Performance & cost
This session
- Delivery time · median
- —
- Live model compute
- —
- Live input tokens
- 0
- Est. cost · USD
- $0.00
Bypass examples to measure live inference. Uses your quota.
Measurement details · 0 successful requests
- Successful requests
- 0
Run an example for free to see its measurements.
Model compute is the average per measured request. Delivery time is the median browser time for successful requests, including queue, network, and retries. Cached delivery speed is not inference speed. Model compute can exceed browser time when one request processes many inputs.
Tokens come from response headers. Inference costs use $0.04 per million input tokens, before plan credits. The estimate includes live and recorded tokens at the same rate; cached examples are not charged again. Missing usage is unavailable or a partial total (≥). Demo resets keep these totals; reload to start a new session.
Detect personal details, then choose what to redact.
Build with the SDKTypeScript · Python · dm1
One request from this demo. Copy it into your app.
Uses your MS_API_KEY and quota. Keep the key on your server.
npm install @cloudraker/milliseconds
export MS_API_KEY="your-api-key"import { DecisionMachine } from "@cloudraker/milliseconds";
// Run on your server; reads MS_API_KEY from the environment.
const dm = new DecisionMachine();
const { result, usage } = await dm.entities(
"Customer: Hi, I’m Maya Chen. The weekly export stops at 80%.\n\nAgent: I can send a reproduction to our integration vendor. Which account is affected?\n\nCustomer: My email is maya.chen@example.com and my account is NW-2048. You can call +1 202 555 0148.\n\nAgent: Thanks. We can reproduce this when the date filter is set to last month. The workaround is to export one week at a time.",
{
"person": "A person’s full name",
"email": "An email address",
"phone": "A telephone number",
"account_id": "A customer account, order, or ticket identifier",
"address": "A street or postal address"
}
).withUsage();
console.log(result);
console.log({ inputTokens: usage.inputTokens, modelMs: usage.inferenceMs });pip install cloudraker-milliseconds
export MS_API_KEY="your-api-key"from milliseconds import DecisionMachine
# Reads MS_API_KEY from the environment.
dm = DecisionMachine()
result = dm.entities(
"Customer: Hi, I’m Maya Chen. The weekly export stops at 80%.\n\nAgent: I can send a reproduction to our integration vendor. Which account is affected?\n\nCustomer: My email is maya.chen@example.com and my account is NW-2048. You can call +1 202 555 0148.\n\nAgent: Thanks. We can reproduce this when the date filter is set to last month. The workaround is to export one week at a time.",
{
"person": "A person’s full name",
"email": "An email address",
"phone": "A telephone number",
"account_id": "A customer account, order, or ticket identifier",
"address": "A street or postal address"
}
)
print(result)npm install -g @cloudraker/milliseconds
export MS_API_KEY="your-api-key"# Reads MS_API_KEY. JSON on stdin supplies the complete request.
dm1 entities --json --usage <<'DM1_REQUEST'
{
"text": "Customer: Hi, I’m Maya Chen. The weekly export stops at 80%.\n\nAgent: I can send a reproduction to our integration vendor. Which account is affected?\n\nCustomer: My email is maya.chen@example.com and my account is NW-2048. You can call +1 202 555 0148.\n\nAgent: Thanks. We can reproduce this when the date filter is set to last month. The workaround is to export one week at a time.",
"types": {
"person": "A person’s full name",
"email": "An email address",
"phone": "A telephone number",
"account_id": "A customer account, order, or ticket identifier",
"address": "A street or postal address"
}
}
DM1_REQUESTUnder the hood How it works & limitations
API calls/entities
Keep the context. Review the details.
The entities endpoint looks for names, emails, phone numbers, account or order IDs, and street addresses. The demo checks every returned span against the original text before highlighting it. Your selections are replaced with literal [REDACTED] markers; overlapping selections are merged.
Detection is a starting point
Models can miss sensitive details or mark harmless text. Review the entire transcript, add missed text, and remove unnecessary selections before exporting. This demo does not certify that text is anonymous. Live detection sends the transcript to the milliseconds API; sample review and manual redactions run in your browser.