# Hosted API

> The hosted Decision API on api.launchables.ai: price per million input tokens, prepaid credit, key limits and what happens to your data.

Section: Deploy. Web page: https://www.launchables.ai/docs/deploy/hosted

## Endpoint and price

| Model | Address | Price |
|---|---|---|
| Myles-G 12B `myles-g-12b` | `api.launchables.ai` | £0.0015 per million input tokens; output tokens free |
| Myles-G 31B `myles-g-31b` | `gw.launchables.ai` | £0.0015 per million input tokens; output tokens free |

To call Myles-G 31B, send `"model": "myles-g-31b"` to `https://gw.launchables.ai/v1/decide`. That address serves every hosted model (Myles-G 12B too, with `"model": "myles-g-12b"` or no model), and the same keys work at both addresses. Myles-G 31B reads text and images, with a context window of 16,384 tokens; Myles-G 12B has 32,768.

The response's `usage.input_tokens` is what you are billed for. A typical decision is about 700 input tokens, so a million decisions costs about £1.05. Prices exclude VAT; UK VAT is added at checkout.

## Access

Create a key in the [console](https://console.launchables.ai) and buy prepaid credit there, from £5 by card, with optional automatic top-up. Credit never expires. Keys work once the account has credit and pause when it runs out, until you top it up.

By default each key can make 1,200 requests a minute, with no daily cap. A workspace can set its own per-key limit in the [console](https://www.launchables.ai/docs/console). [Ask us](https://www.launchables.ai/contact?about=api) for a higher limit.

## Your data

The endpoint does not store states, questions or answers. Its access log records only the method, the path, the status and the time taken. If your data cannot leave your network at all, run Myles [on your own hardware](https://www.launchables.ai/docs/deploy/self-hosting).