# Switching from another decision API

> Switch to the Launchables Decision API from another decision API: keep your requests on /v1/systemone, change the address and key, compare on your own labelled cases, then move to /v1/decide.

Section: Get started. Web page: https://www.launchables.ai/docs/switching

If you already call a decision API that takes a situation and typed questions and returns probabilities, you can try Myles without rewriting your client. This page covers the shortest path: keep your requests, change the address and key, compare on your own cases, then move over.

## 1. Keep your requests

`POST https://api.launchables.ai/v1/systemone` accepts the same request as [`POST /v1/decide`](https://www.launchables.ai/docs/api/decide) and returns the same response, in the shape existing decision-model clients expect. In most clients only two settings change:

- **The base address:** `https://api.launchables.ai`.
- **The key:** a Launchables key from the [console](https://console.launchables.ai), sent as a bearer token (see [Authentication](https://www.launchables.ai/docs/authentication)). Keys work once the account has prepaid credit.

Add `"model": "myles-g-12b"` or `"model": "myles-g-31b"` to each request so you know which model answered. See [Model library](https://www.launchables.ai/docs/models) for the difference.

## 2. What is different

- **Extra fields in answers.** `choice` and `score` answers also carry `confidence`, and `score` answers carry `legend`. Clients that ignore fields they do not know see no change.
- **Calibrated probabilities.** Thresholds set against another model's scores will not carry over unchanged. Set them again on your own cases (step 3).
- **Committed yes/no answers.** Uncertain yes/no answers are reported at least 0.80 towards the chosen side; see [noul](https://www.launchables.ai/docs/question-types#noul-yes-or-no).
- **Billing.** Input tokens only, output free, from prepaid credit in pounds. See [Pricing](https://www.launchables.ai/docs/pricing).
- **Limits.** 1,200 requests a minute per key by default, up to 16 questions per request. See [Errors and limits](https://www.launchables.ai/docs/api/errors).

The full list of accepted variations is in [Compatibility](https://www.launchables.ai/docs/api/decide#compatibility).

## 3. Compare on your own cases

Before switching traffic, send the same labelled sample to both APIs and compare. A few hundred real cases, each with the answer a careful person would give, are enough to see the difference in accuracy and in how often each one is confidently wrong.

```
import json, os, requests

CASES = [json.loads(line) for line in open("labelled.jsonl")]   # {"request": {...}, "label": "billing"}

def ask(url, token, request):
    reply = requests.post(url, json=request, timeout=60,
                          headers={"Authorization": f"Bearer {token}"})
    reply.raise_for_status()
    return reply.json()["answers"]["route"]

right = confident_wrong = 0
for case in CASES:
    request = {**case["request"], "model": "myles-g-12b"}
    answer = ask("https://api.launchables.ai/v1/systemone", os.environ["LAUNCHABLES_API_TOKEN"], request)
    right += answer["choice"] == case["label"]
    confident_wrong += answer["choice"] != case["label"] and answer["probabilities"][answer["choice"]] >= 0.9
print(f"accuracy {right / len(CASES):.1%}, confidently wrong {confident_wrong / len(CASES):.1%}")
```

Run the same loop against your current provider and compare the two lines. Then choose thresholds as described in [Acting on the answer](https://www.launchables.ai/docs/thresholds).

## 4. Move to /v1/decide

When you are ready, change the path from `/v1/systemone` to `/v1/decide`. The request and response stay the same, and new features are documented against `/v1/decide` first. The [Python](https://www.launchables.ai/docs/sdk-python) and [JavaScript](https://www.launchables.ai/docs/sdk-javascript) SDKs call it for you.

## Need help?

For a larger migration, or to compare on data that cannot leave your network, [contact us](https://www.launchables.ai/contact?about=api).