Cash Flow Ref - AI Bank Stmt Auditor Model
Bank Stmt Auditor
by Neurometric📄 Document Intelligence
Cash-Flow-Ref is a task-specific model that identifies recurring subscriptions and hidden fees in bank statement exports.
Cash Flow Ref is designed for Document Intelligence workflows where speed, consistency, and control matter more than generic creativity. Instead of relying on a broad model to guess intent each time, this task-specific SLM is optimized for bank stmt auditor and predictable output quality. That makes it easier to adopt in production pipelines where teams need reliable formatting, lower latency, and reduced hallucination risk.
Most teams integrate CRM records, internal docs, and workflow tools to automate repetitive language-heavy tasks with predictable outputs. This makes deployment practical for sales ops, customer success, legal, and operations teams that need answers grounded in their own data. Because the model is small and focused, teams can run it with efficient infrastructure while still meeting quality targets for the use case.
Compared with general-purpose models, focused SLMs like this one typically deliver better precision for narrow tasks, lower cost per request, and easier governance. You can start with the free tier, test the model against your business data, and scale usage through Neurometric APIs or ClawPack workflows when performance meets your benchmark.
Model: Qwen/Qwen3-4B-Instruct-2507
This task-specific SLM uses Qwen/Qwen3-4B-Instruct-2507 with a specialized system prompt. The model weights are identical to the base Qwen model — the task specialization comes from the system prompt and has been validated through our testing pipeline. Need better accuracy? We can fine-tune the model on your data for your specific use case.
Quickstart
Copy-paste code to use Cash-Flow-Ref in your project
from openai import OpenAI
client = OpenAI(
base_url="https://api.neurometric.ai/v1",
api_key="YOUR_API_KEY"
)
resp = client.chat.completions.create(
model="neurometric/cash-flow-ref",
messages=[
{"role": "user",
"content": "{\n \"metadata\": {\n \"bank\": \"ExampleBank\",\n \"exported_at\": \"2025-12-01T09:30:00Z\"\n },\n \"account_id\": \"CC-7781\",\n \"transactions\": [\n {\n \"date\": \"2025-11-01\",\n \"amount\": -9.99,\n ..."}
]
)
print(resp.choices[0].message.content)Test Results
Example Input
Metadata: Bank: ExampleBank Exported At: 2025-12-01T09:30:00Z Account Id: CC-7781 Transactions: - Date: 2025-11-01; Amount: -9.99; Currency: USD; Description: APPLE.COM/BILL - Date: 2025-11-03; Amount: -18.27; Currency: USD; Description: UBER TRIP HELP.UBER.COM - Date: 2025-11-08; Amount: -1.36; Currency: USD; Description: INTL TRANSACTION FEE - Date: 2025-11-12; Amount: -13.99; Currency: USD; Description: GOOGLE *YouTubePremium - Date: 2025-11-16; Amount: -9.99; Currency: USD; Description: APPLE.COM/BILL - Date: 2025-11-18; Amount: -29; Currency: USD; Description: LATE PAYMENT FEE - Date: 2025-11-25; Amount: -9.99; Currency: USD; Description: APPLE.COM/BILL - Date: 2025-11-28; Amount: -13.99; Currency: USD; Description: YouTubePremium Statement Period: 2025-11
Expected Output
Recurring And Hidden Fees:
Type: subscription
Evidence: - 2025-11-01 -9.99
2025-11-16 -9.99
2025-11-25 -9.99
Merchant: Apple (App Store/iCloud)
Type: subscription
Evidence: - 2025-11-12 -13.99
2025-11-28 -13.99
Merchant: YouTube Premium
Type: fee
Evidence: - 2025-11-08 -1.36
Merchant: International transaction fee
Type: fee
Evidence: - 2025-11-18 -29.00
Merchant: Late payment fee
Actual Model Response
Let's analyze the provided bank statement for account_id: CC-7781 during the period 2025-11 to identify:
Recurring subscriptions 2. Hidden or unexpected fees 3. Potential cost-saving opportunities
---
🔍 Transaction Breakdown
| Date | Description | Amount (USD) | Notes |
|------------|--------------------------------------|--------------|-------|
| 2025-11-01 | APPLE.COM/BILL | -9.99 | Likely Apple subscription (e.g., Apple Music, iCloud) |
| 2025-11-03 | UBER TRIP HELP.UBER.COM | -18.27 | One-time ride or service fee (not recurring) |
| 2025-11-08 | INTL TRANSACTION FEE | -1.36 | Fee for international transaction (one-time) |
| 2025-11-12 | GOOGLE *YouTubePremium | -13.99 | YouTube Premium subscription |
| 2025-11-16 | APPLE.COM/BILL | -9.99 | Recurring Apple charge |
| 2025-11-18 | LATE PAYMENT FEE | -29.00 | Unexpected fee — could indicate missed payment |
| 2025-11-25 | APPLE.COM/BILL | -9.99 | Recurring Apple charge |
| 2025-11-28 | YouTubePremium | -13.99 | Recurring Google YouTube Premium charge |
---
✅ Recurring Subscriptions (Identified)
| Service | Frequency | Monthly Cost | Notes |
|---------------------|----------|--------------|-------|
| Apple (Apple.com/BILL) | Monthly | $9.99 | Appears on 3 dates: 11-01, 11-16, 11-25 → likely monthly subscription (e.g., Apple Music, iCloud, or Apple TV+) |
| YouTube Premium | Monthly | $13.99 | Charged on 11-12 and 11-28 → confirms recurring monthly subscription |
> 💡 Total Monthly Subscription Cost: > $9.99 (Apple) + $13.99 (YouTube Premium) = $23.98/month
> ⚠️ Note: The Apple charge appears to be recurring every ~10–15 days. This may suggest a monthly billing cycle with a 30-day cycle, but the frequency is slightly irregular. It's possible the billing is set to auto-renew every month, and the dates are just not perfectly aligned.
---
⚠️ Hidden or Unexpected Fees
| Fee Type | Amount | Notes |
|------------------------|--------|-------|
| International Transaction Fee | $1.36 | One-time fee — not recurring, but could be a red flag if frequent |
| Late Payment Fee | $29.00 | Highly unusual — $29 is a significant fee. This is not typical for most banks. |
> 🔍 Analysis of Late Payment Fee:
> - A $29 late fee is very high and suggests either:
> - A missed payment on a loan or credit card (not a typical bank account fee)
> - A misclassification of a transaction (e.g., a payment due date was missed)
> - A potential error in the statement or in the user's payment history
> - This fee is not tied to any subscription and appears to be a one-time penalty.
> 🚩 Recommendation: > Verify the source of the late payment fee. > - Check if this was due to a missed payment on a loan, credit card, or another account. > - Contact the bank or financial institution to confirm whether this fee was applied correctly. > - If it was due to a missed payment, consider setting up payment reminders or automatic payments.
---
📊 Summary & Recommendations
✅ What’s Clear:
Two recurring subscriptions: Apple ($9.99/month) and YouTube Premium ($13.99/month)
Total recurring cost: $23.98/month
⚠️ What to Investigate:
Late Payment Fee ($29.00): This is not typical and may be an error or due to a missed obligation.
Test this model
Sign in to run your own test cases against this model.
Capabilities
Related models
Frequently asked questions
Does Cash Flow Ref work with CRM systems?
Yes. Cash Flow Ref is built to work with CRM systems, internal docs, and CSV/JSON pipelines. Most teams connect existing APIs or scheduled exports and map records into prompt-ready JSON.
What data format does this model accept?
You can send plain text or structured JSON. For bank stmt auditor, teams usually pass normalized records with field names, context notes, and output constraints.
Why use a task-specific SLM for bank stmt auditor?
Task-specific SLMs are tuned for one business outcome, so they are often more consistent and cost-efficient than general models for repetitive production workflows.
Try This Model
Send a message to try the model
Use via API
FreeView API settings and get a free key. Sign up when you want more keys or billing access.
Need better performance?
We can fine-tune this model on your data for higher accuracy on your specific use case.