Generative Financial Scenarios

Generate reproducible governed financial stress scenarios from an approved FinanceGPT VAE.

Version: v2

Stability: stable

Sandbox: Available

Production: Entitlement required

Target latency: ≤ 1,800 ms

POST/api/v2/ml/scenarios

Scenario generations are stress-test samples, not forecasts or probabilities. Synthetic peer benchmarking remains disabled.

Required scope: ml:inference

Try it in the FinanceGPT sandbox

The playground uses deterministic isolated sandbox fixtures. It never queries production workspace data and does not require you to paste an API secret into the browser.

Example response

{
    "data": {
        "type": "scenario_generation",
        "output": {
            "samples": [
                {
                    "revenue_growth": -0.059999999999999997779553950749686919152736663818359375,
                    "net_margin": 0.11000000000000000055511151231257827021181583404541015625,
                    "current_ratio": 1.350000000000000088817841970012523233890533447265625
                }
            ]
        }
    }
}

Code examples

curl

curl -X POST \
  https://financegpt.dev/api/v2/ml/scenarios \
  -H "Authorization: Bearer $FINANCEGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"samples":5,"stress":{"revenue_growth":-0.1000000000000000055511151231257827021181583404541015625}}'

python

import os, requests

url = "https://financegpt.dev/api/v2/ml/scenarios"
headers = {"Authorization": f"Bearer {os.environ['FINANCEGPT_API_KEY']}"}
payload = {
    "samples": 5,
    "stress": {
        "revenue_growth": -0.1000000000000000055511151231257827021181583404541015625
    }
}
response = requests.request("POST", url, headers=headers, json=payload)
response.raise_for_status()
print(response.json())

javascript

const response = await fetch('https://financegpt.dev/api/v2/ml/scenarios', {
  method: 'POST',
  headers: { Authorization: `Bearer ${process.env.FINANCEGPT_API_KEY}`, 'Content-Type': 'application/json' },
  body: JSON.stringify({"samples":5,"stress":{"revenue_growth":-0.1000000000000000055511151231257827021181583404541015625}})
});
if (!response.ok) throw new Error(`FinanceGPT ${response.status}`);
console.log(await response.json());

php

<?php
$ch = curl_init('https://financegpt.dev/api/v2/ml/scenarios');
curl_setopt_array($ch, [CURLOPT_RETURNTRANSFER => true, CURLOPT_CUSTOMREQUEST => 'POST', CURLOPT_HTTPHEADER => ['Authorization: Bearer '.getenv('FINANCEGPT_API_KEY'), 'Content-Type: application/json'], CURLOPT_POSTFIELDS => '{\"samples\":5,\"stress\":{\"revenue_growth\":-0.1000000000000000055511151231257827021181583404541015625}}']);
$response = curl_exec($ch);
if (curl_getinfo($ch, CURLINFO_HTTP_CODE) >= 400) throw new RuntimeException($response);
echo $response;

Versions & changelog

v2 published

M15 publication of this governed FinanceGPT API operation.

Ready to build?

Explorer gives immediate isolated sandbox access. Production plans require a commercial entitlement.

Create account