on more than 1M page streams.</p><div class="meta">~0.5 s · $0.05 / page</div></div>
87
+ <div class="card"><h3>Redact</h3><code>POST /v1/redact</code><p>Masks names, account numbers, IBANs, IDs and other PII with black boxes or synthetic values. Run it first to keep PII out of LLM prompts.</p><div class="meta">~3 s · $0.05 / page</div></div>
88
  </div>
89
+ <p class="small" style="margin-top:16px">Included with every call: per-field confidence and source boxes, document-level checks such as line items adding up to the total, <code>request_id</code> / <code>model_used</code> / duration / page count for audit, and sync, async (<code>X-Async</code>) or Batch API with webhooks. Cached re-runs within 24 hours are not billed.</p>
90
  </div>
91
  </section>
92
 
93
+ <section class="alt" id="coverage">
94
+ <div class="wrap">
95
+ <h2>What it reads</h2>
96
+ <p class="sub">No per-format templates. HyperAPI uses a 100-type reference taxonomy in 15 categories for classification and routing.</p>
97
+ <div class="chips">
98
+ <span class="chip">Payables &amp; invoices</span><span class="chip">Statements &amp; reconciliation</span><span class="chip">Credits &amp; adjustments</span><span class="chip">Payments &amp; remittances</span><span class="chip">Collections</span><span class="chip">Procurement &amp; ordering</span><span class="chip">Shipping &amp; logistics</span><span class="chip">HR &amp; employee documents</span><span class="chip">Onboarding, KYC &amp; compliance</span><span class="chip">Financial statements</span><span class="chip">Credit, lending &amp; risk</span><span class="chip">Clinical, lab &amp; healthcare</span><span class="chip">Email, chat &amp; meeting notes</span><span class="chip">Legal &amp; HR contracts</span><span class="chip">Operations, quality &amp; facilities</span>
99
+ </div>
100
+ <div class="two" style="margin-top:28px">
101
+ <div>
102
+ <h3>Formats</h3>
103
+ <ul class="clean">
104
+ <li><b>PDF:</b> native, scanned, mixed, password-protected (with credentials), PDF forms, several hundred pages</li>
105
+ <li><b>Images:</b> PNG, JPEG, TIFF (multi-page), WebP, HEIC, BMP and more</li>
106
+ <li><b>Office:</b> DOCX, XLSX (workbooks parsed natively, sheet by sheet), PPTX, ODT, RTF</li>
107
+ <li><b>Email:</b> EML and MSG, including body blocks and attachments</li>
108
+ </ul>
109
+ </div>
110
+ <div>
111
+ <h3>Hard pages</h3>
112
+ <ul class="clean">
113
+ <li>Skewed, rotated, shadowed and low-resolution scans (deskewed and enhanced first)</li>
114
+ <li>Stamps, seals, signatures and handwritten entries, with the same confidence scoring as print</li>
115
+ <li>Dense multi-column layouts and tables with hundreds of rows, including tables that span pages</li>
116
+ <li>Mixed packets: a cover letter, a form, three invoices, a cheque and a statement in one file</li>
117
+ </ul>
118
+ </div>
119
+ </div>
120
+ </div>
121
+ </section>
122
+
123
+ <section id="quickstart">
124
  <div class="wrap">
125
  <h2>Quickstart</h2>
126
+ <p class="sub">Python 3.9+ (a TypeScript / Node.js SDK and plain REST are also available). The free tier gives you 30 pages a month with no credit card.</p>
127
+ <pre><span class="c"># the package installs as hyperapi-sdk and imports as hyperapi</span>
 
 
 
 
 
128
  pip install <span class="s">"hyperapi-sdk @ git+https://github.com/hyprbots/hyperapi-sdk.git"</span>
129
+ export HYPERAPI_KEY=hk_test_... <span class="c"># https://apis.hyperbots.com/dashboard/api-keys</span></pre>
130
  <pre><span class="k">from</span> hyperapi <span class="k">import</span> HyperAPIClient
131
 
132
+ <span class="k">with</span> HyperAPIClient() <span class="k">as</span> client:
133
+ doc = client.process(<span class="s">"packet.pdf"</span>) <span class="c"># parse + extract in one call</span>
134
+ kind = client.classify(<span class="s">"packet.pdf"</span>) <span class="c"># label + confidence</span>
135
+ parts = client.split(<span class="s">"packet.pdf"</span>) <span class="c"># start/end page per document</span>
136
+ safe = client.redact(<span class="s">"packet.pdf"</span>, mode=<span class="s">"deidentify"</span>)</pre>
137
+ <div class="note">Don't run <code>pip install hyperapi</code>. That PyPI name belongs to an unrelated project. Use the GitHub install above.</div>
138
+ <pre><span class="c"># any document, your schema (REST)</span>
139
+ curl -X POST <span class="s">"https://apis.hyperbots.com/v1/extract?category=non_financial"</span> \
140
+ -H <span class="s">"X-API-Key: $HYPERAPI_KEY"</span> \
141
+ -F <span class="s">"document_key=550e8400-e29b-41d4-a716-446655440000"</span> \
142
+ -F <span class="s">'schema={"policy_number":null,"claimant_name":null,"date_of_loss":null,"amount_claimed":null}'</span></pre>
143
  </div>
144
  </section>
145
 
146
+ <section class="alt" id="agents">
147
  <div class="wrap">
148
+ <h2>Built for agents</h2>
149
+ <p class="sub">Coding agents can follow a goal and write code, but they don't read unstructured documents reliably. HyperAPI exposes its five operations over <b>MCP</b>, so Claude Code, Cursor, GitHub Copilot, Codex, OpenCode or any MCP client can build the pipeline a goal needs. <b>Agent Builder (beta)</b> picks the operations, runs them with guardrails and returns one structured result with a citation for every field.</p>
150
+ <p><i>"Reconcile this month's vendor invoices against our open POs, flag anything over $500, and mask the bank details before it moves on."</i></p>
151
+ <div class="flow">
152
+ <div class="step"><b>classify</b>separate invoices from everything else</div>
153
+ <div class="step"><b>split</b>break the batch into single documents</div>
154
+ <div class="step"><b>extract</b>vendor, totals and line items</div>
155
+ <div class="step agent"><b>agent</b>match to open POs</div>
156
+ <div class="step agent"><b>agent</b>flag totals over $500</div>
157
+ <div class="step"><b>redact</b>mask bank details</div>
158
+ </div>
159
+ <p class="small">Other workflows built from the same five operations include AP reconciliation, contract intake, statement digitisation, supplier onboarding and mixed-inbox triage.</p>
160
+ </div>
161
+ </section>
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
162
 
163
+ <section id="datasets">
164
+ <div class="wrap">
165
+ <h2>Open synthetic datasets</h2>
166
+ <p class="sub">Ten fully synthetic, CC BY 4.0 benchmarks, labelled in HyperAPI's output formats. Use them to evaluate HyperAPI or any document AI pipeline without sharing a single real document.</p>
167
+ <div class="grid">
168
+ <div class="card"><h3><a href="https://huggingface.co/datasets/hyperbots-inc/synthetic-enterprise-doc-extraction" target="_blank" rel="noopener">Enterprise extraction</a></h3><p>31 document types, 372 docs, gold fields plus the HyperAPI schema for each.</p></div>
169
+ <div class="card"><h3><a href="https://huggingface.co/datasets/hyperbots-inc/synthetic-doc-parsing" target="_blank" rel="noopener">Parsing</a></h3><p>100 pages with layout blocks, reading order, tables and Markdown.</p></div>
170
+ <div class="card"><h3><a href="https://huggingface.co/datasets/hyperbots-inc/synthetic-doc-classification" target="_blank" rel="noopener">Classification</a></h3><p>248 pages across 31 taxonomy classes, some stamped or degraded.</p></div>
171
+ <div class="card"><h3><a href="https://huggingface.co/datasets/hyperbots-inc/synthetic-doc-splitting" target="_blank" rel="noopener">Splitting</a></h3><p>200 multi-document bundles with the correct boundaries.</p></div>
172
+ <div class="card"><h3><a href="https://huggingface.co/datasets/hyperbots-inc/synthetic-pii-redaction" target="_blank" rel="noopener">PII redaction</a></h3><p>100 pages with PII spans and boxes, plus redacted and de-identified text.</p></div>
173
+ <div class="card"><h3><a href="https://huggingface.co/datasets/hyperbots-inc/synthetic-handwritten-forms" target="_blank" rel="noopener">Handwritten forms</a></h3><p>100 forms with handwritten fields, ticks, signatures and notes.</p></div>
174
+ <div class="card"><h3><a href="https://huggingface.co/datasets/hyperbots-inc/synthetic-stamped-documents" target="_blank" rel="noopener">Stamped documents</a></h3><p>100 documents with stamps and seals over the text.</p></div>
175
+ <div class="card"><h3><a href="https://huggingface.co/datasets/hyperbots-inc/synthetic-bad-scans" target="_blank" rel="noopener">Bad scans</a></h3><p>120 pages at 3 severities, with skew, blur, noise and compression.</p></div>
176
+ <div class="card"><h3><a href="https://huggingface.co/datasets/hyperbots-inc/synthetic-dense-documents" target="_blank" rel="noopener">Dense documents</a></h3><p>60 high-resolution pages: directories, legal terms, long tables.</p></div>
177
+ <div class="card"><h3><a href="https://huggingface.co/datasets/hyperbots-inc/synthetic-invoice-extraction" target="_blank" rel="noopener">Invoice extraction</a></h3><p>200 invoices with line items and a ready-made HyperAPI scorer.</p></div>
178
+ </div>
179
+ </div>
180
+ </section>
181
 
182
+ <section class="alt" id="production">
183
+ <div class="wrap">
184
+ <h2>In production</h2>
185
+ <p class="sub">Client names are withheld. All figures are as reported by Hyperbots.</p>
186
+ <div class="grid">
187
+ <div class="card"><h3>1M+ invoices a year</h3><p>A US marketing-services enterprise with 21 entities on SAP and NetSuite. An Invoice Processing Agent built on classify, split and extract reports 99%+ extraction accuracy, 80% less manual AP work and 40% lower AP cost.</p></div>
188
+ <div class="card"><h3>$10B manufacturer</h3><p>More than 300K invoices a year posted into SAP ECC, with low-confidence fields routed to review and 40% fewer outsourced (KPO) staff.</p></div>
189
+ <div class="card"><h3>1M pages in 10 days</h3><p>An aged, dense, multi-column directory archive parsed with column boundaries and reading order intact, then extracted into structured records.</p></div>
190
+ <div class="card"><h3>One parse, five formats</h3><p>A document reconstruction pilot across vector PDF, scanned PDF, XPS, Outlook email and Excel, with 97% median text recall on the client's own files.</p></div>
191
  </div>
192
  </div>
193
  </section>
194
 
195
+ <section id="pricing">
196
  <div class="wrap">
197
  <h2>Pricing</h2>
198
+ <p class="sub">Start free. On paid plans, usage beyond the included pages is charged to prepaid credits at per-page rates.</p>
199
  <table>
200
  <tr><th>Plan</th><th>Price</th><th>Pages / month</th><th>Rate limit</th><th>Highlights</th></tr>
201
+ <tr><td><b>Free</b></td><td>$0</td><td>30</td><td>1 req/min</td><td>All five operations, fast parse, no credit card</td></tr>
202
+ <tr><td><b>Starter</b></td><td>$1</td><td>300</td><td>10 req/min</td><td>Email support</td></tr>
203
  <tr><td><b>Plus</b></td><td>$25</td><td>10,000</td><td>30 req/min</td><td>Advanced parse, team workspace with 3 seats</td></tr>
204
+ <tr><td><b>Pro</b></td><td>$99</td><td>50,000</td><td>60 req/min</td><td>Priority routing, up to 10 seats</td></tr>
205
+ <tr><td><b>Custom / Enterprise</b></td><td>Talk to us</td><td>Volume</td><td>Custom throughput</td><td>BYOK, IP allow-listing, SSO, human review step, custom pipelines, forward-deployed engineers</td></tr>
206
  </table>
207
+ <p class="small" style="margin-top:12px">Current prices and promotions are on the <a href="https://apis.hyperbots.com/pricing" target="_blank" rel="noopener">pricing page</a>.</p>
208
  </div>
209
  </section>
210
 
211
+ <section class="alt" id="trust">
212
  <div class="wrap two">
213
  <div>
214
+ <h2>Security &amp; data handling</h2>
215
  <ul class="clean">
216
+ <li>ISO 27001, SOC 1 Type 2 and SOC 2 Type 2, with encryption in transit and at rest</li>
217
+ <li>Documents are processed in memory and deleted when the run completes unless you enable retention</li>
218
+ <li>Customer data is never used for training. Redaction can run before any model sees a document</li>
219
+ <li>BYOK, IP allow-listing, SSO (Okta, Entra ID, Google Workspace, OneLogin), role-based access and full audit trails</li>
220
  </ul>
221
  </div>
222
  <div>
223
+ <h2>The models</h2>
224
+ <p>HyperAPI runs on <b>HyperLM</b>, a mixture-of-experts document stack of small, vision and large language models, with multimodal encoders for layout, text and image and decoders specialised by task and field. It is trained on 35M+ real documents and 0.5B synthetic samples and retrained continuously.</p>
225
+ <p>Related research: <a href="https://www.hyperbots.com/research/breaking-the-annotation-barrier-with-doculite" target="_blank" rel="noopener">DocuLite</a> (4th Deployable AI Workshop, AAAI 2026) adapts small LLMs and VLMs to invoice extraction using synthetic data instead of human annotation.</p>
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
226
  </div>
227
  </div>
228
  </section>
 
233
  <a href="https://apis.hyperbots.com" target="_blank" rel="noopener">apis.hyperbots.com</a>
234
  <a href="https://apis.hyperbots.com/docs" target="_blank" rel="noopener">Docs</a>
235
  <a href="https://github.com/hyprbots/hyperapi-sdk" target="_blank" rel="noopener">Python SDK</a>
236
+ <a href="https://apis.hyperbots.com/blogs" target="_blank" rel="noopener">Engineering blog</a>
237
  <a href="https://apis.hyperbots.com/docs/status" target="_blank" rel="noopener">Status</a>
238
  <a href="https://huggingface.co/hyperbots-inc" target="_blank" rel="noopener">Hyperbots on Hugging Face</a>
 
239
  <a href="mailto:hyperapi-support@hyperbots.com">hyperapi-support@hyperbots.com</a>
240
+ <a href="mailto:research@hyperbots.com">research@hyperbots.com</a>
241
  </div>
242
+ <p style="margin-top:16px">© 2026 Hyperbots Inc. HyperAPI is a product of Hyperbots Inc. Performance figures are as reported by Hyperbots; results on your documents may differ.</p>
243
  </div>
244
  </footer>
245
  </body>