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

# Connect TRAE to LLMEasy with a custom model

> Connect LLMEasy to TRAE with GPT Key group model IDs.

When connecting LLMEasy to TRAE, choose an OpenAI-style provider and use a model ID from the GPT Key group.

## Prerequisites

* LLMEasy API Key (<a href={"https://www.llmeasy.ru/register"}>register here</a>)

## Setup

<Steps>
  <Step title="Open settings">
    In **IDE** mode, click the **Settings** icon in the upper-right corner to open the settings center.

    You can also open **SOLO** mode and click the **Settings** icon in the upper-right corner of the chat panel.
  </Step>

  <Step title="Open the model panel">
    In the left navigation, choose **Model** to open the **Model** panel.
  </Step>

  <Step title="Add a model">
    Click **+ Add model**.

    <img src="https://mintcdn.com/bettertoken/ejT8e_A0sPBKAOtG/images/trae/add-model.png?fit=max&auto=format&n=ejT8e_A0sPBKAOtG&q=85&s=69cce818086c1e77400c7d8e5db40083" alt="The TRAE model panel with the settings entry, model navigation item, and add model button highlighted." width="3024" height="1898" data-path="images/trae/add-model.png" />
  </Step>

  <Step title="Fill in the model configuration">
    When the **Add model** window appears, fill in the fields as follows:

    | Field              | Value                                                                                                   |
    | ------------------ | ------------------------------------------------------------------------------------------------------- |
    | Provider           | `OpenAI`                                                                                                |
    | Model              | `Custom model`                                                                                          |
    | Model ID           | a **GPT Key group** model ID copied from the <a href={"https://www.llmeasy.ru/pricing"}>model plaza</a> |
    | API key            | your API Key copied from the LLMEasy console                                                            |
    | Custom request URL | `https://www.llmeasy.ru/v1/chat/completions`                                                            |

    <img src="https://mintcdn.com/bettertoken/ejT8e_A0sPBKAOtG/images/trae/model-config.png?fit=max&auto=format&n=ejT8e_A0sPBKAOtG&q=85&s=7df53cbba88bee2d6ecdf588fcd5e3f7" alt="The TRAE add model window with OpenAI selected, a custom model selected, and fields for model ID, API key, and custom request URL." width="1638" height="1686" data-path="images/trae/model-config.png" />
  </Step>

  <Step title="Save and start using it">
    Click **Confirm** to save the configuration, then choose the new GPT Key group model.
  </Step>
</Steps>

<Note>
  LLMEasy only supports TRAE through **GPT Key group** models. Do not use fixed Claude model names, and do not set the custom request URL to `https://www.llmeasy.ru/v1`.
</Note>

## Related FAQ

* [OpenAI-compatible API vs Anthropic-compatible API](/en/faq/concepts/openai-compatible-vs-anthropic-compatible)
* [MCP vs API Key and Base URL](/en/faq/concepts/mcp-vs-api-key-base-url)
* [What are model\_provider, base\_url, and wire\_api?](/en/faq/codex/model-provider-base-url-wire-api)
* [How to configure an OpenAI-compatible API in Cline](/en/faq/cline/openai-compatible-api)