---
title: "Try it in the Admin UI"
url: "/docs/decisions/admin_ui"
canonical_url: "https://docs.litellm.ai/docs/decisions/admin_ui"
type: "docs"
last_updated: "2026-10-20"
related:
  - "/docs/decisions/benchmark"
  - "/docs/guides/compatibility_extensibility"
---
# Try it in the Admin UI

> Index of all LiteLLM docs: https://docs.litellm.ai/llms.txt


## Add a decision model

Go to **Models + Endpoints**, open the **Add Model** tab and pick the provider, for example OpenAI. Pick the decision model under **LiteLLM Model Name(s)**, for example `gpt-6-luna`, and a **Decision model** note confirms the pick and links to the Decisions playground. Enter the provider credentials as you would for any other model, then click **Add Model**. The model then answers on `/v1/decisions` and `/v1/systemone` under its public model name. Providers that need an endpoint URL, such as Databricks and Microsoft Foundry, take it in the **API Base** field, matching the `api_base` in the [proxy setup](./index.md#proxy-setup). The optional **Mode** dropdown has a **Decisions - /v1/decisions** entry from `v1.107.0-rc.1`, named **Evaluation - /v1/decisions** in `v1.106.0`, for health checking the model over `/v1/decisions`.

[Image: Add Model with OpenAI and gpt-6-luna picked, showing the Decision model note]

## Decisions playground

The Playground **Decisions** tab sends requests to both routes. Open it at `LITELLM_PROXY_BASE_URL/ui/?page=llm-playground&tab=system-one`, or go to **Playground** and pick **Decisions**. The **Endpoint** selector picks `/v1/decisions` (OpenAI Decisions format) or `/v1/systemone` (System One format), and the **Model** selector lists the decision models in your `model_list`, such as `jev` or `luna` from the [proxy setup](./index.md#proxy-setup); a proxy with no decision models shows an **Add a decision model** link instead. Both endpoints have a **Form** tab for building the request without JSON and a **JSON** tab for the raw request. Image input on `/v1/decisions` is edited in JSON, since the form keeps `messages` and image parts as they are. **Virtual Key Source** picks the key: **Current UI Session** uses your dashboard login and **Virtual Key** attributes the call to a key you paste. Once the call returns, each question shows its answer and probabilities, with the model the provider reported, token usage, latency and the raw JSON response under them.

[Image: Decisions playground with /v1/systemone picked, the jev model, the Form tab and the answers for the issue triage example]

[Image: Decisions playground with /v1/decisions picked, showing the OpenAI Decisions form with predicate, choice and score questions]

The tab is not in `v1.104.2` or `v1.105.0`. Releases before this UI change label it **System One** and only send the System One format, so use curl or the SDK for `/v1/decisions` there. The [TypeSafe page](../pass_through/typesafe.md#try-it-in-the-admin-ui) walks through the System One form, validation and answer view.

## Related pages

- [Benchmark](https://docs.litellm.ai/docs/decisions/benchmark.md)
- [Compatibility](https://docs.litellm.ai/docs/guides/compatibility_extensibility.md)