Postman Collection
Postman v2.1.0 JSON
Import into Postman, Insomnia or Bruno — to click through, debug and share with the team.
llms.txt
llms.txt for Cursor, Claude Code and ChatGPT.
The PaperOffice API as Markdown following the llmstxt.org standard: index or full spec, ready for your IDE.
Paste one URL — the AI writes the integration with real endpoints and the auth header.
llmstxt.org standard Markdown instead of JSON Fetch without a token
- Own EU infrastructure Your data remains in Europe.
- ISO 27001 active Security certified.
- SOC 2 Type II active International audit standards.
- 24+ years of experience Proven. Stable. Future-proof.
How it works
From the URL to working code
Three steps that run the same in every IDE: copy the spec URL, paste it, prompt.
-
Copy the URL
llms-full.txt for the complete spec — or llms.txt for the index with base URL, auth and categories.
-
Paste it into the AI
Claude Code, Cursor and ChatGPT read the URL directly or take the content as context. Pasting is enough.
-
Deploy the code
The AI writes the integration: endpoints, auth header, response handling — working code for your project.
Why llms.txt
Paste. Prompt. Deploy.
Paste llms.txt into Cursor or Claude Code — the IDE writes the integration. Four files, each with a clear job.
llms.txt
Markdown · llmstxt.org
Compact index — base URL, authentication and categories. Paste it for quick lookups and endpoint discovery.
https://api.paperoffice.ai/latest/docs/llms.txt llms-full.txt
Markdown · full spec
Every endpoint with parameters, response samples and error codes — the file you paste when building real integrations.
https://api.paperoffice.ai/latest/docs/llms-full.txt llms.txt
Markdown · paperoffice.ai
Company profile, key facts and top links for LLM crawlers — complements the API docs.
https://paperoffice.ai/llms.txt https://paperoffice.ai/llms-full.txt Example prompts
Copy. Paste. Code.
Copy a prompt, paste it into the AI — done. Every prompt names the spec URL, the task and the auth header.
OCR from PDF
Read this API documentation:
https://api.paperoffice.ai/latest/docs/llms.txt Extract the full text from a PDF (OCR).
Return the plain text. Auth: Authorization: Bearer po_ut_YOUR_API_KEYClassify invoices
Read this API documentation:
https://api.paperoffice.ai/latest/docs/llms.txt Classify uploaded invoices.
Return the detected document type. Auth: Authorization: Bearer po_ut_YOUR_API_KEYExtract invoice fields
Read this API documentation:
https://api.paperoffice.ai/latest/docs/llms.txt Extract invoice fields (amount, date, vendor).
Show each field with its value. Auth: Authorization: Bearer po_ut_YOUR_API_KEYWorks everywhere
Every AI speaks llms.txt.
Markdown is the native language of modern language models — no extension, no plugin.
- Claude Code
- Cursor
- ChatGPT
- GitHub Copilot
Related
What sits next to llms.txt
The pages that cover the path from prompt to running call.
Postman Collection Prefer a UI? For manual testing, debugging and sharing with the team. Publishable Keys API calls straight from Claude, ChatGPT or Grok — with po_pk_: scope-limited, origin-locked, budget-capped. Cookbook Ready-made API examples in cURL, Python, Node.js and PHP. Authentication & keys Create po_sk_ and po_ut_, set permissions, read rate limits.
Video
llms.txt in action
How an IDE works with the llms.txt of the PaperOffice API — in this video.
Common questions
Common questions about llms.txt
What is llms.txt?
A Markdown file following the llmstxt.org standard that describes the PaperOffice API for language models. llms.txt is the index with base URL, authentication and categories; llms-full.txt contains every endpoint with parameters, response samples and error codes.
Which file belongs in the IDE?
For an integration, llms-full.txt: the AI finds paths, required fields and the response structure there. llms.txt is enough for a quick overview or when context is tight.
Does fetching cost credits or need a token?
No. The documentation routes under /docs/ can be fetched without a token and cost no credits. For product endpoints, the generated code needs a bearer token (po_ut_ or po_sk_).
Which tools does this work with?
Any tool that reads a URL or takes pasted text as context: Claude Code, Cursor, ChatGPT, GitHub Copilot. No extension and no plugin is needed — Markdown is enough.
When is the Postman Collection the better choice?
For manual testing, debugging and sharing with the team. The collection lives under the same documentation base; llms.txt is meant for prompts, the collection for clicks.
What is in paperoffice.ai/llms.txt?
Company profile, key facts and the most important links of the website for LLM crawlers. It complements the API docs but does not replace them.
Next station
Where to go next
The recommended next step in the developer funnel and two fitting branches.
