Original text
Hello, I’m Lena Fischer (lena@example.org). Please update the delivery address for order SR-2048 to 14 Linden Street, Berlin. Could you confirm the change and send me the revised delivery date? Thank you, Lena.
210 characters 1 recordUnderstand your usage
What is a record?
A record measures how much text ShinrAI processes. It is not a user, a file, an AI token or a monthly seat.
See the text. Understand the records.
Fictional examples · Standard processing
Protected text
Hello, I’m Noah Weber (noah@example.org). Please update the delivery address for order TK-7316 to 28 Oak Street, Hamburg. Could you confirm the change and send me the revised delivery date? Thank you, Noah.
The charge is based on the submitted text, not the replacement text.
Chat messages: what gets sent matters
Hi, I’m Lena Fischer. Can you check order SR-2048?
50 characters 1 recordPlease send the update to lena@example.org. Thank you!
54 characters 1 recordSent separately: 1 + 1 = 2 records
Sent together as one text, these two messages fit into one record. Sent as two texts, each is rounded separately.
Conversation history and retrieved context count again whenever your application submits them.
A longer document
1.0001.000500
2.500 characters → 3 records
Round up each text in blocks of 1.000 characters.
Start with 1.000 characters
With Standard processing, a text up to 1.000 characters uses one record. A 2.500-character text uses three. Each text is rounded separately.
We count Unicode code points, including spaces and punctuation. A displayed character can contain several code points. UTF-8 bytes and AI tokens are different units.
Records per text = rounded-up blocks × processing tier
Standard: 1 record per block · Batch: 0,5 · Real-Time: 1,6
Small examples, clear totals
| Submitted text | Standard | Batch | Real-Time |
|---|---|---|---|
| 1.000 characters | 1 | 0,5 | 1,6 |
| 1.001 characters | 2 | 1 | 3,2 |
| 2.500 characters | 3 | 1,5 | 4,8 |
| Two separate 500-character texts | 2 | 1 | 3,2 |
Sending two texts in one request does not combine their rounding. Supported empty documents still have a minimum charge of one block; invalid requests are rejected.
A company chatbot example
A 1.000-character question plus four 1.500-character retrieved passages makes one 7.000-character submission: seven Standard records. At 8.000 questions per month, that is 56.000 records.
Indexing 1.000 new files of 3.000 characters each with Batch adds 1.500 records. The combined monthly estimate is 57.500. Initial indexing of an existing library is a separate, one-time workload.
Conversation history, retrieved emails and repeated agent steps count again when submitted again. Protecting a document during indexing does not make later API requests free. Restoring values locally does not itself use another ShinrAI record.
Allowance, top-ups and optional help
Your subscription month starts on your billing date. Unused monthly records do not carry over. Purchased packs do not expire.
Monthly allowance is used before managed record packs. Offline packs belong to one offline installation and are separate from managed API usage. Partner onboarding and training are optional one-time services, not record allowances.
Check usage.weighted_records in the API response and the remaining balance in Dashboard. Measure a representative workload before committing to a larger rollout.