All demosEvidence Check

Evidence Check

Does the record match the source? Check before you copy.

Performance & cost

This session

Ready to run

Delivery time · median: —
Live model compute: —
Live input tokens: 0
Est. cost · USD: $0.00

Use my key for every request

Bypass examples to measure live inference. Uses your quota.

Measurement details · 0 successful requests

Successful requests: 0

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.

Try it

Check the record, then open a flagged field.

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.

API request

Install · set your key

npm install @cloudraker/milliseconds
export MS_API_KEY="your-api-key"

example.ts

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.verify(
  "SERVICE AGREEMENT\n\nCustomer: Northstar Design Ltd.\nAnnual fee: USD 18,000.\nRenewal date: 2027-03-01.\n\nServices include hosting and priority support.",
  {
    "name": "customer",
    "description": "The customer company named in the service agreement"
  },
  "Northstar Design Ltd."
).withUsage();

console.log(result);
console.log({ inputTokens: usage.inputTokens, modelMs: usage.inferenceMs });

Install · set your key

pip install cloudraker-milliseconds
export MS_API_KEY="your-api-key"

example.py

from milliseconds import DecisionMachine

# Reads MS_API_KEY from the environment.
dm = DecisionMachine()

result = dm.verify(
    "SERVICE AGREEMENT\n\nCustomer: Northstar Design Ltd.\nAnnual fee: USD 18,000.\nRenewal date: 2027-03-01.\n\nServices include hosting and priority support.",
    {
      "name": "customer",
      "description": "The customer company named in the service agreement"
    },
    "Northstar Design Ltd."
)

print(result)

Install · set your key

npm install -g @cloudraker/milliseconds
export MS_API_KEY="your-api-key"

Terminal

# Reads MS_API_KEY. JSON on stdin supplies the complete request.
dm1 verify --json --usage <<'DM1_REQUEST'
{
  "text": "SERVICE AGREEMENT\n\nCustomer: Northstar Design Ltd.\nAnnual fee: USD 18,000.\nRenewal date: 2027-03-01.\n\nServices include hosting and priority support.",
  "field": {
    "name": "customer",
    "description": "The customer company named in the service agreement"
  },
  "value": "Northstar Design Ltd."
}
DM1_REQUEST

Under the hood How it works & limitations

API calls/verify

Check the record before it travels

Review a contract summary, imported record or extracted field against supplied text. Each populated field makes one verify request. The demo locates the returned wording in the source and applies a conservative match rule.

Demo scope

This is field-value checking, not general fact-checking or a hallucination detector. A model can select the wrong field, miss a value or accept a partial match. “Different value” is a review prompt, not proof of contradiction. The 0.90 span-confidence threshold is a demo policy, not a measured accuracy rate. No external systems are updated.