# Choosing the LLM model

> Select which AI model processes your requests in Delegate, from the models your organization has enabled.

Select the model from the dropdown next to the chatbox — the AI model that processes your requests, set by your organization by default:

![Model picker dropdown showing available models with capability and cost indicators](https://dev-assets.cms.uipath.com/assets/images/delegate/model-picker-dropdown-2bce2852.webp)

## Selected model

The model determines Delegate's reasoning quality, speed, and capabilities. Which models are available, and which one is used by default for new conversations, is set by your organization — see [Governance with Automation Ops](centralized-configuration.md) — and depends on your UiPath tenant configuration. You can change the model for your own session if the model you want is enabled.

**Available models by provider:**

| Provider | Models |
|---|---|
| **Anthropic (Claude)** | Claude Sonnet 5, Claude Opus 4.8 |
| **Azure OpenAI** | GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna |
| **Google (Gemini)** | Gemini 3.6 Flash |
| **Moonshot AI** | Kimi K2.7 Code |

Your organization can also bring its own model instead of using the models listed above — see [Configuring LLMs](https://docs.uipath.com/automation-cloud/automation-cloud/latest/admin-guide/configuring-llms) for how to set this up.

:::important
A model must be enabled both in **AI Trust Layer → Models** and through an Automation Ops policy to be usable in Delegate. AI Trust Layer is the source of truth: if a model is allowed by policy but its provider is disabled in AI Trust Layer, it is not available. See also AI Trust Layer → PII & Guardrails and AI Trust Layer → Regions for related tenant-level controls.
:::