Conditional Financial Scenarios

Generate reproducible financial feature scenarios conditioned on contraction, neutral or expansion regimes.

Version: v2

Stability: stable

Sandbox: Available

Production: Entitlement required

Target latency: ≤ 1,800 ms

POST/api/v2/generative/scenarios

Regime conditioning is learned from derived financial-ratio training data. Outputs are synthetic stress-test inputs, not forecasts or probabilities.

Required scope: generative: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": {
        "run_uid": "00000000-0000-4000-8000-000000000020",
        "generation_type": "conditional_scenario",
        "regime": "contraction",
        "seed": 42,
        "output": {
            "samples": [
                {
                    "revenue_growth": -0.08000000000000000166533453693773481063544750213623046875,
                    "net_margin": -0.01000000000000000020816681711721685132943093776702880859375
                }
            ]
        }
    }
}

Code examples

curl

curl -X POST \
  https://financegpt.dev/api/v2/generative/scenarios \
  -H "Authorization: Bearer $FINANCEGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"samples":5,"regime":"contraction","seed":42,"stress":{"current_ratio":-0.1499999999999999944488848768742172978818416595458984375}}'

python

import os, requests

url = "https://financegpt.dev/api/v2/generative/scenarios"
headers = {"Authorization": f"Bearer {os.environ['FINANCEGPT_API_KEY']}"}
payload = {
    "samples": 5,
    "regime": "contraction",
    "seed": 42,
    "stress": {
        "current_ratio": -0.1499999999999999944488848768742172978818416595458984375
    }
}
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/generative/scenarios', {
  method: 'POST',
  headers: { Authorization: `Bearer ${process.env.FINANCEGPT_API_KEY}`, 'Content-Type': 'application/json' },
  body: JSON.stringify({"samples":5,"regime":"contraction","seed":42,"stress":{"current_ratio":-0.1499999999999999944488848768742172978818416595458984375}})
});
if (!response.ok) throw new Error(`FinanceGPT ${response.status}`);
console.log(await response.json());

php

<?php
$ch = curl_init('https://financegpt.dev/api/v2/generative/scenarios');
curl_setopt_array($ch, [CURLOPT_RETURNTRANSFER => true, CURLOPT_CUSTOMREQUEST => 'POST', CURLOPT_HTTPHEADER => ['Authorization: Bearer '.getenv('FINANCEGPT_API_KEY'), 'Content-Type: application/json'], CURLOPT_POSTFIELDS => '{\"samples\":5,\"regime\":\"contraction\",\"seed\":42,\"stress\":{\"current_ratio\":-0.1499999999999999944488848768742172978818416595458984375}}']);
$response = curl_exec($ch);
if (curl_getinfo($ch, CURLINFO_HTTP_CODE) >= 400) throw new RuntimeException($response);
echo $response;

Versions & changelog

v2 published

M20 publication of this governed FinanceGPT API operation.

Ready to build?

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

Create account