> ## Documentation Index
> Fetch the complete documentation index at: https://docs.synapsai.cloud/llms.txt
> Use this file to discover all available pages before exploring further.

# Custom image

> Launch a model from your own container image, GPU count, VRAM, and launch arguments

Choose **Custom image** in the [launch wizard](https://platform.synapsai.cloud/launch-model) when managed Hugging Face / artifact loading is not enough. You bring a container that already serves HTTP. SynapsAI schedules GPUs and **proxies** traffic to it.

## What you configure

| Field | Notes |
| - | - |
| Display name | Required |
| Image | Container image reference the platform can pull |
| GPU count | Positive integer |
| VRAM (MB) | Positive integer |
| Launch args | String or JSON array passed to the container |
| Minimum / maximum workers | Scaling (custom image defaults are often max 1, cooldown 300s) |
| Scale-up threshold / cooldown | Same ideas as managed models |

Pricing is **hourly** only. Per-token is not available for custom images.

## How you call it

Managed models use `/v1/...`. Custom containers are reached **without** the `/v1` prefix:

```
https://api.synapsai.cloud/{model_id}
https://api.synapsai.cloud/{model_id}/{path}
```

`GET`, `POST`, `PUT`, `PATCH`, `DELETE`, `OPTIONS`, and `HEAD` are proxied. Authenticate with the same [API key](/manage/api-keys) as other inference.

Reserved first path segments (`v1`, `webhooks`, `metrics`, `docs`, …) are not custom-container routes.

If the container streams, send `Accept: text/event-stream` or a JSON body with `stream` / `stream_format`.

## After launch

The model appears on [Models](https://platform.synapsai.cloud/models) like any other deployment: Usage, Logs, Instances, Configuration, Manage. See [Manage models](/manage/model) and [Autoscaling](/manage/autoscaling).

<Card title="Managed launch instead" icon="box" href="/guides/deploy-model">
  Hugging Face or artifact, OpenAI-compatible `/v1` endpoints.
</Card>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.